---
title: "Compare alternatives to GPT-4 Turbo · Undominated.ai"
canonical: https://undominated.ai/alternatives/openai__gpt-4-turbo/
description: "130 alternatives score at least as high as GPT-4 Turbo and cost no more under at least one listed workload. 83 preserve recorded capabilities; 47 have named trade-offs."
---

# Compare alternatives to GPT-4 Turbo · Undominated.ai

> 130 alternatives score at least as high as GPT-4 Turbo and cost no more under at least one listed workload. 83 preserve recorded capabilities; 47 have named trade-offs.

# Alternatives to GPT-4 Turbo

OpenAI · LMArena 1271.7 · $15.00/M on a balanced workload · prices as of 2026-10-06

 [Compare models](https://undominated.ai/compare/) Comparison context

Choose up to three standard models in Compare.

Requirements and prompt length apply in Compare. This page keeps its stated price basis and workload controls.

## 83 models are higher-scoring or cheaper, with neither dimension worse.

Of the 144 models carrying both an independent score and a published price at the same delivery mode, **130** score at least as high as GPT-4 Turbo and cost no more under at least one listed workload, with at least one of those dimensions improved. **83** match or beat its recorded context, maximum output, input modes, tool use and extended reasoning. **47** have a recorded capability loss, named on every row.

Dominance is not a property of a model. It is a property of a model, a capability lens and a workload, and all three are named on every row. Scores are LMArena Elo, used under CC BY 4.0 from the official dataset; prices are blended per million tokens. A higher score is not a drop-in replacement.

This page is built only while a candidate improves score or price without worsening the other under a listed workload. When that comparison no longer holds, it is not generated.

## Where it holds

| Workload | GPT-4 Turbo $/M | Recorded capabilities preserved | Recorded capability losses |
| --- | --- | --- | --- |
| Balanced | $15.00 | 80 | 47 |
| Summarise | $11.00 | 83 | 47 |
| Chat | $18.00 | 80 | 47 |
| Code gen | $22.00 | 80 | 47 |
| Agentic | $13.00 | 83 | 47 |

Workload mixes are defined on the [methodology page](/methodology/). Cached input is priced at the cached rate, and reasoning tokens at the worse of the reasoning and output rates.

## What you would be replacing

| Intelligence | 1271.7 |
| --- | --- |
| Context window | 128K |
| Max output | 4K |
| Input modes | text, image |
| Tool use | yes |
| Extended reasoning | no |

Preserving recorded capabilities requires matching or beating these fields. [Full record for GPT-4 Turbo](/models/openai__gpt-4-turbo/), or [check GPT-4 Turbo against the whole catalogue](/check/openai__gpt-4-turbo/).

## Recorded capabilities preserved 83

Each option has a higher score or a lower price, with neither dimension worse under the listed workloads. It matches or beats GPT-4 Turbo on recorded context, maximum output, input modes, tool use and extended reasoning.

| # | Model | Intelligence | $/M | Holds under |
| --- | --- | --- | --- | --- |
| 1 | [Claude Opus 5.5](/models/anthropic__claude-opus-5.5/) Anthropic | 1511.7 +240 | $8.00 | Balanced −47% Summarise −66% Chat −49% Code gen −40% Agentic −68% |
| 2 | [Claude Opus 4.6](/models/anthropic__claude-opus-4.6/) Anthropic | 1503.2 +231.5 | $10.00 | Balanced −33% Summarise −57% Chat −35% Code gen −24% Agentic −59% |
| 3 | [Claude Opus 5](/models/anthropic__claude-opus-5/) Anthropic | 1502.1 +230.4 | $10.00 | Balanced −33% Summarise −57% Chat −35% Code gen −24% Agentic −59% |
| 4 | [Gemini 3.8 Flash](/models/google__gemini-3.8-flash/) Google | 1497 +225.3 | $3.00 | Balanced −80% Summarise −87% Chat −81% Code gen −77% Agentic −88% |
| 5 | [MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) Xiaomi | 1491 +219.3 | $0.540 | Balanced −96% Summarise −97% Chat −97% Code gen −97% Agentic −98% |
| 6 | [Muse Spark 1.3](/models/meta__muse-spark-1.3/) Meta | 1489.9 +218.2 | $2.00 | Balanced −87% Summarise −90% Chat −88% Code gen −87% Agentic −92% |
| 7 | [Gemini 3.7 Flash](/models/google__gemini-3.7-flash/) Google | 1487 +215.3 | $3.00 | Balanced −80% Summarise −87% Chat −81% Code gen −77% Agentic −88% |
| 8 | [Claude Opus 4.7](/models/anthropic__claude-opus-4.7/) Anthropic | 1489.9 +218.2 | $10.00 | Balanced −33% Summarise −57% Chat −35% Code gen −24% Agentic −59% |
| 9 | [Muse Spark 1.2](/models/meta__muse-spark-1.2/) Meta | 1483.2 +211.5 | $2.00 | Balanced −87% Summarise −90% Chat −88% Code gen −87% Agentic −92% |
| 10 | [Gemini 3.6 Flash](/models/google__gemini-3.6-flash/) Google | 1479.5 +207.8 | $1.50 | Balanced −90% Summarise −94% Chat −90% Code gen −89% Agentic −94% |
| 11 | [Muse Spark 1.1](/models/meta__muse-spark-1.1/) Meta | 1479.2 +207.5 | $2.00 | Balanced −87% Summarise −90% Chat −88% Code gen −87% Agentic −92% |
| 12 | [Gemini 3.1 Pro Preview](/models/google__gemini-3.1-pro-preview/) Google | 1480.2 +208.5 | $4.50 | Balanced −70% Summarise −82% Chat −70% Code gen −64% Agentic −81% |
| 13 | [Gemini 3.5 Flash](/models/google__gemini-3.5-flash/) Google | 1477.7 +206 | $3.38 | Balanced −78% Summarise −86% Chat −77% Code gen −73% Agentic −86% |
| 14 | [Kimi K3](/models/moonshotai__kimi-k3/) Moonshot AI | 1475.9 +204.2 | $3.76 | Balanced −75% Summarise −89% Chat −69% Code gen −63% Agentic −82% |
| 15 | [GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) Z.ai | 1469.6 +197.9 | $0.238 | Balanced −98% Summarise −99% Chat −99% Code gen −98% Agentic −99% |
| 16 | [Claude Sonnet 5.5](/models/anthropic__claude-sonnet-5.5/) Anthropic | 1466.6 +194.9 | $4.00 | Balanced −73% Summarise −83% Chat −74% Code gen −70% Agentic −84% |
| 17 | [DeepSeek V4.1 Flash](/models/deepseek__deepseek-v4.1-flash/) DeepSeek | 1462.5 +190.8 | $0.182 | Balanced −99% Summarise −99% Chat −99% Code gen −98% Agentic −99% |
| 18 | [GPT-5.5](/models/openai__gpt-5.5/) OpenAI | 1466.8 +195.1 | $11.25 | Balanced −25% Summarise −55% Chat −24% Code gen −11% Agentic −53% |
| 19 | [MiMo-V2.6-Flash](/models/xiaomi__mimo-v2.6-flash/) Xiaomi | 1456.4 +184.7 | $0.175 | Balanced −99% Summarise −99% Chat −99% Code gen −99% Agentic −99% |
| 20 | [Gemini 2.5 Pro](/models/google__gemini-2.5-pro/) Google | 1457.8 +186.1 | $3.44 | Balanced −77% Summarise −88% Chat −75% Code gen −71% Agentic −85% |
| 21 | [Kimi K2.6](/models/moonshotai__kimi-k2.6/) Moonshot AI | 1455.5 +183.8 | $0.961 | Balanced −94% Summarise −96% Chat −94% Code gen −93% Agentic −96% |
| 22 | [Claude Opus 4.8](/models/anthropic__claude-opus-4.8/) Anthropic | 1461 +189.3 | $10.00 | Balanced −33% Summarise −57% Chat −35% Code gen −24% Agentic −59% |
| 23 | [Qwen3.7 Plus](/models/qwen__qwen3.7-plus/) Qwen | 1454.6 +182.9 | $0.560 | Balanced −96% Summarise −97% Chat −97% Code gen −96% Agentic −98% |
| 24 | [Claude Sonnet 4.6](/models/anthropic__claude-sonnet-4.6/) Anthropic | 1457.8 +186.1 | $6.00 | Balanced −60% Summarise −74% Chat −61% Code gen −55% Agentic −75% |
| 25 | [GPT-5.6 Sol](/models/openai__gpt-5.6-sol/) OpenAI | 1456.3 +184.6 | $8.00 | Balanced −47% Summarise −66% Chat −48% Code gen −39% Agentic −67% |
| 26 | [GPT-5.4](/models/openai__gpt-5.4/) OpenAI | 1452.2 +180.5 | $5.63 | Balanced −63% Summarise −77% Chat −62% Code gen −55% Agentic −77% |
| 27 | [Grok 4.5](/models/x-ai__grok-4.5/) xAI | 1448.1 +176.4 | $3.00 | Balanced −80% Summarise −84% Chat −83% Code gen −81% Agentic −88% |
| 28 | [Kimi K2.5](/models/moonshotai__kimi-k2.5/) Moonshot AI | 1445.2 +173.5 | $1.20 | Balanced −92% Summarise −95% Chat −92% Code gen −91% Agentic −95% |
| 29 | [Claude Opus 4.5](/models/anthropic__claude-opus-4.5/) Anthropic | 1451 +179.3 | $10.00 | Balanced −33% Summarise −57% Chat −35% Code gen −24% Agentic −59% |
| 30 | [GPT-5.6 Terra](/models/openai__gpt-5.6-terra/) OpenAI | 1446.3 +174.6 | $4.50 | Balanced −70% Summarise −82% Chat −70% Code gen −64% Agentic −81% |
| 31 | [Gemma 4 31B](/models/google__gemma-4-31b-it/) Google | 1443.4 +171.7 | $0.205 | Balanced −99% Summarise −99% Chat −99% Code gen −99% Agentic −99% |
| 32 | [GPT-6.1 Sol](/models/openai__gpt-6.1-sol/) OpenAI | 1445.6 +173.9 | $4.00 | Balanced −73% Summarise −83% Chat −74% Code gen −70% Agentic −84% |
| 33 | [Inkling](/models/thinkingmachines__inkling/) Thinking Machines | 1441.8 +170.1 | $1.73 | Balanced −89% Summarise −92% Chat −89% Code gen −88% Agentic −93% |
| 34 | [Qwen3.8 27B](/models/qwen__qwen3.8-27b/) Qwen | 1440.7 +169 | $0.562 | Balanced −96% Summarise −98% Chat −95% Code gen −94% Agentic −97% |
| 35 | [Claude Sonnet 5](/models/anthropic__claude-sonnet-5/) Anthropic | 1442.9 +171.2 | $4.00 | Balanced −73% Summarise −83% Chat −74% Code gen −70% Agentic −84% |
| 36 | [Qwen3.5 397B A17B](/models/qwen__qwen3.5-397b-a17b/) Qwen | 1438 +166.3 | $0.878 | Balanced −94% Summarise −96% Chat −94% Code gen −93% Agentic −95% |
| 37 | [Qwen3.6 Plus](/models/qwen__qwen3.6-plus/) Qwen | 1436.7 +165 | $0.731 | Balanced −95% Summarise −96% Chat −95% Code gen −94% Agentic −96% |
| 38 | [GLM 5V Turbo](/models/z-ai__glm-5v-turbo/) Z.ai | 1437.2 +165.5 | $1.90 | Balanced −87% Summarise −90% Chat −89% Code gen −87% Agentic −92% |
| 39 | [Claude Sonnet 4.5](/models/anthropic__claude-sonnet-4.5/) Anthropic | 1438.6 +166.9 | $6.00 | Balanced −60% Summarise −74% Chat −61% Code gen −55% Agentic −75% |
| 40 | [Gemini 3.5 Flash Lite](/models/google__gemini-3.5-flash-lite/) Google | 1434.7 +163 | $0.850 | Balanced −94% Summarise −97% Chat −94% Code gen −93% Agentic −96% |
| 41 | [Gemma 4 26B A4B](/models/google__gemma-4-26b-a4b-it/) Google | 1433.9 +162.2 | $0.127 | Balanced −99% Summarise −99% Chat −99% Code gen −99% Agentic −99% |
| 42 | [MiniMax M3](/models/minimax__minimax-m3/) MiniMax | 1432.1 +160.4 | $0.485 | Balanced −97% Summarise −98% Chat −97% Code gen −97% Agentic −98% |
| 43 | [GPT-5.6 Luna](/models/openai__gpt-5.6-luna/) OpenAI | 1431 +159.3 | $0.450 | Balanced −97% Summarise −98% Chat −97% Code gen −96% Agentic −98% |
| 44 | [MiMo-V2.5](/models/xiaomi__mimo-v2.5/) Xiaomi | 1427.5 +155.8 | $0.175 | Balanced −99% Summarise −99% Chat −99% Code gen −99% Agentic −99% |
| 45 | [Grok 4.6](/models/x-ai__grok-4.6/) xAI | 1427.4 +155.7 | $3.00 | Balanced −80% Summarise −84% Chat −83% Code gen −81% Agentic −87% |
| 46 | [GPT-5.1](/models/openai__gpt-5.1/) OpenAI | 1422.2 +150.5 | $3.44 | Balanced −77% Summarise −88% Chat −75% Code gen −71% Agentic −85% |
| 47 | [Qwen3 VL 235B A22B Instruct](/models/qwen__qwen3-vl-235b-a22b-instruct/) Qwen | 1420.1 +148.4 | $0.370 | Balanced −98% Summarise −98% Chat −98% Code gen −97% Agentic −98% |
| 48 | [Mistral Medium 3.5](/models/mistralai__mistral-medium-3-5/) Mistral | 1421.2 +149.5 | $3.00 | Balanced −80% Summarise −84% Chat −78% Code gen −77% Agentic −82% |
| 49 | [Qwen3.5-122B-A10B](/models/qwen__qwen3.5-122b-a10b/) Qwen | 1417.1 +145.4 | $0.715 | Balanced −95% Summarise −97% Chat −95% Code gen −94% Agentic −96% |
| 50 | [Gemini 2.5 Flash](/models/google__gemini-2.5-flash/) Google | 1417 +145.3 | $0.850 | Balanced −94% Summarise −97% Chat −94% Code gen −93% Agentic −96% |
| 51 | [Gemini 3.1 Flash Lite Preview](/models/google__gemini-3.1-flash-lite-preview/) Google | 1415.7 +144 | $0.563 | Balanced −96% Summarise −98% Chat −96% Code gen −96% Agentic −98% |
| 52 | [Inkling Small](/models/thinkingmachines__inkling-small/) Thinking Machines | 1413.7 +142 | $0.638 | Balanced −96% Summarise −96% Chat −96% Code gen −96% Agentic −97% |
| 53 | [GPT-5.4 Mini](/models/openai__gpt-5.4-mini/) OpenAI | 1411.4 +139.7 | $1.69 | Balanced −89% Summarise −93% Chat −89% Code gen −87% Agentic −93% |
| 54 | [GPT-5.2](/models/openai__gpt-5.2/) OpenAI | 1412.3 +140.6 | $4.81 | Balanced −68% Summarise −83% Chat −66% Code gen −59% Agentic −80% |
| 55 | [Qwen3.5-27B](/models/qwen__qwen3.5-27b/) Qwen | 1408.9 +137.2 | $0.536 | Balanced −96% Summarise −98% Chat −96% Code gen −95% Agentic −97% |
| 56 | [o3](/models/openai__o3/) OpenAI | 1409.9 +138.2 | $3.50 | Balanced −77% Summarise −83% Chat −78% Code gen −75% Agentic −85% |
| 57 | [GPT-5](/models/openai__gpt-5/) OpenAI | 1406.1 +134.4 | $3.44 | Balanced −77% Summarise −88% Chat −75% Code gen −71% Agentic −85% |
| 58 | [Qwen3 VL 235B A22B Thinking](/models/qwen__qwen3-vl-235b-a22b-thinking/) Qwen | 1400.7 +129 | $1.30 | Balanced −91% Summarise −95% Chat −90% Code gen −88% Agentic −93% |
| 59 | [Grok 4.7](/models/x-ai__grok-4.7/) xAI | 1399.9 +128.2 | $3.00 | Balanced −80% Summarise −84% Chat −83% Code gen −81% Agentic −87% |
| 60 | [Qwen3.5-Flash](/models/qwen__qwen3.5-flash-02-23/) Qwen | 1397 +125.3 | $0.114 | Balanced −99% Summarise −99% Chat −99% Code gen −99% Agentic −99% |
| 61 | [Grok 4.3](/models/x-ai__grok-4.3/) xAI | 1396.7 +125 | $1.56 | Balanced −90% Summarise −91% Chat −92% Code gen −91% Agentic −94% |
| 62 | [Claude Haiku 4.5](/models/anthropic__claude-haiku-4.5/) Anthropic | 1396.1 +124.4 | $2.00 | Balanced −87% Summarise −91% Chat −87% Code gen −85% Agentic −92% |
| 63 | [Qwen3.5-35B-A3B](/models/qwen__qwen3.5-35b-a3b/) Qwen | 1394.4 +122.7 | $0.355 | Balanced −98% Summarise −99% Chat −97% Code gen −97% Agentic −98% |
| 64 | [GPT-6 Sol](/models/openai__gpt-6-sol/) OpenAI | 1395.4 +123.7 | $4.00 | Balanced −73% Summarise −83% Chat −74% Code gen −70% Agentic −84% |
| 65 | [GPT-6 Luna](/models/openai__gpt-6-luna/) OpenAI | 1391.5 +119.8 | $0.200 | Balanced −99% Summarise −99% Chat −99% Code gen −98% Agentic −99% |
| 66 | [GPT-4.1](/models/openai__gpt-4.1/) OpenAI | 1383 +111.3 | $3.50 | Balanced −77% Summarise −83% Chat −78% Code gen −75% Agentic −85% |
| 67 | [GLM 4.6V](/models/z-ai__glm-4.6v/) Z.ai | 1376.8 +105.1 | $0.450 | Balanced −97% Summarise −98% Chat −97% Code gen −97% Agentic −98% |
| 68 | [GPT-5 Mini](/models/openai__gpt-5-mini/) OpenAI | 1373.2 +101.5 | $0.688 | Balanced −95% Summarise −98% Chat −95% Code gen −94% Agentic −97% |
| 69 | [GPT-5.4 Nano](/models/openai__gpt-5.4-nano/) OpenAI | 1372.1 +100.4 | $0.463 | Balanced −97% Summarise −98% Chat −97% Code gen −96% Agentic −98% |
| 70 | [Nova 2 Lite](/models/amazon__nova-2-lite-v1/) Amazon | 1361.8 +90.1 | $0.850 | Balanced −94% Summarise −96% Chat −93% Code gen −93% Agentic −95% |
| 71 | [Gemma 3 27B](/models/google__gemma-3-27b-it/) Google | 1357.8 +86.1 | $0.100 | Balanced −99% Summarise −99% Chat −99% Code gen −99% Agentic −99% |
| 72 | [o4 Mini](/models/openai__o4-mini/) OpenAI | 1353.2 +81.5 | $1.93 | Balanced −87% Summarise −91% Chat −88% Code gen −86% Agentic −92% |
| 73 | [GPT-4.1 Mini](/models/openai__gpt-4.1-mini/) OpenAI | 1340.4 +68.7 | $0.700 | Balanced −95% Summarise −97% Chat −96% Code gen −95% Agentic −97% |
| 74 | [Claude Sonnet 4](/models/anthropic__claude-sonnet-4/) Anthropic | 1339.1 +67.4 | $6.00 | Balanced −60% Summarise −74% Chat −61% Code gen −55% Agentic −75% |
| 75 | [Gemma 3 12B](/models/google__gemma-3-12b-it/) Google | 1334.2 +62.5 | $0.075 | Balanced over 99% less Summarise over 99% less Chat over 99% less Code gen over 99% less Agentic over 99% less |
| 76 | [GPT-5 Nano](/models/openai__gpt-5-nano/) OpenAI | 1320 +48.3 | $0.138 | Balanced −99% Summarise over 99% less Chat −99% Code gen −99% Agentic −99% |
| 77 | [GPT-4o (2024-05-13)](/models/openai__gpt-4o-2024-05-13/) OpenAI | 1300.4 +28.7 | $7.50 | Balanced −50% Summarise −50% Chat −50% Code gen −50% Agentic −50% |
| 78 | [GPT-4o-mini (2024-07-18)](/models/openai__gpt-4o-mini-2024-07-18/) OpenAI | 1286.4 +14.7 | $0.263 | Balanced −98% Summarise −99% Chat −98% Code gen −98% Agentic −99% |
| 79 | [GPT-4.1 Nano](/models/openai__gpt-4.1-nano/) OpenAI | 1284.8 +13.1 | $0.175 | Balanced −99% Summarise −99% Chat −99% Code gen −99% Agentic −99% |
| 80 | [GPT-4o (2024-08-06)](/models/openai__gpt-4o-2024-08-06/) OpenAI | 1282.5 +10.8 | $4.38 | Balanced −71% Summarise −77% Chat −72% Code gen −69% Agentic −78% |
| 81 | [Claude Fable 5.1](/models/anthropic__claude-fable-5.1/) Anthropic | 1510.6 +238.9 | $9.22 summarise | Summarise −16% Agentic −22% |
| 82 | [Claude Fable 5](/models/anthropic__claude-fable-5/) Anthropic | 1491.7 +220 | $9.44 summarise | Summarise −14% Agentic −18% |
| 83 | [GPT-6 Astra](/models/openai__gpt-6-astra/) OpenAI | 1442.3 +170.6 | $9.44 summarise | Summarise −14% Agentic −18% |

## Alternatives with recorded capability losses 47

These improve score or price without worsening the other under the listed workloads, but reduce at least one recorded capability. Read the last column before switching.

| Model | Intelligence | $/M | Holds under | Recorded capability loss |
| --- | --- | --- | --- | --- |
| [GLM 5.3](/models/z-ai__glm-5.3/) Z.ai | 1471.4 +199.7 | $1.00 | Balanced −93% Summarise −97% Chat −92% Code gen −90% Agentic −95% | no image input |
| [GLM 5.2](/models/z-ai__glm-5.2/) Z.ai | 1470.4 +198.7 | $1.12 | Balanced −93% Summarise −96% Chat −91% Code gen −90% Agentic −95% | no image input |
| [MiMo-V2.5-Pro](/models/xiaomi__mimo-v2.5-pro/) Xiaomi | 1465 +193.3 | $0.544 | Balanced −96% Summarise −97% Chat −97% Code gen −97% Agentic −98% | no image input |
| [GLM 5.1](/models/z-ai__glm-5.1/) Z.ai | 1461.5 +189.8 | $1.83 | Balanced −88% Summarise −90% Chat −89% Code gen −88% Agentic −91% | no image input |
| [GLM 5](/models/z-ai__glm-5/) Z.ai | 1446.3 +174.6 | $1.09 | Balanced −93% Summarise −94% Chat −94% Code gen −93% Agentic −95% | no image input |
| [Qwen3.6 Max Preview](/models/qwen__qwen3.6-max-preview/) Qwen | 1446.8 +175.1 | $2.31 | Balanced −85% Summarise −88% Chat −83% Code gen −81% Agentic −86% | no image input |
| [DeepSeek V4 Pro 0423](/models/deepseek__deepseek-v4-pro/) DeepSeek | 1445.2 +173.5 | $1.21 | Balanced −92% Summarise −95% Chat −91% Code gen −90% Agentic −95% | no image input |
| [Hy3](/models/tencent__hy3/) Tencent | 1440.7 +169 | $0.231 | Balanced −98% Summarise −99% Chat −99% Code gen −98% Agentic −99% | no image input |
| [GLM 4.6](/models/z-ai__glm-4.6/) Z.ai | 1439.9 +168.2 | $0.760 | Balanced −95% Summarise −96% Chat −95% Code gen −95% Agentic −97% | no image input |
| [GLM 4.7](/models/z-ai__glm-4.7/) Z.ai | 1435.5 +163.8 | $0.738 | Balanced −95% Summarise −97% Chat −95% Code gen −95% Agentic −97% | no image input |
| [DeepSeek V4 Flash 0423](/models/deepseek__deepseek-v4-flash/) DeepSeek | 1432.1 +160.4 | $0.113 | Balanced −99% Summarise −99% Chat −99% Code gen −99% Agentic over 99% less | no image input |
| [GLM 4.5](/models/z-ai__glm-4.5/) Z.ai | 1430.3 +158.6 | $1.00 | Balanced −93% Summarise −95% Chat −94% Code gen −93% Agentic −96% | no image input |
| [R1 0528](/models/deepseek__deepseek-r1-0528/) DeepSeek | 1427.9 +156.2 | $0.920 | Balanced −94% Summarise −95% Chat −93% Code gen −93% Agentic −94% | no image input |
| [DeepSeek V3.2](/models/deepseek__deepseek-v3.2/) DeepSeek | 1424.5 +152.8 | $0.290 | Balanced −98% Summarise −98% Chat −99% Code gen −99% Agentic −98% | no image input |
| [DeepSeek V3.2 Exp](/models/deepseek__deepseek-v3.2-exp/) DeepSeek | 1422.4 +150.7 | $0.305 | Balanced −98% Summarise −97% Chat −98% Code gen −98% Agentic −98% | no image input |
| [DeepSeek V3.1](/models/deepseek__deepseek-chat-v3.1/) DeepSeek | 1419.7 +148 | $0.453 | Balanced −97% Summarise −97% Chat −97% Code gen −97% Agentic −97% | no image input |
| [Qwen3 235B A22B Instruct 2507](/models/qwen__qwen3-235b-a22b-2507/) Qwen | 1419.3 +147.6 | $0.205 | Balanced −99% Summarise −99% Chat −98% Code gen −98% Agentic −99% | no image input |
| [Qwen3 Next 80B A3B Instruct](/models/qwen__qwen3-next-80b-a3b-instruct/) Qwen | 1417.3 +145.6 | $0.268 | Balanced −98% Summarise −99% Chat −98% Code gen −98% Agentic −98% | no image input |
| [DeepSeek V3.1 Terminus](/models/deepseek__deepseek-v3.1-terminus/) DeepSeek | 1417.1 +145.4 | $0.453 | Balanced −97% Summarise −97% Chat −97% Code gen −97% Agentic −97% | no image input |
| [Qwen3 235B A22B Thinking 2507](/models/qwen__qwen3-235b-a22b-thinking-2507/) Qwen | 1415.2 +143.5 | $0.748 | Balanced −95% Summarise −97% Chat −94% Code gen −93% Agentic −96% | no image input |
| [Qwen3 Max](/models/qwen__qwen3-max/) Qwen | 1412.4 +140.7 | $1.56 | Balanced −90% Summarise −93% Chat −90% Code gen −88% Agentic −93% | no image input |
| [MiniMax M2.7](/models/minimax__minimax-m2.7/) MiniMax | 1404.6 +132.9 | $0.525 | Balanced −97% Summarise −97% Chat −97% Code gen −96% Agentic −98% | no image input |
| [Step 3.5 Flash](/models/stepfun__step-3.5-flash/) StepFun | 1403 +131.3 | $0.150 | Balanced −99% Summarise −99% Chat −99% Code gen −99% Agentic −99% | no image input |
| [Solar Pro 4](/models/upstage__solar-pro4/) Upstage | 1386.2 +114.5 | $0.525 | Balanced −97% Summarise −97% Chat −97% Code gen −96% Agentic −98% | no image input |
| [Qwen3 30B A3B Instruct 2507](/models/qwen__qwen3-30b-a3b-instruct-2507/) Qwen | 1384.1 +112.4 | $0.143 | Balanced −99% Summarise −99% Chat −99% Code gen −99% Agentic −99% | no image input |
| [GLM 4.5 Air](/models/z-ai__glm-4.5-air/) Z.ai | 1383.9 +112.2 | $0.310 | Balanced −98% Summarise −99% Chat −98% Code gen −97% Agentic −99% | no image input |
| [DeepSeek V3 0324](/models/deepseek__deepseek-chat-v3-0324/) DeepSeek | 1375 +103.3 | $0.438 | Balanced −97% Summarise −97% Chat −97% Code gen −97% Agentic −97% | no image input |
| [R1](/models/deepseek__deepseek-r1/) DeepSeek | 1372.7 +101 | $1.15 | Balanced −92% Summarise −93% Chat −92% Code gen −92% Agentic −93% | 128K → 64K context no image input |
| [Qwen3 Next 80B A3B Thinking](/models/qwen__qwen3-next-80b-a3b-thinking/) Qwen | 1368.3 +96.6 | $0.413 | Balanced −97% Summarise −98% Chat −97% Code gen −96% Agentic −98% | no image input |
| [Qwen3 235B A22B](/models/qwen__qwen3-235b-a22b/) Qwen | 1366.6 +94.9 | $0.796 | Balanced −95% Summarise −95% Chat −94% Code gen −94% Agentic −95% | no image input |
| [gpt-oss-120b](/models/openai__gpt-oss-120b/) OpenAI | 1365.4 +93.7 | $0.065 | Balanced over 99% less Summarise over 99% less Chat over 99% less Code gen −99% Agentic over 99% less | no image input |
| [MiniMax M2.5](/models/minimax__minimax-m2.5/) MiniMax | 1359.3 +87.6 | $0.521 | Balanced −97% Summarise −98% Chat −97% Code gen −96% Agentic −98% | no image input |
| [Mercury 2](/models/inception__mercury-2/) Inception | 1355.2 +83.5 | $0.375 | Balanced −98% Summarise −98% Chat −98% Code gen −98% Agentic −99% | no image input |
| [GLM 4.7 Flash](/models/z-ai__glm-4.7-flash/) Z.ai | 1350.9 +79.2 | $0.145 | Balanced −99% Summarise −99% Chat −99% Code gen −99% Agentic −99% | no image input |
| [MiniMax M1](/models/minimax__minimax-m1/) MiniMax | 1342.8 +71.1 | $0.850 | Balanced −94% Summarise −96% Chat −94% Code gen −93% Agentic −95% | no image input |
| [Qwen3 32B](/models/qwen__qwen3-32b/) Qwen | 1340.1 +68.4 | $0.130 | Balanced −99% Summarise −99% Chat −99% Code gen −99% Agentic −99% | no image input |
| [Trinity Large Thinking](/models/arcee-ai__trinity-large-thinking/) Arcee | 1340 +68.3 | $0.388 | Balanced −97% Summarise −98% Chat −98% Code gen −97% Agentic −98% | no image input |
| [MiniMax M2](/models/minimax__minimax-m2/) MiniMax | 1339.9 +68.2 | $0.525 | Balanced −97% Summarise −98% Chat −97% Code gen −96% Agentic −98% | no image input |
| [o3 Mini High](/models/openai__o3-mini-high/) OpenAI | 1336.6 +64.9 | $1.93 | Balanced −87% Summarise −90% Chat −87% Code gen −86% Agentic −90% | no image input |
| [GLM 4.5V](/models/z-ai__glm-4.5v/) Z.ai | 1332.8 +61.1 | $0.900 | Balanced −94% Summarise −95% Chat −95% Code gen −94% Agentic −96% | 128K → 66K context |
| [DeepSeek V3](/models/deepseek__deepseek-chat/) DeepSeek | 1332.5 +60.8 | $0.500 | Balanced −97% Summarise −97% Chat −97% Code gen −96% Agentic −97% | no image input |
| [o3 Mini](/models/openai__o3-mini/) OpenAI | 1319.4 +47.7 | $1.93 | Balanced −87% Summarise −90% Chat −87% Code gen −86% Agentic −90% | no image input |
| [Granite 4.2 8B](/models/ibm-granite__granite-4.2-8b/) IBM | 1317.8 +46.1 | $0.108 | Balanced −99% Summarise −99% Chat −99% Code gen −99% Agentic over 99% less | no image input |
| [Qwen3 30B A3B](/models/qwen__qwen3-30b-a3b/) Qwen | 1316.6 +44.9 | $0.215 | Balanced −99% Summarise −99% Chat −98% Code gen −98% Agentic −99% | no image input |
| [Gemma 3 4B](/models/google__gemma-3-4b-it/) Google | 1290.8 +19.1 | $0.063 | Balanced over 99% less Summarise over 99% less Chat over 99% less Code gen over 99% less Agentic over 99% less | no tool use |
| [gpt-oss-20b](/models/openai__gpt-oss-20b/) OpenAI | 1287.7 +16 | $0.036 | Balanced over 99% less Summarise over 99% less Chat over 99% less Code gen over 99% less Agentic over 99% less | no image input |
| [Llama 3.3 70B Instruct](/models/meta-llama__llama-3.3-70b-instruct/) Meta | 1274.1 tie | $0.201 | Balanced −99% Summarise −99% Chat −99% Code gen −99% Agentic −99% | no image input |

## What this compares, and what it leaves out

 - Quality is LMArena Elo, used under CC BY 4.0 from the official dataset. The 95% confidence interval on a difference between two scores is about ±10.47 points, so a gap smaller than that is marked *tie* rather than an improvement — see [significance bands](/significance/).
 - 204 further models at this delivery mode carry a price but no independent score. They are absent from the comparison in both directions — unrated is not a zero, and an unmeasured model is neither an alternative nor a worse buy.
 - Retired models are never offered as an alternative, and a model only competes against its own delivery mode: batch trades latency for price, so it is not a like-for-like swap.
 - Nothing here measures latency, throughput, rate limits or how a model behaves on your prompts. Two models with the same index score are not interchangeable.
 - Models with no higher-scoring or cheaper alternative that is no worse on the other axis are on the [value frontier](/frontier/). Models with such an alternative are [listed here](/alternatives/).

## Continue your investigation

 - [Check requirements](/check/)
- [Compare exact differences](/compare/)
- [Set a quality floor](/cheapest-at/)
- [Inspect tier boundaries](/cliffs/)