---
title: "AI Model Rankings & API Price Comparison | Undominated.ai"
canonical: https://undominated.ai/
description: "Rank 364 AI models by independently measured capability, then compare what they actually cost across 55 providers. 92% of rated, priced models have another on the list that scores at least as high, costs no more, and wins on one of the two."
---

# AI Model Rankings & API Price Comparison | Undominated.ai

> Rank 364 AI models by independently measured capability, then compare what they actually cost across 55 providers. 92% of rated, priced models have another on the list that scores at least as high, costs no more, and wins on one of the two.

# Best models first. Then what they cost.

**133** of **145** rated, priced standard models have a higher-scoring or cheaper alternative, with neither dimension worse. They cost a median **6.7×** the cheapest such alternative. **12** are Undominated .

[Check a model](/check/) [Audit a bill](/audit/) [Subscription vs API](/plans/)

364 models · 55 providers · 51 with tiered pricing · verified 2026-10-06

 Best for Everything Websites · 116 Code categories · 109 Game development · 109 Data visualisation · 108 UI components · 107 3D · 101 SVG · 79 ASCII art · 63 Mobile apps · 42 Full-stack apps · 41 Web apps · 40 Native Android apps · 36 Godot games · 34 Workload Balanced Summarise Chat Code gen Agentic Prompt size Short 33K 200K 300K Measured on General Document
 145 ranked · 213 unrated · 6 batch or free only

 Advanced filters Refine Frontier only Tool use Reasoning Open weights Show batch & free Worth shopping around

 Filter these results
 Sort Rank Score ↓ Score ↑ Effective $/M ↑ Effective $/M ↓ Model A–Z Model Z–A Context ↓ Context ↑ Released ↓ Released ↑ Density Compact Comfortable Detailed share this view

4 models share #1 — the benchmark can't separate them. The cheapest, **Claude Opus 5.5**, costs $8.00/M , 2.5× less than **Claude Fable 5.1**.

 [Skip past model table](#after-model-table)

A model’s rank is 1 + the number of models that clearly beat it. Ranks count the models listed here. LMArena ranks gemini-4-argon-high (1533.5) above all of them: not ranked here, because not in the price feed this site reads. [How they work](/methodology/#ranks)

When a cache-read rate is unlisted, blended estimates use the selected tier’s full input rate.

AI models ranked by General capability, then by price for a Balanced workload.

| # | Model | General ▾ 95% interval Axis 1471–1524, following the rows in view 1471–1524 1480 1490 1500 1510 1520 | Effective $/M ▾ | Context | Capabilities | Verdict | Side by side |
| --- | --- | --- | --- | --- | --- | --- | --- |
| =1 4 models share rank 1 — the benchmark can't separate them $8.00–$20.00 /M · cheapest Claude Opus 5.5 | | | | | | | |
| =1 | [Claude Opus 5.5 Anthropic](/models/anthropic__claude-opus-5.5/) | 1511.7 | $8.00 $4.00 in · $20.00 out | 1M | Reasoning Tools | Undominated nothing better for less | [⇄](/compare/?models=anthropic%2Fclaude-opus-5.5) |
| =1 | [Claude Fable 5.1 Anthropic](/models/anthropic__claude-fable-5.1/) | 1510.6 | $20.00 $10.00 in · $50.00 out | 1M | Reasoning Tools | [Pick Claude Opus 5.5 +1.1, within error](/models/anthropic__claude-opus-5.5/) 60% cheaper · +1.1, within error | [⇄](/compare/?models=anthropic%2Fclaude-fable-5.1) |
| =1 | [Claude Opus 4.6 Anthropic](/models/anthropic__claude-opus-4.6/) | 1503.2 | $10.00 $5.00 in · $25.00 out | 1M | Reasoning Tools | [Pick Claude Opus 5.5 +8.5, within error](/models/anthropic__claude-opus-5.5/) 20% cheaper · +8.5, within error | [⇄](/compare/?models=anthropic%2Fclaude-opus-4.6) |
| =1 | [Claude Opus 5 Anthropic](/models/anthropic__claude-opus-5/) | 1502.1 | $10.00 $5.00 in · $25.00 out | 1M | Reasoning Tools | [Pick Claude Opus 5.5 +9.6, within error](/models/anthropic__claude-opus-5.5/) 20% cheaper · +9.6, within error | [⇄](/compare/?models=anthropic%2Fclaude-opus-5) |
| =3 2 models share rank 3 — the benchmark can't separate them $0.540–$3.00 /M · cheapest MiMo-V2.6-Pro | | | | | | | |
| =3 | [Gemini 3.8 Flash Google](/models/google__gemini-3.8-flash/) | 1497.0 | $3.00 + reasoning billed $1.50 in · $7.50 out | 1M | Reasoning Tools | Undominated nothing better for less | [⇄](/compare/?models=google%2Fgemini-3.8-flash) |
| =3 | [MiMo-V2.6-Pro Xiaomi](/models/xiaomi__mimo-v2.6-pro/) | 1491.0 | $0.540 $0.430 in · $0.870 out | 1M | Reasoning Tools | Undominated nothing better for less | [⇄](/compare/?models=xiaomi%2Fmimo-v2.6-pro) |
| =5 5 models share rank 5 — the benchmark can't separate them $2.00–$20.00 /M · cheapest Muse Spark 1.3 | | | | | | | |
| =5 | [Claude Fable 5 Anthropic](/models/anthropic__claude-fable-5/) | 1491.7 | $20.00 $10.00 in · $50.00 out | 1M | Reasoning Tools | [Pick Claude Opus 5.5](/models/anthropic__claude-opus-5.5/) 60% cheaper · +20.0 | [⇄](/compare/?models=anthropic%2Fclaude-fable-5) |
| =5 | [Muse Spark 1.3 Meta](/models/meta__muse-spark-1.3/) | 1489.9 | $2.00 $1.25 in · $4.25 out | 1M | Reasoning Tools | [Pick MiMo-V2.6-Pro +1.1, within error shorter max output +1](/models/xiaomi__mimo-v2.6-pro/) 73% cheaper · +1.1, within error | [⇄](/compare/?models=meta%2Fmuse-spark-1.3) |
| =5 | [Claude Opus 4.7 Anthropic](/models/anthropic__claude-opus-4.7/) | 1489.9 | $10.00 $5.00 in · $25.00 out | 1M | Reasoning Tools | [Pick Claude Opus 5.5](/models/anthropic__claude-opus-5.5/) 20% cheaper · +21.8 | [⇄](/compare/?models=anthropic%2Fclaude-opus-4.7) |
| =5 | [Gemini 3.7 Flash Google](/models/google__gemini-3.7-flash/) | 1487.0 | $3.00 + reasoning billed $1.50 in · $7.50 out | 1M | Reasoning Tools | [Pick Gemini 3.8 Flash +10.0, within error](/models/google__gemini-3.8-flash/) same price · +10.0, within error | [⇄](/compare/?models=google%2Fgemini-3.7-flash) |
| =5 | [Muse Spark 1.2 Meta](/models/meta__muse-spark-1.2/) | 1483.2 | $2.00 $1.25 in · $4.25 out | 1M | Reasoning Tools | [Pick Muse Spark 1.3 +6.7, within error](/models/meta__muse-spark-1.3/) same price · +6.7, within error | [⇄](/compare/?models=meta%2Fmuse-spark-1.2) |
| 8 | [Gemini 3.6 Flash Google](/models/google__gemini-3.6-flash/) | 1479.5 | $1.50 + reasoning billed $0.750 in · $3.75 out | 1M | Reasoning Tools | [Pick MiMo-V2.6-Pro +11.5, within error no file input](/models/xiaomi__mimo-v2.6-pro/) 64% cheaper · +11.5, within error | [⇄](/compare/?models=google%2Fgemini-3.6-flash) |
| =9 2 models share rank 9 — the benchmark can't separate them $2.00–$4.50 /M · cheapest Muse Spark 1.1 | | | | | | | |
| =9 | [Gemini 3.1 Pro Preview Google](/models/google__gemini-3.1-pro-preview/) | 1480.2 | $4.50 tiered + reasoning billed $2.00 in · $12.00 out | 1M | Reasoning Tools | [Pick Gemini 3.8 Flash](/models/google__gemini-3.8-flash/) 33% cheaper · +16.8 | [⇄](/compare/?models=google%2Fgemini-3.1-pro-preview) |
| =9 | [Muse Spark 1.1 Meta](/models/meta__muse-spark-1.1/) | 1479.2 | $2.00 $1.25 in · $4.25 out | 1M | Reasoning Tools | [Pick Muse Spark 1.3](/models/meta__muse-spark-1.3/) same price · +10.7 | [⇄](/compare/?models=meta%2Fmuse-spark-1.1) |
| 10 | [Gemini 3.5 Flash Google](/models/google__gemini-3.5-flash/) | 1477.7 | $3.38 + reasoning billed $1.50 in · $9.00 out | 1M | Reasoning Tools | [Pick Gemini 3.8 Flash](/models/google__gemini-3.8-flash/) 11% cheaper · +19.3 | [⇄](/compare/?models=google%2Fgemini-3.5-flash) |
| 11 | [Kimi K3 Moonshot AI](/models/moonshotai__kimi-k3/) | 1475.9 | $3.76 $0.680 in · $13.00 out | 1M | Reasoning Tools | [Pick Muse Spark 1.3](/models/meta__muse-spark-1.3/) 47% cheaper · +14.0 | [⇄](/compare/?models=moonshotai%2Fkimi-k3) |
| =12 2 models share rank 12 — the benchmark can't separate them $1.00–$4.00 /M · cheapest GLM 5.3 | | | | | | | |
| =12 | [GLM 5.3 Z.ai](/models/z-ai__glm-5.3/) | 1471.4 | $1.00 $0.200 in · $3.40 out | 1M | Reasoning Tools | [Pick MiMo-V2.6-Pro shorter max output](/models/xiaomi__mimo-v2.6-pro/) 46% cheaper · +19.6 | [⇄](/compare/?models=z-ai%2Fglm-5.3) |
| =12 | [Claude Sonnet 5.5 Anthropic](/models/anthropic__claude-sonnet-5.5/) | 1466.6 | $4.00 $2.00 in · $10.00 out | 1M | Reasoning Tools | [Pick Muse Spark 1.3](/models/meta__muse-spark-1.3/) 50% cheaper · +23.3 | [⇄](/compare/?models=anthropic%2Fclaude-sonnet-5.5) |
| 13 | [GLM 5.3 Flash Z.ai](/models/z-ai__glm-5.3-flash/) | 1469.6 | $0.238 $0.150 in · $0.500 out | 1M | Reasoning Tools | Undominated nothing better for less | [⇄](/compare/?models=z-ai%2Fglm-5.3-flash) |
| 14 | [GLM 5.2 Z.ai](/models/z-ai__glm-5.2/) | 1470.4 | $1.12 $0.309 in · $3.55 out | 1M | Reasoning Tools | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 52% cheaper · +20.6 | [⇄](/compare/?models=z-ai%2Fglm-5.2) |
| =17 3 models share rank 17 — the benchmark can't separate them $0.182–$11.25 /M · cheapest DeepSeek V4.1 Flash | | | | | | | |
| =17 | [GPT-5.5 OpenAI](/models/openai__gpt-5.5/) | 1466.8 | $11.25 tiered $5.00 in · $30.00 out | 1M | Reasoning Tools | [Pick Claude Opus 5.5 smaller context](/models/anthropic__claude-opus-5.5/) 29% cheaper · +44.9 | [⇄](/compare/?models=openai%2Fgpt-5.5) |
| =17 | [MiMo-V2.5-Pro Xiaomi](/models/xiaomi__mimo-v2.5-pro/) | 1465.0 | $0.544 $0.435 in · $0.870 out | 1M | Reasoning Tools | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 1% cheaper · +26.0 | [⇄](/compare/?models=xiaomi%2Fmimo-v2.5-pro) |
| =17 | [DeepSeek V4.1 Flash DeepSeek](/models/deepseek__deepseek-v4.1-flash/) | 1462.5 | $0.182 $0.053 in · $0.570 out | 1M | Reasoning Tools | Undominated nothing better for less | [⇄](/compare/?models=deepseek%2Fdeepseek-v4.1-flash) |
| =19 2 models share rank 19 — the benchmark can't separate them $1.83–$10.00 /M · cheapest GLM 5.1 | | | | | | | |
| =19 | [GLM 5.1 Z.ai](/models/z-ai__glm-5.1/) | 1461.5 | $1.83 $1.19 in · $3.74 out | 204K | Reasoning Tools | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 70% cheaper · +29.5 | [⇄](/compare/?models=z-ai%2Fglm-5.1) |
| =19 | [Claude Opus 4.8 Anthropic](/models/anthropic__claude-opus-4.8/) | 1461.0 | $10.00 $5.00 in · $25.00 out | 1M | Reasoning Tools | [Pick Claude Opus 5.5](/models/anthropic__claude-opus-5.5/) 20% cheaper · +50.7 | [⇄](/compare/?models=anthropic%2Fclaude-opus-4.8) |
| 20 | [MiMo-V2.6-Flash Xiaomi](/models/xiaomi__mimo-v2.6-flash/) | 1456.4 | $0.175 $0.140 in · $0.280 out | 1M | Reasoning Tools | Undominated nothing better for less | [⇄](/compare/?models=xiaomi%2Fmimo-v2.6-flash) |
| =22 5 models share rank 22 — the benchmark can't separate them $0.560–$8.00 /M · cheapest Qwen3.7 Plus | | | | | | | |
| =22 | [Gemini 2.5 Pro Google](/models/google__gemini-2.5-pro/) retires Oct 20, 2026 | 1457.8 | $3.44 tiered + reasoning billed $1.25 in · $10.00 out | 1M | Reasoning Tools | [Pick Gemini 3.8 Flash](/models/google__gemini-3.8-flash/) 13% cheaper · +39.2 | [⇄](/compare/?models=google%2Fgemini-2.5-pro) |
| =22 | [Claude Sonnet 4.6 Anthropic](/models/anthropic__claude-sonnet-4.6/) | 1457.8 | $6.00 $3.00 in · $15.00 out | 1M | Reasoning Tools | [Pick Muse Spark 1.3](/models/meta__muse-spark-1.3/) 67% cheaper · +32.1 | [⇄](/compare/?models=anthropic%2Fclaude-sonnet-4.6) |
| =22 | [GPT-5.6 Sol OpenAI](/models/openai__gpt-5.6-sol/) | 1456.3 | $8.00 tiered $4.00 in · $20.00 out | 1M | Reasoning Tools | [Pick Claude Opus 5.5 smaller context](/models/anthropic__claude-opus-5.5/) same price · +55.4 | [⇄](/compare/?models=openai%2Fgpt-5.6-sol) |
| =22 | [Kimi K2.6 Moonshot AI](/models/moonshotai__kimi-k2.6/) | 1455.5 | $0.961 $0.465 in · $2.45 out | 262K | Reasoning Tools | [Pick GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) 75% cheaper · +14.1 | [⇄](/compare/?models=moonshotai%2Fkimi-k2.6) |
| =22 | [Qwen3.7 Plus Qwen](/models/qwen__qwen3.7-plus/) | 1454.6 | $0.560 tiered $0.320 in · $1.28 out | 1M | Reasoning Tools | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 4% cheaper · +36.4 | [⇄](/compare/?models=qwen%2Fqwen3.7-plus) |
| =25 2 models share rank 25 — the benchmark can't separate them $4.00–$5.63 /M · cheapest GPT-6.1 Sol | | | | | | | |
| =25 | [GPT-5.4 OpenAI](/models/openai__gpt-5.4/) | 1452.2 | $5.63 tiered $2.50 in · $15.00 out | 1M | Reasoning Tools | [Pick Gemini 3.8 Flash smaller context +1](/models/google__gemini-3.8-flash/) 47% cheaper · +44.8 | [⇄](/compare/?models=openai%2Fgpt-5.4) |
| =25 | [GPT-6.1 Sol OpenAI](/models/openai__gpt-6.1-sol/) | 1445.6 | $4.00 tiered $2.00 in · $10.00 out | 1M | Reasoning Tools | [Pick Gemini 3.8 Flash smaller context +1](/models/google__gemini-3.8-flash/) 25% cheaper · +51.4 | [⇄](/compare/?models=openai%2Fgpt-6.1-sol) |
| 27 | [Qwen3.6 Max Preview Qwen](/models/qwen__qwen3.6-max-preview/) retires Oct 9, 2026 | 1446.8 | $2.31 tiered $1.03 in · $6.16 out | 262K | Reasoning Tools | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 77% cheaper · +44.2 | [⇄](/compare/?models=qwen%2Fqwen3.6-max-preview) |
| =28 2 models share rank 28 — the benchmark can't separate them $3.00–$10.00 /M · cheapest Grok 4.5 | | | | | | | |
| =28 | [Claude Opus 4.5 Anthropic](/models/anthropic__claude-opus-4.5/) | 1451.0 | $10.00 $5.00 in · $25.00 out | 200K | Reasoning Tools | [Pick Claude Opus 5.5](/models/anthropic__claude-opus-5.5/) 20% cheaper · +60.7 | [⇄](/compare/?models=anthropic%2Fclaude-opus-4.5) |
| =28 | [Grok 4.5 xAI](/models/x-ai__grok-4.5/) | 1448.1 | $3.00 tiered $2.00 in · $6.00 out | 500K | Reasoning Tools | [Pick Muse Spark 1.3](/models/meta__muse-spark-1.3/) 33% cheaper · +41.8 | [⇄](/compare/?models=x-ai%2Fgrok-4.5) |
| 29 | [DeepSeek V4 Pro 0423 DeepSeek](/models/deepseek__deepseek-v4-pro/) | 1445.2 | $1.21 $0.450 in · $3.48 out | 1M | Reasoning Tools | [Pick GLM 5.3](/models/z-ai__glm-5.3/) 17% cheaper · +26.2 | [⇄](/compare/?models=deepseek%2Fdeepseek-v4-pro) |
| =30 3 models share rank 30 — the benchmark can't separate them $0.205–$4.50 /M · cheapest Gemma 4 31B | | | | | | | |
| =30 | [GLM 5 Z.ai](/models/z-ai__glm-5/) | 1446.3 | $1.09 $0.700 in · $2.24 out | 204K | Reasoning Tools | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 50% cheaper · +44.7 | [⇄](/compare/?models=z-ai%2Fglm-5) |
| =30 | [GPT-5.6 Terra OpenAI](/models/openai__gpt-5.6-terra/) | 1446.3 | $4.50 tiered $2.00 in · $12.00 out | 1M | Reasoning Tools | [Pick Gemini 3.8 Flash smaller context +1](/models/google__gemini-3.8-flash/) 33% cheaper · +50.7 | [⇄](/compare/?models=openai%2Fgpt-5.6-terra) |
| =30 | [Gemma 4 31B Google](/models/google__gemma-4-31b-it/) | 1443.4 | $0.205 $0.140 in · $0.400 out | 262K | Reasoning Tools | [Pick MiMo-V2.6-Flash +13.0, within error](/models/xiaomi__mimo-v2.6-flash/) 15% cheaper · +13.0, within error | [⇄](/compare/?models=google%2Fgemma-4-31b-it) |
| 31 | [GPT-6 Astra OpenAI](/models/openai__gpt-6-astra/) | 1442.3 | $20.00 tiered $10.00 in · $50.00 out | 1M | Reasoning Tools | [Pick GPT-5.5](/models/openai__gpt-5.5/) 44% cheaper · +24.5 | [⇄](/compare/?models=openai%2Fgpt-6-astra) |
| 33 | [Kimi K2.5 Moonshot AI](/models/moonshotai__kimi-k2.5/) | 1445.2 | $1.20 $0.600 in · $3.00 out | 262K | Reasoning Tools | [Pick GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) 80% cheaper · +24.4 | [⇄](/compare/?models=moonshotai%2Fkimi-k2.5) |
| =34 5 models share rank 34 — the benchmark can't separate them $0.231–$4.00 /M · cheapest Hy3 | | | | | | | |
| =34 | [Claude Sonnet 5 Anthropic](/models/anthropic__claude-sonnet-5/) | 1442.9 | $4.00 $2.00 in · $10.00 out | 1M | Reasoning Tools | [Pick Muse Spark 1.3](/models/meta__muse-spark-1.3/) 50% cheaper · +47.0 | [⇄](/compare/?models=anthropic%2Fclaude-sonnet-5) |
| =34 | [Inkling Thinking Machines](/models/thinkingmachines__inkling/) | 1441.8 | $1.73 $0.950 in · $4.05 out | 524K | Reasoning Tools | [Pick MiMo-V2.6-Pro shorter max output](/models/xiaomi__mimo-v2.6-pro/) 69% cheaper · +49.2 | [⇄](/compare/?models=thinkingmachines%2Finkling) |
| =34 | [Hy3 Tencent](/models/tencent__hy3/) | 1440.7 | $0.231 time-of-day rates $0.132 in · $0.528 out | 262K | Reasoning Tools | [Pick DeepSeek V4.1 Flash](/models/deepseek__deepseek-v4.1-flash/) 21% cheaper · +21.8 | [⇄](/compare/?models=tencent%2Fhy3) |
| =34 | [Qwen3.8 27B Qwen](/models/qwen__qwen3.8-27b/) | 1440.7 | $0.562 $0.089 in · $1.98 out | 1M | Reasoning Tools | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 4% cheaper · +50.3 | [⇄](/compare/?models=qwen%2Fqwen3.8-27b) |
| =34 | [GLM 4.6 Z.ai](/models/z-ai__glm-4.6/) | 1439.9 | $0.760 $0.430 in · $1.75 out | 204K | Reasoning Tools | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 29% cheaper · +51.1 | [⇄](/compare/?models=z-ai%2Fglm-4.6) |
| 35 | [GLM 5V Turbo Z.ai](/models/z-ai__glm-5v-turbo/) | 1437.2 | $1.90 $1.20 in · $4.00 out | 202K | Reasoning Tools | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 72% cheaper · +53.8 | [⇄](/compare/?models=z-ai%2Fglm-5v-turbo) |
| =38 6 models share rank 38 — the benchmark can't separate them $0.127–$6.00 /M · cheapest Gemma 4 26B A4B | | | | | | | |
| =38 | [Claude Sonnet 4.5 Anthropic](/models/anthropic__claude-sonnet-4.5/) | 1438.6 | $6.00 tiered $3.00 in · $15.00 out | 1M | Reasoning Tools | [Pick Gemini 3.8 Flash](/models/google__gemini-3.8-flash/) 50% cheaper · +58.4 | [⇄](/compare/?models=anthropic%2Fclaude-sonnet-4.5) |
| =38 | [Qwen3.5 397B A17B Qwen](/models/qwen__qwen3.5-397b-a17b/) | 1438.0 | $0.878 $0.390 in · $2.34 out | 262K | Reasoning Tools | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 38% cheaper · +53.0 | [⇄](/compare/?models=qwen%2Fqwen3.5-397b-a17b) |
| =38 | [Qwen3.6 Plus Qwen](/models/qwen__qwen3.6-plus/) | 1436.7 | $0.731 tiered $0.325 in · $1.95 out | 1M | Reasoning Tools | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 26% cheaper · +54.3 | [⇄](/compare/?models=qwen%2Fqwen3.6-plus) |
| =38 | [GLM 4.7 Z.ai](/models/z-ai__glm-4.7/) retires Dec 31, 2026 | 1435.5 | $0.738 $0.400 in · $1.75 out | 204K | Reasoning Tools | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 27% cheaper · +55.5 | [⇄](/compare/?models=z-ai%2Fglm-4.7) |
| =38 | [Gemini 3.5 Flash Lite Google](/models/google__gemini-3.5-flash-lite/) | 1434.7 | $0.850 + reasoning billed $0.300 in · $2.50 out | 1M | Reasoning Tools | [Pick MiMo-V2.6-Pro no file input](/models/xiaomi__mimo-v2.6-pro/) 36% cheaper · +56.3 | [⇄](/compare/?models=google%2Fgemini-3.5-flash-lite) |
| =38 | [Gemma 4 26B A4B Google](/models/google__gemma-4-26b-a4b-it/) | 1433.9 | $0.127 $0.069 in · $0.300 out | 262K | Reasoning Tools | Undominated nothing better for less | [⇄](/compare/?models=google%2Fgemma-4-26b-a4b-it) |
| =42 2 models share rank 42 — the benchmark can't separate them $0.113–$0.485 /M · cheapest DeepSeek V4 Flash 0423 | | | | | | | |
| =42 | [DeepSeek V4 Flash 0423 DeepSeek](/models/deepseek__deepseek-v4-flash/) | 1432.1 | $0.113 $0.090 in · $0.180 out | 1M | Reasoning Tools | Undominated nothing better for less | [⇄](/compare/?models=deepseek%2Fdeepseek-v4-flash) |
| =42 | [MiniMax M3 MiniMax](/models/minimax__minimax-m3/) | 1432.1 | $0.485 $0.280 in · $1.10 out | 1M | Reasoning Tools | [Pick GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) 51% cheaper · +37.5 | [⇄](/compare/?models=minimax%2Fminimax-m3) |
| 46 | [GPT-5.6 Luna OpenAI](/models/openai__gpt-5.6-luna/) | 1431.0 | $0.450 tiered $0.200 in · $1.20 out | 1M | Reasoning Tools | [Pick GLM 5.3 Flash smaller context +1](/models/z-ai__glm-5.3-flash/) 47% cheaper · +38.6 | [⇄](/compare/?models=openai%2Fgpt-5.6-luna) |
| 47 | [GLM 4.5 Z.ai](/models/z-ai__glm-4.5/) retires Dec 31, 2026 | 1430.3 | $1.00 $0.600 in · $2.20 out | 131K | Reasoning Tools | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 46% cheaper · +60.7 | [⇄](/compare/?models=z-ai%2Fglm-4.5) |
| 50 | [R1 0528 DeepSeek](/models/deepseek__deepseek-r1-0528/) | 1427.9 | $0.920 $0.500 in · $2.18 out | 163K | Reasoning Tools | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 41% cheaper · +63.1 | [⇄](/compare/?models=deepseek%2Fdeepseek-r1-0528) |
| =51 2 models share rank 51 — the benchmark can't separate them $0.175–$3.00 /M · cheapest MiMo-V2.5 | | | | | | | |
| =51 | [MiMo-V2.5 Xiaomi](/models/xiaomi__mimo-v2.5/) | 1427.5 | $0.175 $0.140 in · $0.280 out | 1M | Reasoning Tools | [Pick MiMo-V2.6-Flash](/models/xiaomi__mimo-v2.6-flash/) same price · +28.9 | [⇄](/compare/?models=xiaomi%2Fmimo-v2.5) |
| =51 | [Grok 4.6 xAI](/models/x-ai__grok-4.6/) | 1427.4 | $3.00 tiered $2.00 in · $6.00 out | 500K | Reasoning Tools | [Pick Muse Spark 1.3](/models/meta__muse-spark-1.3/) 33% cheaper · +62.5 | [⇄](/compare/?models=x-ai%2Fgrok-4.6) |
| 54 | [DeepSeek V3.2 Exp DeepSeek](/models/deepseek__deepseek-v3.2-exp/) | 1422.4 | $0.305 $0.270 in · $0.410 out | 163K | Reasoning Tools | [Pick GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) 22% cheaper · +47.2 | [⇄](/compare/?models=deepseek%2Fdeepseek-v3.2-exp) |
| =56 3 models share rank 56 — the benchmark can't separate them $0.290–$3.00 /M · cheapest DeepSeek V3.2 | | | | | | | |
| =56 | [DeepSeek V3.2 DeepSeek](/models/deepseek__deepseek-v3.2/) | 1424.5 | $0.290 $0.260 in · $0.380 out | 163K | Reasoning Tools | [Pick GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) 18% cheaper · +45.1 | [⇄](/compare/?models=deepseek%2Fdeepseek-v3.2) |
| =56 | [Mistral Medium 3.5 Mistral](/models/mistralai__mistral-medium-3-5/) | 1421.2 | $3.00 $1.50 in · $7.50 out | 262K | Reasoning Tools | [Pick Muse Spark 1.3](/models/meta__muse-spark-1.3/) 33% cheaper · +68.7 | [⇄](/compare/?models=mistralai%2Fmistral-medium-3-5) |
| =56 | [DeepSeek V3.1 Terminus DeepSeek](/models/deepseek__deepseek-v3.1-terminus/) | 1417.1 | $0.453 $0.270 in · $1.00 out | 163K | Reasoning Tools | [Pick GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) 48% cheaper · +52.5 | [⇄](/compare/?models=deepseek%2Fdeepseek-v3.1-terminus) |
| 57 | [Qwen3 VL 235B A22B Instruct Qwen](/models/qwen__qwen3-vl-235b-a22b-instruct/) | 1420.1 | $0.370 $0.200 in · $0.880 out | 262K | Tools | [Pick GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) 36% cheaper · +49.5 | [⇄](/compare/?models=qwen%2Fqwen3-vl-235b-a22b-instruct) |
| =58 2 models share rank 58 — the benchmark can't separate them $0.453–$3.44 /M · cheapest DeepSeek V3.1 | | | | | | | |
| =58 | [GPT-5.1 OpenAI](/models/openai__gpt-5.1/) | 1422.2 | $3.44 $1.25 in · $10.00 out | 400K | Reasoning Tools | [Pick Muse Spark 1.3](/models/meta__muse-spark-1.3/) 42% cheaper · +67.7 | [⇄](/compare/?models=openai%2Fgpt-5.1) |
| =58 | [DeepSeek V3.1 DeepSeek](/models/deepseek__deepseek-chat-v3.1/) | 1419.7 | $0.453 $0.270 in · $1.00 out | 163K | Reasoning Tools | [Pick GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) 48% cheaper · +49.9 | [⇄](/compare/?models=deepseek%2Fdeepseek-chat-v3.1) |
| =62 5 models share rank 62 — the benchmark can't separate them $0.205–$30.00 /M · cheapest Qwen3 235B A22B Instruct 2507 | | | | | | | |
| =62 | [Qwen3 235B A22B Instruct 2507 Qwen](/models/qwen__qwen3-235b-a22b-2507/) | 1419.3 | $0.205 $0.090 in · $0.550 out | 262K | Tools | [Pick DeepSeek V4.1 Flash](/models/deepseek__deepseek-v4.1-flash/) 11% cheaper · +43.2 | [⇄](/compare/?models=qwen%2Fqwen3-235b-a22b-2507) |
| =62 | [Claude Opus 4.1 Anthropic](/models/anthropic__claude-opus-4.1/) | 1418.6 | $30.00 $15.00 in · $75.00 out | 200K | Reasoning Tools | [Pick Claude Opus 5.5](/models/anthropic__claude-opus-5.5/) 73% cheaper · +93.1 | [⇄](/compare/?models=anthropic%2Fclaude-opus-4.1) |
| =62 | [Qwen3 Next 80B A3B Instruct Qwen](/models/qwen__qwen3-next-80b-a3b-instruct/) | 1417.3 | $0.268 $0.098 in · $0.780 out | 262K | Tools | [Pick GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) 11% cheaper · +52.3 | [⇄](/compare/?models=qwen%2Fqwen3-next-80b-a3b-instruct) |
| =62 | [Qwen3.5-122B-A10B Qwen](/models/qwen__qwen3.5-122b-a10b/) | 1417.1 | $0.715 $0.260 in · $2.08 out | 262K | Reasoning Tools | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 24% cheaper · +73.9 | [⇄](/compare/?models=qwen%2Fqwen3.5-122b-a10b) |
| =62 | [Qwen3 235B A22B Thinking 2507 Qwen](/models/qwen__qwen3-235b-a22b-thinking-2507/) retires Oct 9, 2026 | 1415.2 | $0.748 $0.230 in · $2.30 out | 131K | Reasoning Tools | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 28% cheaper · +75.8 | [⇄](/compare/?models=qwen%2Fqwen3-235b-a22b-thinking-2507) |
| =63 3 models share rank 63 — the benchmark can't separate them $0.563–$1.56 /M · cheapest Gemini 3.1 Flash Lite Preview | | | | | | | |
| =63 | [Gemini 2.5 Flash Google](/models/google__gemini-2.5-flash/) retires Oct 20, 2026 | 1417.0 | $0.850 + reasoning billed $0.300 in · $2.50 out | 1M | Reasoning Tools | [Pick Gemini 3.5 Flash Lite](/models/google__gemini-3.5-flash-lite/) same price · +17.7 | [⇄](/compare/?models=google%2Fgemini-2.5-flash) |
| =63 | [Gemini 3.1 Flash Lite Preview Google](/models/google__gemini-3.1-flash-lite-preview/) | 1415.7 | $0.563 + reasoning billed $0.250 in · $1.50 out | 1M | Reasoning Tools | [Pick MiMo-V2.6-Pro no file input](/models/xiaomi__mimo-v2.6-pro/) 4% cheaper · +75.3 | [⇄](/compare/?models=google%2Fgemini-3.1-flash-lite-preview) |
| =63 | [Qwen3 Max Qwen](/models/qwen__qwen3-max/) retires Oct 9, 2026 | 1412.4 | $1.56 tiered $0.780 in · $3.90 out | 262K | Reasoning Tools | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 65% cheaper · +78.6 | [⇄](/compare/?models=qwen%2Fqwen3-max) |
| 64 | [Inkling Small Thinking Machines](/models/thinkingmachines__inkling-small/) | 1413.7 | $0.638 $0.450 in · $1.20 out | 524K | Reasoning Tools | [Pick MiMo-V2.6-Pro shorter max output](/models/xiaomi__mimo-v2.6-pro/) 15% cheaper · +77.3 | [⇄](/compare/?models=thinkingmachines%2Finkling-small) |
| =67 2 models share rank 67 — the benchmark can't separate them $1.69–$4.81 /M · cheapest GPT-5.4 Mini | | | | | | | |
| =67 | [GPT-5.2 OpenAI](/models/openai__gpt-5.2/) | 1412.3 | $4.81 $1.75 in · $14.00 out | 400K | Reasoning Tools | [Pick Muse Spark 1.3](/models/meta__muse-spark-1.3/) 58% cheaper · +77.6 | [⇄](/compare/?models=openai%2Fgpt-5.2) |
| =67 | [GPT-5.4 Mini OpenAI](/models/openai__gpt-5.4-mini/) | 1411.4 | $1.69 $0.750 in · $4.50 out | 400K | Reasoning Tools | [Pick GPT-5.6 Luna](/models/openai__gpt-5.6-luna/) 73% cheaper · +19.6 | [⇄](/compare/?models=openai%2Fgpt-5.4-mini) |
| =71 2 models share rank 71 — the benchmark can't separate them $0.536–$3.50 /M · cheapest Qwen3.5-27B | | | | | | | |
| =71 | [o3 OpenAI](/models/openai__o3/) | 1409.9 | $3.50 $2.00 in · $8.00 out | 200K | Reasoning Tools | [Pick Muse Spark 1.3](/models/meta__muse-spark-1.3/) 43% cheaper · +80.0 | [⇄](/compare/?models=openai%2Fo3) |
| =71 | [Qwen3.5-27B Qwen](/models/qwen__qwen3.5-27b/) | 1408.9 | $0.536 $0.195 in · $1.56 out | 262K | Reasoning Tools | [Pick GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) 56% cheaper · +60.7 | [⇄](/compare/?models=qwen%2Fqwen3.5-27b) |
| 74 | [GPT-5 OpenAI](/models/openai__gpt-5/) | 1406.1 | $3.44 $1.25 in · $10.00 out | 400K | Reasoning Tools | [Pick Muse Spark 1.3](/models/meta__muse-spark-1.3/) 42% cheaper · +83.8 | [⇄](/compare/?models=openai%2Fgpt-5) |
| 77 | [MiniMax M2.7 MiniMax](/models/minimax__minimax-m2.7/) | 1404.6 | $0.525 $0.300 in · $1.20 out | 204K | Reasoning Tools | [Pick GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) 55% cheaper · +65.0 | [⇄](/compare/?models=minimax%2Fminimax-m2.7) |
| =78 2 models share rank 78 — the benchmark can't separate them $1.30–$3.00 /M · cheapest Qwen3 VL 235B A22B Thinking | | | | | | | |
| =78 | [Qwen3 VL 235B A22B Thinking Qwen](/models/qwen__qwen3-vl-235b-a22b-thinking/) retires Oct 9, 2026 | 1400.7 | $1.30 $0.400 in · $4.00 out | 131K | Reasoning Tools | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 58% cheaper · +90.3 | [⇄](/compare/?models=qwen%2Fqwen3-vl-235b-a22b-thinking) |
| =78 | [Grok 4.7 xAI](/models/x-ai__grok-4.7/) | 1399.9 | $3.00 tiered $2.00 in · $6.00 out | 500K | Reasoning Tools | [Pick Muse Spark 1.3](/models/meta__muse-spark-1.3/) 33% cheaper · +90.0 | [⇄](/compare/?models=x-ai%2Fgrok-4.7) |
| 79 | [Step 3.5 Flash StepFun](/models/stepfun__step-3.5-flash/) | 1403.0 | $0.150 $0.100 in · $0.300 out | 262K | Reasoning Tools | [Pick Gemma 4 26B A4B](/models/google__gemma-4-26b-a4b-it/) 16% cheaper · +30.9 | [⇄](/compare/?models=stepfun%2Fstep-3.5-flash) |
| 82 | [GPT-6 Sol OpenAI](/models/openai__gpt-6-sol/) | 1395.4 | $4.00 tiered $2.00 in · $10.00 out | 1M | Reasoning Tools | [Pick GPT-6.1 Sol](/models/openai__gpt-6.1-sol/) same price · +50.2 | [⇄](/compare/?models=openai%2Fgpt-6-sol) |
| =84 2 models share rank 84 — the benchmark can't separate them $0.114–$1.56 /M · cheapest Qwen3.5-Flash | | | | | | | |
| =84 | [Qwen3.5-Flash Qwen](/models/qwen__qwen3.5-flash-02-23/) | 1397.0 | $0.114 $0.065 in · $0.260 out | 1M | Reasoning Tools | [Pick DeepSeek V4 Flash 0423 no image input +1](/models/deepseek__deepseek-v4-flash/) 1% cheaper · +35.1 | [⇄](/compare/?models=qwen%2Fqwen3.5-flash-02-23) |
| =84 | [Grok 4.3 xAI](/models/x-ai__grok-4.3/) | 1396.7 | $1.56 tiered $1.25 in · $2.50 out | 1M | Reasoning Tools | [Pick MiMo-V2.6-Pro shorter max output +1](/models/xiaomi__mimo-v2.6-pro/) 65% cheaper · +94.3 | [⇄](/compare/?models=x-ai%2Fgrok-4.3) |
| =85 3 models share rank 85 — the benchmark can't separate them $0.200–$2.00 /M · cheapest GPT-6 Luna | | | | | | | |
| =85 | [Claude Haiku 4.5 Anthropic](/models/anthropic__claude-haiku-4.5/) | 1396.1 | $2.00 $1.00 in · $5.00 out | 200K | Reasoning Tools | [Pick Muse Spark 1.3](/models/meta__muse-spark-1.3/) same price · +93.8 | [⇄](/compare/?models=anthropic%2Fclaude-haiku-4.5) |
| =85 | [Qwen3.5-35B-A3B Qwen](/models/qwen__qwen3.5-35b-a3b/) | 1394.4 | $0.355 $0.140 in · $1.00 out | 262K | Reasoning Tools | [Pick GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) 33% cheaper · +75.2 | [⇄](/compare/?models=qwen%2Fqwen3.5-35b-a3b) |
| =85 | [GPT-6 Luna OpenAI](/models/openai__gpt-6-luna/) | 1391.5 | $0.200 tiered $0.100 in · $0.500 out | 1M | Reasoning Tools | [Pick DeepSeek V4.1 Flash smaller context +1](/models/deepseek__deepseek-v4.1-flash/) 9% cheaper · +71.0 | [⇄](/compare/?models=openai%2Fgpt-6-luna) |
| 90 | [Solar Pro 4 Upstage](/models/upstage__solar-pro4/) | 1386.2 | $0.525 $0.300 in · $1.20 out | 524K | Reasoning Tools | [Pick GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) 55% cheaper · +83.4 | [⇄](/compare/?models=upstage%2Fsolar-pro4) |
| 91 | [Qwen3 30B A3B Instruct 2507 Qwen](/models/qwen__qwen3-30b-a3b-instruct-2507/) | 1384.1 | $0.143 $0.090 in · $0.300 out | 262K | Tools | [Pick Gemma 4 26B A4B](/models/google__gemma-4-26b-a4b-it/) 11% cheaper · +49.8 | [⇄](/compare/?models=qwen%2Fqwen3-30b-a3b-instruct-2507) |
| =92 3 models share rank 92 — the benchmark can't separate them $0.310–$3.50 /M · cheapest GLM 4.5 Air | | | | | | | |
| =92 | [GLM 4.5 Air Z.ai](/models/z-ai__glm-4.5-air/) | 1383.9 | $0.310 $0.130 in · $0.850 out | 131K | Reasoning Tools | [Pick GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) 23% cheaper · +85.7 | [⇄](/compare/?models=z-ai%2Fglm-4.5-air) |
| =92 | [GPT-4.1 OpenAI](/models/openai__gpt-4.1/) | 1383.0 | $3.50 $2.00 in · $8.00 out | 1M | Tools | [Pick Gemini 3.8 Flash](/models/google__gemini-3.8-flash/) 14% cheaper · +114.0 | [⇄](/compare/?models=openai%2Fgpt-4.1) |
| =92 | [GLM 4.6V Z.ai](/models/z-ai__glm-4.6v/) | 1376.8 | $0.450 $0.300 in · $0.900 out | 131K | Reasoning Tools | [Pick GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) 47% cheaper · +92.8 | [⇄](/compare/?models=z-ai%2Fglm-4.6v) |
| =97 6 models share rank 97 — the benchmark can't separate them $0.413–$1.15 /M · cheapest Qwen3 Next 80B A3B Thinking | | | | | | | |
| =97 | [DeepSeek V3 0324 DeepSeek](/models/deepseek__deepseek-chat-v3-0324/) | 1375.0 | $0.438 $0.250 in · $1.00 out | 163K | Tools | [Pick GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) 46% cheaper · +94.6 | [⇄](/compare/?models=deepseek%2Fdeepseek-chat-v3-0324) |
| =97 | [GPT-5 Mini OpenAI](/models/openai__gpt-5-mini/) | 1373.2 | $0.688 $0.250 in · $2.00 out | 400K | Reasoning Tools | [Pick GPT-5.6 Luna](/models/openai__gpt-5.6-luna/) 35% cheaper · +57.8 | [⇄](/compare/?models=openai%2Fgpt-5-mini) |
| =97 | [R1 DeepSeek](/models/deepseek__deepseek-r1/) | 1372.7 | $1.15 $0.700 in · $2.50 out | 64K | Reasoning Tools | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 53% cheaper · +118.3 | [⇄](/compare/?models=deepseek%2Fdeepseek-r1) |
| =97 | [GPT-5.4 Nano OpenAI](/models/openai__gpt-5.4-nano/) | 1372.1 | $0.463 $0.200 in · $1.25 out | 400K | Reasoning Tools | [Pick GPT-5.6 Luna](/models/openai__gpt-5.6-luna/) 3% cheaper · +58.9 | [⇄](/compare/?models=openai%2Fgpt-5.4-nano) |
| =97 | [Qwen3 Next 80B A3B Thinking Qwen](/models/qwen__qwen3-next-80b-a3b-thinking/) retires Oct 9, 2026 | 1368.3 | $0.413 $0.150 in · $1.20 out | 262K | Reasoning Tools | [Pick GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) 42% cheaper · +101.3 | [⇄](/compare/?models=qwen%2Fqwen3-next-80b-a3b-thinking) |
| =97 | [Qwen3 235B A22B Qwen](/models/qwen__qwen3-235b-a22b/) retires Oct 9, 2026 | 1366.6 | $0.796 $0.455 in · $1.82 out | 131K | Reasoning Tools | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 32% cheaper · +124.4 | [⇄](/compare/?models=qwen%2Fqwen3-235b-a22b) |
| =98 2 models share rank 98 — the benchmark can't separate them $0.065–$26.25 /M · cheapest gpt-oss-120b | | | | | | | |
| =98 | [o1 OpenAI](/models/openai__o1/) | 1365.8 | $26.25 $15.00 in · $60.00 out | 200K | Reasoning Tools | [Pick Claude Opus 5.5](/models/anthropic__claude-opus-5.5/) 70% cheaper · +145.9 | [⇄](/compare/?models=openai%2Fo1) |
| =98 | [gpt-oss-120b OpenAI](/models/openai__gpt-oss-120b/) | 1365.4 | $0.065 $0.030 in · $0.170 out | 131K | Reasoning Tools | Undominated nothing better for less | [⇄](/compare/?models=openai%2Fgpt-oss-120b) |
| 101 | [Nova 2 Lite Amazon](/models/amazon__nova-2-lite-v1/) | 1361.8 | $0.850 $0.300 in · $2.50 out | 1M | Reasoning Tools | [Pick Gemini 3.5 Flash Lite](/models/google__gemini-3.5-flash-lite/) same price · +72.9 | [⇄](/compare/?models=amazon%2Fnova-2-lite-v1) |
| =102 2 models share rank 102 — the benchmark can't separate them $0.375–$0.521 /M · cheapest Mercury 2 | | | | | | | |
| =102 | [MiniMax M2.5 MiniMax](/models/minimax__minimax-m2.5/) | 1359.3 | $0.521 $0.295 in · $1.20 out | 204K | Reasoning Tools | [Pick GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) 54% cheaper · +110.3 | [⇄](/compare/?models=minimax%2Fminimax-m2.5) |
| =102 | [Mercury 2 Inception](/models/inception__mercury-2/) | 1355.2 | $0.375 $0.250 in · $0.750 out | 128K | Reasoning Tools | [Pick GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) 37% cheaper · +114.4 | [⇄](/compare/?models=inception%2Fmercury-2) |
| 104 | [Gemma 3 27B Google](/models/google__gemma-3-27b-it/) | 1357.8 | $0.100 $0.080 in · $0.160 out | 131K | Tools | [Pick gpt-oss-120b +7.6, within error no image input](/models/openai__gpt-oss-120b/) 35% cheaper · +7.6, within error | [⇄](/compare/?models=google%2Fgemma-3-27b-it) |
| =106 2 models share rank 106 — the benchmark can't separate them $0.145–$1.93 /M · cheapest GLM 4.7 Flash | | | | | | | |
| =106 | [o4 Mini OpenAI](/models/openai__o4-mini/) | 1353.2 | $1.93 $1.10 in · $4.40 out | 200K | Reasoning Tools | [Pick GPT-5.6 Luna](/models/openai__gpt-5.6-luna/) 77% cheaper · +77.8 | [⇄](/compare/?models=openai%2Fo4-mini) |
| =106 | [GLM 4.7 Flash Z.ai](/models/z-ai__glm-4.7-flash/) | 1350.9 | $0.145 $0.060 in · $0.400 out | 200K | Reasoning Tools | [Pick Gemma 4 26B A4B](/models/google__gemma-4-26b-a4b-it/) 13% cheaper · +83.0 | [⇄](/compare/?models=z-ai%2Fglm-4.7-flash) |
| 109 | [Qwen3 32B Qwen](/models/qwen__qwen3-32b/) | 1340.1 | $0.130 $0.080 in · $0.280 out | 131K | Reasoning Tools | [Pick Gemma 4 26B A4B](/models/google__gemma-4-26b-a4b-it/) 3% cheaper · +93.8 | [⇄](/compare/?models=qwen%2Fqwen3-32b) |
| =110 2 models share rank 110 — the benchmark can't separate them $0.525–$0.850 /M · cheapest MiniMax M2 | | | | | | | |
| =110 | [MiniMax M1 MiniMax](/models/minimax__minimax-m1/) | 1342.8 | $0.850 $0.400 in · $2.20 out | 1M | Reasoning Tools | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 36% cheaper · +148.2 | [⇄](/compare/?models=minimax%2Fminimax-m1) |
| =110 | [MiniMax M2 MiniMax](/models/minimax__minimax-m2/) | 1339.9 | $0.525 $0.300 in · $1.20 out | 204K | Reasoning Tools | [Pick GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) 55% cheaper · +129.7 | [⇄](/compare/?models=minimax%2Fminimax-m2) |
| =112 6 models share rank 112 — the benchmark can't separate them $0.075–$6.00 /M · cheapest Gemma 3 12B | | | | | | | |
| =112 | [GPT-4.1 Mini OpenAI](/models/openai__gpt-4.1-mini/) | 1340.4 | $0.700 $0.400 in · $1.60 out | 1M | Tools | [Pick GPT-5.6 Luna](/models/openai__gpt-5.6-luna/) 36% cheaper · +90.6 | [⇄](/compare/?models=openai%2Fgpt-4.1-mini) |
| =112 | [Trinity Large Thinking Arcee](/models/arcee-ai__trinity-large-thinking/) | 1340.0 | $0.388 $0.250 in · $0.800 out | 262K | Reasoning Tools | [Pick GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) 39% cheaper · +129.6 | [⇄](/compare/?models=arcee-ai%2Ftrinity-large-thinking) |
| =112 | [Claude Sonnet 4 Anthropic](/models/anthropic__claude-sonnet-4/) | 1339.1 | $6.00 tiered $3.00 in · $15.00 out | 200K | Reasoning Tools | [Pick Gemini 3.8 Flash](/models/google__gemini-3.8-flash/) 50% cheaper · +157.9 | [⇄](/compare/?models=anthropic%2Fclaude-sonnet-4) |
| =112 | [o3 Mini High OpenAI](/models/openai__o3-mini-high/) | 1336.6 | $1.93 $1.10 in · $4.40 out | 200K | Reasoning Tools | [Pick GPT-5.6 Luna](/models/openai__gpt-5.6-luna/) 77% cheaper · +94.4 | [⇄](/compare/?models=openai%2Fo3-mini-high) |
| =112 | [Gemma 3 12B Google](/models/google__gemma-3-12b-it/) | 1334.2 | $0.075 $0.050 in · $0.150 out | 131K | Tools | [Pick gpt-oss-120b no image input](/models/openai__gpt-oss-120b/) 13% cheaper · +31.2 | [⇄](/compare/?models=google%2Fgemma-3-12b-it) |
| =112 | [GLM 4.5V Z.ai](/models/z-ai__glm-4.5v/) | 1332.8 | $0.900 $0.600 in · $1.80 out | 65K | Reasoning Tools | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 40% cheaper · +158.2 | [⇄](/compare/?models=z-ai%2Fglm-4.5v) |
| 113 | [DeepSeek V3 DeepSeek](/models/deepseek__deepseek-chat/) | 1332.5 | $0.500 $0.286 in · $1.14 out | 163K | Tools | [Pick GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) 53% cheaper · +137.1 | [⇄](/compare/?models=deepseek%2Fdeepseek-chat) |
| 119 | [Granite 4.2 8B IBM](/models/ibm-granite__granite-4.2-8b/) | 1317.8 | $0.108 $0.060 in · $0.250 out | 131K | Reasoning Tools | [Pick gpt-oss-120b](/models/openai__gpt-oss-120b/) 40% cheaper · +47.6 | [⇄](/compare/?models=ibm-granite%2Fgranite-4.2-8b) |
| 120 | [GPT-5 Nano OpenAI](/models/openai__gpt-5-nano/) | 1320.0 | $0.138 $0.050 in · $0.400 out | 400K | Reasoning Tools | [Pick Gemma 4 26B A4B smaller context +1](/models/google__gemma-4-26b-a4b-it/) 8% cheaper · +113.9 | [⇄](/compare/?models=openai%2Fgpt-5-nano) |
| =122 2 models share rank 122 — the benchmark can't separate them $0.215–$1.93 /M · cheapest Qwen3 30B A3B | | | | | | | |
| =122 | [o3 Mini OpenAI](/models/openai__o3-mini/) | 1319.4 | $1.93 $1.10 in · $4.40 out | 200K | Reasoning Tools | [Pick GPT-5.6 Luna](/models/openai__gpt-5.6-luna/) 77% cheaper · +111.6 | [⇄](/compare/?models=openai%2Fo3-mini) |
| =122 | [Qwen3 30B A3B Qwen](/models/qwen__qwen3-30b-a3b/) | 1316.6 | $0.215 $0.120 in · $0.500 out | 131K | Reasoning Tools | [Pick DeepSeek V4.1 Flash](/models/deepseek__deepseek-v4.1-flash/) 15% cheaper · +145.9 | [⇄](/compare/?models=qwen%2Fqwen3-30b-a3b) |
| =126 2 models share rank 126 — the benchmark can't separate them $0.063–$7.50 /M · cheapest Gemma 3 4B | | | | | | | |
| =126 | [GPT-4o (2024-05-13) OpenAI](/models/openai__gpt-4o-2024-05-13/) | 1300.4 | $7.50 $5.00 in · $15.00 out | 128K | Tools | [Pick Gemini 3.8 Flash](/models/google__gemini-3.8-flash/) 60% cheaper · +196.6 | [⇄](/compare/?models=openai%2Fgpt-4o-2024-05-13) |
| =126 | [Gemma 3 4B Google](/models/google__gemma-3-4b-it/) | 1290.8 | $0.063 $0.050 in · $0.100 out | 131K | | Undominated nothing better for less | [⇄](/compare/?models=google%2Fgemma-3-4b-it) |
| =127 4 models share rank 127 — the benchmark can't separate them $0.036–$4.38 /M · cheapest gpt-oss-20b | | | | | | | |
| =127 | [gpt-oss-20b OpenAI](/models/openai__gpt-oss-20b/) | 1287.7 | $0.036 $0.018 in · $0.090 out | 131K | Reasoning Tools | Undominated nothing better for less | [⇄](/compare/?models=openai%2Fgpt-oss-20b) |
| =127 | [GPT-4o-mini (2024-07-18) OpenAI](/models/openai__gpt-4o-mini-2024-07-18/) | 1286.4 | $0.263 $0.150 in · $0.600 out | 128K | Tools | [Pick GPT-6 Luna](/models/openai__gpt-6-luna/) 24% cheaper · +105.1 | [⇄](/compare/?models=openai%2Fgpt-4o-mini-2024-07-18) |
| =127 | [GPT-4.1 Nano OpenAI](/models/openai__gpt-4.1-nano/) | 1284.8 | $0.175 $0.100 in · $0.400 out | 1M | Tools | [Pick MiMo-V2.6-Flash no file input](/models/xiaomi__mimo-v2.6-flash/) same price · +171.6 | [⇄](/compare/?models=openai%2Fgpt-4.1-nano) |
| =127 | [GPT-4o (2024-08-06) OpenAI](/models/openai__gpt-4o-2024-08-06/) | 1282.5 | $4.38 $2.50 in · $10.00 out | 128K | Tools | [Pick Gemini 3.8 Flash](/models/google__gemini-3.8-flash/) 31% cheaper · +214.5 | [⇄](/compare/?models=openai%2Fgpt-4o-2024-08-06) |
| 131 | [Llama 3.3 70B Instruct Meta](/models/meta-llama__llama-3.3-70b-instruct/) | 1274.1 | $0.201 $0.135 in · $0.400 out | 131K | Tools | [Pick DeepSeek V4.1 Flash](/models/deepseek__deepseek-v4.1-flash/) 9% cheaper · +188.4 | [⇄](/compare/?models=meta-llama%2Fllama-3.3-70b-instruct) |
| =132 2 models share rank 132 — the benchmark can't separate them $0.370–$15.00 /M · cheapest Qwen2.5 72B Instruct | | | | | | | |
| =132 | [GPT-4 Turbo OpenAI](/models/openai__gpt-4-turbo/) | 1271.7 | $15.00 $10.00 in · $30.00 out | 128K | Tools | [Pick Claude Opus 5.5](/models/anthropic__claude-opus-5.5/) 47% cheaper · +240.0 | [⇄](/compare/?models=openai%2Fgpt-4-turbo) |
| =132 | [Qwen2.5 72B Instruct Qwen](/models/qwen__qwen-2.5-72b-instruct/) | 1269.0 | $0.370 $0.360 in · $0.400 out | 32K | Tools | [Pick GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) 36% cheaper · +200.6 | [⇄](/compare/?models=qwen%2Fqwen-2.5-72b-instruct) |
| 133 | [Mistral Large 2407 Mistral](/models/mistralai__mistral-large-2407/) | 1266.1 | $3.00 $2.00 in · $6.00 out | 131K | Tools | [Pick Muse Spark 1.3](/models/meta__muse-spark-1.3/) 33% cheaper · +223.8 | [⇄](/compare/?models=mistralai%2Fmistral-large-2407) |
| 135 | [Llama 3.1 70B Instruct Meta](/models/meta-llama__llama-3.1-70b-instruct/) | 1260.9 | $0.720 $0.720 in · $0.720 out | 131K | Tools | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 25% cheaper · +230.1 | [⇄](/compare/?models=meta-llama%2Fllama-3.1-70b-instruct) |
| =137 4 models share rank 137 — the benchmark can't separate them $0.058–$4.38 /M · cheapest Mistral Small 3 | | | | | | | |
| =137 | [Mistral Small 3 Mistral](/models/mistralai__mistral-small-24b-instruct-2501/) | 1233.6 | $0.058 $0.050 in · $0.080 out | 32K | | [Pick gpt-oss-20b](/models/openai__gpt-oss-20b/) 37% cheaper · +54.1 | [⇄](/compare/?models=mistralai%2Fmistral-small-24b-instruct-2501) |
| =137 | [Gemma 2 27B Google](/models/google__gemma-2-27b-it/) | 1231.3 | $0.650 $0.650 in · $0.650 out | 8K | | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 17% cheaper · +259.7 | [⇄](/compare/?models=google%2Fgemma-2-27b-it) |
| =137 | [Qwen2.5 Coder 32B Instruct Qwen](/models/qwen__qwen-2.5-coder-32b-instruct/) | 1230.0 | $0.745 $0.660 in · $1.00 out | 32K | | [Pick MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) 28% cheaper · +261.0 | [⇄](/compare/?models=qwen%2Fqwen-2.5-coder-32b-instruct) |
| =137 | [Command R+ (08-2024) Cohere](/models/cohere__command-r-plus-08-2024/) | 1228.9 | $4.38 $2.50 in · $10.00 out | 128K | Tools | [Pick Gemini 3.8 Flash](/models/google__gemini-3.8-flash/) 31% cheaper · +268.1 | [⇄](/compare/?models=cohere%2Fcommand-r-plus-08-2024) |
| 141 | [Phi 4 Microsoft](/models/microsoft__phi-4/) | 1216.7 | $0.088 $0.070 in · $0.140 out | 16K | | [Pick gpt-oss-120b](/models/openai__gpt-oss-120b/) 26% cheaper · +148.7 | [⇄](/compare/?models=microsoft%2Fphi-4) |
| =142 2 models share rank 142 — the benchmark can't separate them $0.025–$0.263 /M · cheapest Llama 3.1 8B Instruct | | | | | | | |
| =142 | [Command R (08-2024) Cohere](/models/cohere__command-r-08-2024/) | 1187.3 | $0.263 $0.150 in · $0.600 out | 128K | Tools | [Pick GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) 10% cheaper · +282.3 | [⇄](/compare/?models=cohere%2Fcommand-r-08-2024) |
| =142 | [Llama 3.1 8B Instruct Meta](/models/meta-llama__llama-3.1-8b-instruct/) | 1186.5 | $0.025 $0.020 in · $0.040 out | 131K | Tools | Undominated nothing better for less | [⇄](/compare/?models=meta-llama%2Fllama-3.1-8b-instruct) |
| 144 | [Llama 3.2 3B Instruct Meta](/models/meta-llama__llama-3.2-3b-instruct/) | 1109.5 | $0.120 $0.050 in · $0.330 out | 131K | | [Pick DeepSeek V4 Flash 0423](/models/deepseek__deepseek-v4-flash/) 6% cheaper · +322.6 | [⇄](/compare/?models=meta-llama%2Fllama-3.2-3b-instruct) |
| 145 | [Llama 3.2 1B Instruct Meta](/models/meta-llama__llama-3.2-1b-instruct/) | 1054.6 | $0.071 $0.027 in · $0.201 out | 60K | | [Pick gpt-oss-120b](/models/openai__gpt-oss-120b/) 8% cheaper · +310.8 | [⇄](/compare/?models=meta-llama%2Fllama-3.2-1b-instruct) |

## Just released, awaiting a score

 - [Nano Banana 2.1](/models/google__gemini-nano-banana-2.1/) Google · released Oct 6, 2026 $3.00/M · 65K context awaiting score
- [Mistral Large 4](/models/mistralai__mistral-large-4-0/) Mistral · released Oct 6, 2026 $2.07/M · 524K context awaiting score
- [Ling 3.1 Flash](/models/inclusionai__ling-3.1-flash/) inclusionAI · released Oct 2, 2026 free · 262K context awaiting score
- [Pareto 26.10 Preview](/models/unbiased__pareto-26.10-preview/) Unbiased · released Oct 1, 2026 $1.40/M · 1M context awaiting score

## 213 models have no score on this board

Grouped by maker, newest first. Unscored here is not the same as scored badly.

### OpenAI 35

 - [GPT-6.1 Sol Pro](/models/openai__gpt-6.1-sol-pro/) $4.00
- [GPT-6 Luna Pro](/models/openai__gpt-6-luna-pro/) $0.200
- [GPT-6 Sol Pro](/models/openai__gpt-6-sol-pro/) $4.00
 - [GPT-6 Astra Pro](/models/openai__gpt-6-astra-pro/) $20.00
- [GPT-5.6 Luna Pro](/models/openai__gpt-5.6-luna-pro/) $0.450
- [GPT-5.6 Sol Pro](/models/openai__gpt-5.6-sol-pro/) $8.00
- [GPT-5.6 Terra Pro](/models/openai__gpt-5.6-terra-pro/) $4.50
- [GPT Chat Latest](/models/openai__gpt-chat-latest/) $11.25
- [GPT-5.5 Pro](/models/openai__gpt-5.5-pro/) $67.50
- [GPT-5.4 Image 2](/models/openai__gpt-5.4-image-2/) $9.75
- [GPT-5.4 Pro](/models/openai__gpt-5.4-pro/) $67.50
- [GPT-5.3-Codex](/models/openai__gpt-5.3-codex/) $4.81
- [GPT Audio](/models/openai__gpt-audio/) $4.38
- [GPT Audio Mini](/models/openai__gpt-audio-mini/) $1.05
- [GPT-5.2-Codex](/models/openai__gpt-5.2-codex/) $4.81
- [GPT-5.2 Chat](/models/openai__gpt-5.2-chat/) $4.81
- [GPT-5.2 Pro](/models/openai__gpt-5.2-pro/) $57.75
- [GPT-5.1-Codex-Max](/models/openai__gpt-5.1-codex-max/) $3.44
- [GPT-5.1-Codex](/models/openai__gpt-5.1-codex/) $3.44
- [GPT-5.1-Codex-Mini](/models/openai__gpt-5.1-codex-mini/) $0.688
- [gpt-oss-safeguard-20b](/models/openai__gpt-oss-safeguard-20b/) $0.131
- [GPT-5 Image Mini](/models/openai__gpt-5-image-mini/) $2.38
- [GPT-5 Image](/models/openai__gpt-5-image/) $10.00
- [GPT-5 Pro](/models/openai__gpt-5-pro/) $41.25
- [o3 Pro](/models/openai__o3-pro/) $35.00
- [o4 Mini High](/models/openai__o4-mini-high/) $1.93
- [o1-pro](/models/openai__o1-pro/) $263
- [GPT-4o (2024-11-20)](/models/openai__gpt-4o-2024-11-20/) $4.38
- [GPT-4o-mini](/models/openai__gpt-4o-mini/) $0.263
- [GPT-4o](/models/openai__gpt-4o/) $4.38
- [GPT-3.5 Turbo (older v0613)](/models/openai__gpt-3.5-turbo-0613/) $1.25
- [GPT-3.5 Turbo Instruct](/models/openai__gpt-3.5-turbo-instruct/) $1.63
- [GPT-3.5 Turbo 16k](/models/openai__gpt-3.5-turbo-16k/) $3.25
- [GPT-3.5 Turbo](/models/openai__gpt-3.5-turbo/) $0.750
- [GPT-4](/models/openai__gpt-4/) $37.50

 +32 more

### Qwen 31

 - [Qwen3.8 Max Prime](/models/qwen__qwen3.8-max-prime/) $6.00
- [Qwen3.8 Omni Flash](/models/qwen__qwen3.8-omni-flash/) $0.230
- [Qwen3.8 Max (0902)](/models/qwen__qwen3.8-max-0902/) $3.00
 - [Qwen3.8 Flash](/models/qwen__qwen3.8-flash/) $0.230
- [Qwen3.8 2.4T A95B](/models/qwen__qwen3.8-2.4t-a95b/) $3.00
- [Qwen3.7 Flash](/models/qwen__qwen3.7-flash/) $0.055
- [Qwen3.7 Max](/models/qwen__qwen3.7-max/) $2.21
- [Qwen3.5 Plus 2026-04-20](/models/qwen__qwen3.5-plus-20260420/) $0.675
- [Qwen3.6 27B](/models/qwen__qwen3.6-27b/) $1.01
- [Qwen3.6 35B A3B](/models/qwen__qwen3.6-35b-a3b/) $0.300
- [Qwen3.6 Flash](/models/qwen__qwen3.6-flash/) $0.422
- [Qwen3.5-9B](/models/qwen__qwen3.5-9b/) $0.113
- [Qwen3.5 Plus 2026-02-15](/models/qwen__qwen3.5-plus-02-15/) $0.585
- [Qwen3 Max Thinking](/models/qwen__qwen3-max-thinking/) $1.56
- [Qwen3 Coder Next](/models/qwen__qwen3-coder-next/) $0.290
- [Qwen3 VL 32B Instruct](/models/qwen__qwen3-vl-32b-instruct/) $0.182
- [Qwen3 VL 8B Instruct](/models/qwen__qwen3-vl-8b-instruct/) $0.202
- [Qwen3 VL 8B Thinking](/models/qwen__qwen3-vl-8b-thinking/) $0.660
- [Qwen3 VL 30B A3B Instruct](/models/qwen__qwen3-vl-30b-a3b-instruct/) $0.228
- [Qwen3 VL 30B A3B Thinking](/models/qwen__qwen3-vl-30b-a3b-thinking/) $0.468
- [Qwen3 Coder Plus](/models/qwen__qwen3-coder-plus/) $1.30
- [Qwen3 Coder Flash](/models/qwen__qwen3-coder-flash/) $0.390
- [Qwen Plus 0728](/models/qwen__qwen-plus-2025-07-28/) $0.390
- [Qwen3 30B A3B Thinking 2507](/models/qwen__qwen3-30b-a3b-thinking-2507/) $0.750
- [Qwen3 Coder 30B A3B Instruct](/models/qwen__qwen3-coder-30b-a3b-instruct/) $0.120
- [Qwen3 Coder 480B A35B](/models/qwen__qwen3-coder/) $0.638
- [Qwen3 14B](/models/qwen__qwen3-14b/) $0.150
- [Qwen3 8B](/models/qwen__qwen3-8b/) $0.202
- [Qwen-Plus](/models/qwen__qwen-plus/) $0.390
- [Qwen2.5 VL 72B Instruct](/models/qwen__qwen2.5-vl-72b-instruct/) $0.850
- [Qwen2.5 7B Instruct](/models/qwen__qwen-2.5-7b-instruct/) $0.125

 +28 more

### Mistral 16

 - [Mistral Large 4](/models/mistralai__mistral-large-4-0/) $2.07
- [Mistral Small 4](/models/mistralai__mistral-small-2603/) $0.263
- [Ministral 3 14B 2512](/models/mistralai__ministral-14b-2512/) $0.200
 - [Ministral 3 3B 2512](/models/mistralai__ministral-3b-2512/) $0.100
- [Ministral 3 8B 2512](/models/mistralai__ministral-8b-2512/) $0.150
- [Mistral Large 3 2512](/models/mistralai__mistral-large-2512/) $0.750
- [Voxtral Small 24B 2507](/models/mistralai__voxtral-small-24b-2507/) $0.150
- [Mistral Medium 3.1](/models/mistralai__mistral-medium-3.1/) $0.800
- [Codestral 2508](/models/mistralai__codestral-2508/) $0.450
- [Mistral Small 3.2 24B](/models/mistralai__mistral-small-3.2-24b-instruct/) $0.106
- [Mistral Medium 3](/models/mistralai__mistral-medium-3/) $0.800
- [Mistral Small 3.1 24B](/models/mistralai__mistral-small-3.1-24b-instruct/) $0.402
- [Saba](/models/mistralai__mistral-saba/) $0.300
- [Mistral Nemo](/models/mistralai__mistral-nemo/) $0.021
- [Mixtral 8x22B Instruct](/models/mistralai__mixtral-8x22b-instruct/) $3.00
- [Mistral Large](/models/mistralai__mistral-large/) $3.00

 +13 more

### Google 14

 - [Nano Banana 2.1](/models/google__gemini-nano-banana-2.1/) $3.00
- [Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)](/models/google__gemini-3.1-flash-lite-image/) $0.563
- [Nano Banana 2 (Gemini 3.1 Flash Image)](/models/google__gemini-3.1-flash-image/) $1.13
 - [Nano Banana Pro (Gemini 3 Pro Image)](/models/google__gemini-3-pro-image/) $4.50
- [Gemini 3.1 Flash Lite](/models/google__gemini-3.1-flash-lite/) $0.563
- [Lyria 3 Clip Preview](/models/google__lyria-3-clip-preview/) not priced per token
- [Lyria 3 Pro Preview](/models/google__lyria-3-pro-preview/) not priced per token
- [Nano Banana 2 (Gemini 3.1 Flash Image Preview)](/models/google__gemini-3.1-flash-image-preview/) $1.13
- [Gemini 3.1 Pro Preview Custom Tools](/models/google__gemini-3.1-pro-preview-customtools/) $4.50
- [Gemini 3 Flash Preview](/models/google__gemini-3-flash-preview/) $1.13
- [Nano Banana Pro (Gemini 3 Pro Image Preview)](/models/google__gemini-3-pro-image-preview/) $4.50
- [Nano Banana (Gemini 2.5 Flash Image)](/models/google__gemini-2.5-flash-image/) $0.850
- [Gemini 2.5 Flash Lite](/models/google__gemini-2.5-flash-lite/) $0.175
- [Gemini 2.5 Pro Preview 06-05](/models/google__gemini-2.5-pro-preview/) $3.44

 +11 more

### ByteDance 7

 - [Seed 2.1 Turbo](/models/bytedance-seed__seed-2-1-turbo/) $1.00
- [Seed-2.0-Code](/models/bytedance-seed__seed-2.0-code/) $1.13
- [Seed-2.0-Lite](/models/bytedance-seed__seed-2.0-lite/) $0.688
 - [Seed-2.0-Mini](/models/bytedance-seed__seed-2.0-mini/) $0.175
- [Seed 1.6](/models/bytedance-seed__seed-1.6/) $0.688
- [Seed 1.6 Flash](/models/bytedance-seed__seed-1.6-flash/) $0.131
- [UI-TARS 7B](/models/bytedance__ui-tars-1.5-7b/) $0.125

 +4 more

### Aion Labs 6

 - [Aion 3.5](/models/aion-labs__aion-3.5/) $3.75
- [Aion 3.5 Mini](/models/aion-labs__aion-3.5-mini/) $0.875
- [Aion-3.0](/models/aion-labs__aion-3.0/) $3.75
 - [Aion-3.0-Mini](/models/aion-labs__aion-3.0-mini/) $0.875
- [Aion-2.0](/models/aion-labs__aion-2.0/) $1.00
- [Aion-RP 1.0 (8B)](/models/aion-labs__aion-rp-llama-3.1-8b/) $1.00

 +3 more

### Meta 6

 - [Muse Spark 1.3 Contributor](/models/meta__muse-spark-1.3-contributor/) $0.125
- [Muse Spark 1.2 Contributor](/models/meta__muse-spark-1.2-contributor/) $0.125
- [Muse Glimmer 30B](/models/meta__muse-glimmer-30b/) $0.525
 - [Llama Guard 4 12B](/models/meta-llama__llama-guard-4-12b/) $0.180
- [Llama 4 Maverick](/models/meta-llama__llama-4-maverick/) $0.415
- [Llama 4 Scout](/models/meta-llama__llama-4-scout/) $0.150

 +3 more

### NVIDIA 6

 - [Switchyard](/models/nvidia__switchyard/) —
- [Nemotron 3.5 Lightning](/models/nvidia__nemotron-3.5-lightning/) $0.085
- [Nemotron 3 Ultra](/models/nvidia__nemotron-3-ultra-550b-a55b/) $1.25
 - [Nemotron 3.5 Content Safety](/models/nvidia__nemotron-3.5-content-safety/) $0.200
- [Nemotron 3 Super](/models/nvidia__nemotron-3-super-120b-a12b/) $0.164
- [Nemotron 3 Nano 30B A3B](/models/nvidia__nemotron-3-nano-30b-a3b/) $0.088

 +3 more

### OpenRouter 6

 - [Auto Router (Beta)](/models/openrouter__auto-beta/) —
- [Fusion](/models/openrouter__fusion/) —
- [Pareto Code Router](/models/openrouter__pareto-code/) —
 - [Free Models Router](/models/openrouter__free/) free
- [Body Builder (beta)](/models/openrouter__bodybuilder/) —
- [Auto Router](/models/openrouter__auto/) —

 +3 more

### Tencent 6

 - [Hy4 preview](/models/tencent__hy4-preview/) $1.25
- [Hy-MT2-1.8B](/models/tencent__hy-mt2-1.8b/) $0.077
- [Hy-MT2-30B-A3B](/models/tencent__hy-mt2-30b-a3b/) $0.129
 - [Hy-MT2-7B](/models/tencent__hy-mt2-7b/) $0.129
- [Hy3 preview](/models/tencent__hy3-preview/) $0.285
- [Hunyuan A13B Instruct](/models/tencent__hunyuan-a13b-instruct/) $0.248

 +3 more

### Perplexity 5

 - [Sonar Pro Search](/models/perplexity__sonar-pro-search/) $6.00
- [Sonar Deep Research](/models/perplexity__sonar-deep-research/) $3.50
- [Sonar Pro](/models/perplexity__sonar-pro/) $6.00
 - [Sonar Reasoning Pro](/models/perplexity__sonar-reasoning-pro/) $3.50
- [Sonar](/models/perplexity__sonar/) $1.00

 +2 more

### Amazon 4

 - [Nova Premier 1.0](/models/amazon__nova-premier-v1/) $5.00
- [Nova Lite 1.0](/models/amazon__nova-lite-v1/) $0.105
- [Nova Micro 1.0](/models/amazon__nova-micro-v1/) $0.061
 - [Nova Pro 1.0](/models/amazon__nova-pro-v1/) $1.40

 +1 more

### inclusionAI 4

 - [Ling 3.1 Flash](/models/inclusionai__ling-3.1-flash/) free
- [Ling 3.0 Flash VL](/models/inclusionai__ling-3.0-flash-vl/) $0.090
- [Ling 3.0 Flash Fin](/models/inclusionai__ling-3.0-flash-fin/) $0.111
 - [Ling 3.0 Flash](/models/inclusionai__ling-3.0-flash/) $0.090

 +1 more

### Moonshot AI 4

 - [Kimi K2.7 Code](/models/moonshotai__kimi-k2.7-code/) $1.34
- [Kimi K2 Thinking](/models/moonshotai__kimi-k2-thinking/) $1.08
- [Kimi K2 0905](/models/moonshotai__kimi-k2-0905/) $1.08
 - [Kimi K2 0711](/models/moonshotai__kimi-k2/) $1.00

 +1 more

### Sakana AI 4

 - [Fugu Max](/models/sakana__fugu-max/) $3.00
- [Fugu Ultra v2](/models/sakana__fugu-ultra-v2/) $11.25
- [Sakana Namazu](/models/sakana__sakana-namazu/) $1.71
 - [Fugu Ultra](/models/sakana__fugu-ultra/) $11.25

 +1 more

### Cohere 3

 - [Command A+](/models/cohere__command-a-plus/) $0.600
- [Command A](/models/cohere__command-a/) $4.38
- [Command R7B (12-2024)](/models/cohere__command-r7b-12-2024/) $0.066

### DeepSeek 3

 - [DeepSeek V4 Flash Vision Exp](/models/deepseek__deepseek-v4-flash-vision-exp/) $0.660
- [DeepSeek V4 Pro 0813](/models/deepseek__deepseek-v4-pro-0813/) $1.63
- [DeepSeek V4 Flash 0731](/models/deepseek__deepseek-v4-flash-0731/) $0.090

### MiniMax 3

 - [MiniMax M2-her](/models/minimax__minimax-m2-her/) $0.525
- [MiniMax M2.1](/models/minimax__minimax-m2.1/) $0.525
- [MiniMax-01](/models/minimax__minimax-01/) $0.425

### Nous Research 3

 - [Hermes 4 405B](/models/nousresearch__hermes-4-405b/) $1.50
- [Hermes 3 70B Instruct](/models/nousresearch__hermes-3-llama-3.1-70b/) $0.700
- [Hermes 3 405B Instruct](/models/nousresearch__hermes-3-llama-3.1-405b/) $1.00

### Sao10k 3

 - [Llama 3.3 Euryale 70B](/models/sao10k__l3.3-euryale-70b/) $0.675
- [Llama 3.1 Euryale 70B v2.2](/models/sao10k__l3.1-euryale-70b/) $0.850
- [Llama 3 8B Lunaris](/models/sao10k__l3-lunaris-8b/) $0.043

### Thedrummer 3

 - [Cydonia 24B V4.1](/models/thedrummer__cydonia-24b-v4.1/) $0.350
- [Skyfall 36B V2](/models/thedrummer__skyfall-36b-v2/) $0.613
- [UnslopNemo 12B](/models/thedrummer__unslopnemo-12b/) $0.400

### xAI 3

 - [Grok Build 0.1](/models/x-ai__grok-build-0.1/) $1.25
- [Grok 4.20](/models/x-ai__grok-4.20/) $1.56
- [Grok 4.20 Multi-Agent](/models/x-ai__grok-4.20-multi-agent/) $1.56

### Z.ai 3

 - [GLM 5.3 Prime](/models/z-ai__glm-5.3-prime/) $4.30
- [GLM 5.3 FlashX](/models/z-ai__glm-5.3-flashx/) $0.590
- [GLM 5 Turbo](/models/z-ai__glm-5-turbo/) $1.90

### Inference Net 2

 - [Schematron V2 Small](/models/inference-net__schematron-v2-small/) $0.095
- [Schematron V2 Turbo](/models/inference-net__schematron-v2-turbo/) $0.060

### Morph 2

 - [Morph V3 Fast](/models/morph__morph-v3-fast/) $0.900
- [Morph V3 Large](/models/morph__morph-v3-large/) $1.15

### Nex Agi 2

 - [Nex-N2.5-Mini](/models/nex-agi__nex-n2.5-mini/) $0.044
- [Nex-N2.5-Pro](/models/nex-agi__nex-n2.5-pro/) $0.119

### Perceptron 2

 - [Perceptron Mk1.5](/models/perceptron__perceptron-mk1.5/) $0.488
- [Perceptron Mk1](/models/perceptron__perceptron-mk1/) $0.488

### Poolside 2

 - [Laguna S 2.1](/models/poolside__laguna-s-2.1/) $0.125
- [Laguna XS 2.1](/models/poolside__laguna-xs-2.1/) $0.125

### Reka 2

 - [Reka Edge](/models/rekaai__reka-edge/) $0.100
- [Reka Flash 3](/models/rekaai__reka-flash-3/) $0.125

### Relace 2

 - [Relace Search](/models/relace__relace-search/) $1.50
- [Relace Apply 3](/models/relace__relace-apply-3/) $0.950

### Unbiased 2

 - [Pareto 26.10 Preview](/models/unbiased__pareto-26.10-preview/) $1.40
- [Pareto](/models/unbiased__pareto/) $3.75

### Upstage 2

 - [Solar Mini 4](/models/upstage__solar-mini4/) $0.175
- [Solar Pro 3](/models/upstage__solar-pro-3/) $0.263

### Anthracite Org 1

 - [Magnum v4 72B](/models/anthracite-org__magnum-v4-72b/) $3.13

### Baidu 1

 - [ERNIE 4.5 VL 424B A47B](/models/baidu__ernie-4.5-vl-424b-a47b/) $0.628

### Cognitivecomputations 1

 - [Uncensored](/models/cognitivecomputations__dolphin-mistral-24b-venice-edition/) $0.375

### Fireworks 1

 - [Ember-1](/models/fireworks__ember-1/) $6.00

### Gryphe 1

 - [MythoMax 13B](/models/gryphe__mythomax-l2-13b/) $0.088

### IBM 1

 - [Granite 4.0 Micro](/models/ibm-granite__granite-4.0-h-micro/) $0.041

### Inception 1

 - [Mercury 2.5](/models/inception__mercury-2.5/) $0.338

### Kwaipilot 1

 - [KAT-Coder-Pro V2.5](/models/kwaipilot__kat-coder-pro-v2.5/) $1.30

### Mancer 1

 - [Weaver (alpha)](/models/mancer__weaver/) $0.488

### Meituan 1

 - [LongCat 2.0](/models/meituan__longcat-2.0/) $1.31

### Microsoft 1

 - [WizardLM-2 8x22B](/models/microsoft__wizardlm-2-8x22b/) $0.620

### Prism Ml 1

 - [Ternary Bonsai 2 27B](/models/prism-ml__ternary-bonsai-2-27b/) $0.181

### StepFun 1

 - [Step 3.7 Flash](/models/stepfun__step-3.7-flash/) $0.438

### Typesafe 1

 - [Jev Router](/models/typesafe__jev-router/) —

### Undi95 1

 - [ReMM SLERP 13B](/models/undi95__remm-slerp-l2-13b/) $0.425

### Writer 1

 - [Palmyra X5](/models/writer__palmyra-x5/) $1.95

### Xiaomi 1

 - [MiMo-V2.6-Pro-UltraSpeed](/models/xiaomi__mimo-v2.6-pro-ultraspeed/) $5.44

 Show all 213 unscored models

## Cite this claim

 Plain text and BibTeX Plain Copy
 133 of 145 rated, priced models have an alternative with an equal-or-higher measured score and an equal-or-lower price, with a strict advantage on at least one axis. 12 are not dominated on these two axes. As of 2026-10-06. Lens: LMArena Elo (CC BY 4.0). Ranking source digest: 06cd12db54e2968c. https://undominated.ai/
Publication: sha256:ecef83f767cd4d2c21766f6a5b4dffa36c06351f23657542d473bc1a030c0932; calculation SHA-256: 5ae4d0bee9b70298dd437b05df87c32acb407040b50bf88240677f295f25955d; permitted inputs: https://undominated.ai/data/publications/manifests/ecef83f767cd4d2c21766f6a5b4dffa36c06351f23657542d473bc1a030c0932.json
 BibTeX Copy
 @misc{undominated-dominated-census-2026-10-06,
 author = {{Undominated.ai}},
 title = {Dominated census — Undominated.ai},
 year = {2026},
 url = {https://undominated.ai/},
 note = {as of 2026-10-06; LMArena Elo (CC BY 4.0); ranking source 06cd12db54e2968c},
 annote = {Publication: sha256:ecef83f767cd4d2c21766f6a5b4dffa36c06351f23657542d473bc1a030c0932; calculation SHA-256: 5ae4d0bee9b70298dd437b05df87c32acb407040b50bf88240677f295f25955d; permitted inputs: https://undominated.ai/data/publications/manifests/ecef83f767cd4d2c21766f6a5b4dffa36c06351f23657542d473bc1a030c0932.json}
} Download BibTeX

[LMArena scores used under CC BY 4.0](/methodology/) · numbers recomputed from the catalogue on this page. [Input identity & calculation SHA](https://undominated.ai/data/publications/manifests/ecef83f767cd4d2c21766f6a5b4dffa36c06351f23657542d473bc1a030c0932.json).