---
title: "Compare alternatives to GPT-4o (2024-08-06) · Undominated.ai"
canonical: https://undominated.ai/alternatives/openai__gpt-4o-2024-08-06/
description: "113 alternatives score at least as high as GPT-4o (2024-08-06) and cost no more under at least one listed workload. 40 preserve recorded capabilities; 73 have named trade-offs."
---

# Compare alternatives to GPT-4o (2024-08-06) · Undominated.ai

> 113 alternatives score at least as high as GPT-4o (2024-08-06) and cost no more under at least one listed workload. 40 preserve recorded capabilities; 73 have named trade-offs.

# Alternatives to GPT-4o (2024-08-06)

OpenAI · LMArena 1282.5 · $4.38/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.

## 40 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, **113** score at least as high as GPT-4o (2024-08-06) and cost no more under at least one listed workload, with at least one of those dimensions improved. **40** match or beat its recorded context, maximum output, input modes, tool use and extended reasoning. **73** 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-4o (2024-08-06) $/M | Recorded capabilities preserved | Recorded capability losses |
| --- | --- | --- | --- |
| Balanced | $4.38 | 36 | 73 |
| Summarise | $2.52 | 40 | 73 |
| Chat | $5.13 | 36 | 72 |
| Code gen | $6.90 | 36 | 72 |
| Agentic | $2.88 | 39 | 73 |

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 | 1282.5 |
| --- | --- |
| Context window | 128K |
| Max output | 16K |
| Input modes | text, image, file |
| Tool use | yes |
| Extended reasoning | no |

Preserving recorded capabilities requires matching or beating these fields. [Full record for GPT-4o (2024-08-06)](/models/openai__gpt-4o-2024-08-06/), or [check GPT-4o (2024-08-06) against the whole catalogue](/check/openai__gpt-4o-2024-08-06/).

## Recorded capabilities preserved 40

Each option has a higher score or a lower price, with neither dimension worse under the listed workloads. It matches or beats GPT-4o (2024-08-06) on recorded context, maximum output, input modes, tool use and extended reasoning.

| # | Model | Intelligence | $/M | Holds under |
| --- | --- | --- | --- | --- |
| 1 | [Gemini 3.8 Flash](/models/google__gemini-3.8-flash/) Google | 1497 +214.5 | $3.00 | Balanced −31% Summarise −44% Chat −32% Code gen −28% Agentic −45% |
| 2 | [Muse Spark 1.3](/models/meta__muse-spark-1.3/) Meta | 1489.9 +207.4 | $2.00 | Balanced −54% Summarise −57% Chat −59% Code gen −57% Agentic −64% |
| 3 | [Gemini 3.7 Flash](/models/google__gemini-3.7-flash/) Google | 1487 +204.5 | $3.00 | Balanced −31% Summarise −44% Chat −32% Code gen −28% Agentic −45% |
| 4 | [Muse Spark 1.2](/models/meta__muse-spark-1.2/) Meta | 1483.2 +200.7 | $2.00 | Balanced −54% Summarise −57% Chat −59% Code gen −57% Agentic −64% |
| 5 | [Gemini 3.6 Flash](/models/google__gemini-3.6-flash/) Google | 1479.5 +197 | $1.50 | Balanced −66% Summarise −72% Chat −66% Code gen −64% Agentic −72% |
| 6 | [Muse Spark 1.1](/models/meta__muse-spark-1.1/) Meta | 1479.2 +196.7 | $2.00 | Balanced −54% Summarise −57% Chat −59% Code gen −57% Agentic −64% |
| 7 | [Gemini 3.5 Flash](/models/google__gemini-3.5-flash/) Google | 1477.7 +195.2 | $3.38 | Balanced −23% Summarise −41% Chat −20% Code gen −15% Agentic −37% |
| 8 | [Claude Sonnet 5.5](/models/anthropic__claude-sonnet-5.5/) Anthropic | 1466.6 +184.1 | $4.00 | Balanced −9% Summarise −25% Chat −9% Code gen −4% Agentic −26% |
| 9 | [Gemini 2.5 Pro](/models/google__gemini-2.5-pro/) Google | 1457.8 +175.3 | $3.44 | Balanced −21% Summarise −46% Chat −14% Code gen −7% Agentic −34% |
| 10 | [Grok 4.5](/models/x-ai__grok-4.5/) xAI | 1448.1 +165.6 | $3.00 | Balanced −31% Summarise −32% Chat −40% Code gen −38% Agentic −45% |
| 11 | [GPT-6.1 Sol](/models/openai__gpt-6.1-sol/) OpenAI | 1445.6 +163.1 | $4.00 | Balanced −9% Summarise −26% Chat −10% Code gen −4% Agentic −28% |
| 12 | [Claude Sonnet 5](/models/anthropic__claude-sonnet-5/) Anthropic | 1442.9 +160.4 | $4.00 | Balanced −9% Summarise −25% Chat −9% Code gen −4% Agentic −26% |
| 13 | [Gemini 3.5 Flash Lite](/models/google__gemini-3.5-flash-lite/) Google | 1434.7 +152.2 | $0.850 | Balanced −81% Summarise −87% Chat −79% Code gen −77% Agentic −84% |
| 14 | [GPT-5.6 Luna](/models/openai__gpt-5.6-luna/) OpenAI | 1431 +148.5 | $0.450 | Balanced −90% Summarise −92% Chat −89% Code gen −89% Agentic −92% |
| 15 | [Grok 4.6](/models/x-ai__grok-4.6/) xAI | 1427.4 +144.9 | $3.00 | Balanced −31% Summarise −30% Chat −39% Code gen −38% Agentic −41% |
| 16 | [Gemini 2.5 Flash](/models/google__gemini-2.5-flash/) Google | 1417 +134.5 | $0.850 | Balanced −81% Summarise −87% Chat −79% Code gen −77% Agentic −84% |
| 17 | [Gemini 3.1 Flash Lite Preview](/models/google__gemini-3.1-flash-lite-preview/) Google | 1415.7 +133.2 | $0.563 | Balanced −87% Summarise −90% Chat −87% Code gen −86% Agentic −89% |
| 18 | [GPT-5.1](/models/openai__gpt-5.1/) OpenAI | 1422.2 +139.7 | $3.44 | Balanced −21% Summarise −46% Chat −14% Code gen −7% Agentic −34% |
| 19 | [Mistral Medium 3.5](/models/mistralai__mistral-medium-3-5/) Mistral | 1421.2 +138.7 | $3.00 | Balanced −31% Summarise −29% Chat −24% Code gen −26% Agentic −17% |
| 20 | [GPT-5.4 Mini](/models/openai__gpt-5.4-mini/) OpenAI | 1411.4 +128.9 | $1.69 | Balanced −61% Summarise −70% Chat −60% Code gen −57% Agentic −68% |
| 21 | [o3](/models/openai__o3/) OpenAI | 1409.9 +127.4 | $3.50 | Balanced −20% Summarise −26% Chat −23% Code gen −21% Agentic −30% |
| 22 | [GPT-5](/models/openai__gpt-5/) OpenAI | 1406.1 +123.6 | $3.44 | Balanced −21% Summarise −46% Chat −14% Code gen −7% Agentic −34% |
| 23 | [Grok 4.3](/models/x-ai__grok-4.3/) xAI | 1396.7 +114.2 | $1.56 | Balanced −64% Summarise −60% Chat −72% Code gen −72% Agentic −72% |
| 24 | [Grok 4.7](/models/x-ai__grok-4.7/) xAI | 1399.9 +117.4 | $3.00 | Balanced −31% Summarise −30% Chat −39% Code gen −38% Agentic −41% |
| 25 | [Claude Haiku 4.5](/models/anthropic__claude-haiku-4.5/) Anthropic | 1396.1 +113.6 | $2.00 | Balanced −54% Summarise −63% Chat −55% Code gen −52% Agentic −63% |
| 26 | [GPT-6 Luna](/models/openai__gpt-6-luna/) OpenAI | 1391.5 +109 | $0.200 | Balanced −95% Summarise −96% Chat −95% Code gen −95% Agentic −96% |
| 27 | [GPT-6 Sol](/models/openai__gpt-6-sol/) OpenAI | 1395.4 +112.9 | $4.00 | Balanced −9% Summarise −25% Chat −9% Code gen −4% Agentic −26% |
| 28 | [GPT-4.1](/models/openai__gpt-4.1/) OpenAI | 1383 +100.5 | $3.50 | Balanced −20% Summarise −26% Chat −23% Code gen −21% Agentic −30% |
| 29 | [GPT-5 Mini](/models/openai__gpt-5-mini/) OpenAI | 1373.2 +90.7 | $0.688 | Balanced −84% Summarise −89% Chat −83% Code gen −81% Agentic −87% |
| 30 | [GPT-5.4 Nano](/models/openai__gpt-5.4-nano/) OpenAI | 1372.1 +89.6 | $0.463 | Balanced −89% Summarise −92% Chat −89% Code gen −88% Agentic −91% |
| 31 | [Nova 2 Lite](/models/amazon__nova-2-lite-v1/) Amazon | 1361.8 +79.3 | $0.850 | Balanced −81% Summarise −84% Chat −77% Code gen −77% Agentic −78% |
| 32 | [o4 Mini](/models/openai__o4-mini/) OpenAI | 1353.2 +70.7 | $1.93 | Balanced −56% Summarise −59% Chat −58% Code gen −56% Agentic −62% |
| 33 | [GPT-4.1 Mini](/models/openai__gpt-4.1-mini/) OpenAI | 1340.4 +57.9 | $0.700 | Balanced −84% Summarise −85% Chat −85% Code gen −84% Agentic −86% |
| 34 | [GPT-5 Nano](/models/openai__gpt-5-nano/) OpenAI | 1320 +37.5 | $0.138 | Balanced −97% Summarise −98% Chat −97% Code gen −96% Agentic −97% |
| 35 | [GPT-4o-mini (2024-07-18)](/models/openai__gpt-4o-mini-2024-07-18/) OpenAI | 1286.4 tie | $0.263 | Balanced −94% Summarise −94% Chat −94% Code gen −94% Agentic −94% |
| 36 | [GPT-4.1 Nano](/models/openai__gpt-4.1-nano/) OpenAI | 1284.8 tie | $0.175 | Balanced −96% Summarise −96% Chat −96% Code gen −96% Agentic −97% |
| 37 | [Gemini 3.1 Pro Preview](/models/google__gemini-3.1-pro-preview/) Google | 1480.2 +197.7 | $1.99 summarise | Summarise −21% Agentic −16% |
| 38 | [GPT-5.4](/models/openai__gpt-5.4/) OpenAI | 1452.2 +169.7 | $2.48 summarise | Summarise −1% |
| 39 | [GPT-5.6 Terra](/models/openai__gpt-5.6-terra/) OpenAI | 1446.3 +163.8 | $1.99 summarise | Summarise −21% Agentic −16% |
| 40 | [GPT-5.2](/models/openai__gpt-5.2/) OpenAI | 1412.3 +129.8 | $1.91 summarise | Summarise −24% Agentic −8% |

## Alternatives with recorded capability losses 73

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 |
| --- | --- | --- | --- | --- |
| [MiMo-V2.6-Pro](/models/xiaomi__mimo-v2.6-pro/) Xiaomi | 1491 +208.5 | $0.540 | Balanced −88% Summarise −87% Chat −91% Code gen −90% Agentic −92% | no file input |
| [GLM 5.3](/models/z-ai__glm-5.3/) Z.ai | 1471.4 +188.9 | $1.00 | Balanced −77% Summarise −86% Chat −71% Code gen −69% Agentic −77% | no image, file input |
| [GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) Z.ai | 1469.6 +187.1 | $0.238 | Balanced −95% Summarise −95% Chat −95% Code gen −95% Agentic −95% | no file input |
| [GLM 5.2](/models/z-ai__glm-5.2/) Z.ai | 1470.4 +187.9 | $1.12 | Balanced −74% Summarise −83% Chat −70% Code gen −68% Agentic −76% | no image, file input |
| [Kimi K3](/models/moonshotai__kimi-k3/) Moonshot AI | 1475.9 +193.4 | $3.76 | Balanced −14% Summarise −51% Agentic −17% | no file input |
| [MiMo-V2.5-Pro](/models/xiaomi__mimo-v2.5-pro/) Xiaomi | 1465 +182.5 | $0.544 | Balanced −88% Summarise −87% Chat −91% Code gen −90% Agentic −92% | no image, file input |
| [DeepSeek V4.1 Flash](/models/deepseek__deepseek-v4.1-flash/) DeepSeek | 1462.5 +180 | $0.182 | Balanced −96% Summarise −97% Chat −95% Code gen −95% Agentic −96% | no file input |
| [GLM 5.1](/models/z-ai__glm-5.1/) Z.ai | 1461.5 +179 | $1.83 | Balanced −58% Summarise −54% Chat −60% Code gen −61% Agentic −58% | no image, file input |
| [MiMo-V2.6-Flash](/models/xiaomi__mimo-v2.6-flash/) Xiaomi | 1456.4 +173.9 | $0.175 | Balanced −96% Summarise −96% Chat −97% Code gen −97% Agentic −97% | no file input |
| [Qwen3.7 Plus](/models/qwen__qwen3.7-plus/) Qwen | 1454.6 +172.1 | $0.560 | Balanced −87% Summarise −88% Chat −88% Code gen −87% Agentic −89% | no file input |
| [Kimi K2.6](/models/moonshotai__kimi-k2.6/) Moonshot AI | 1455.5 +173 | $0.961 | Balanced −78% Summarise −82% Chat −78% Code gen −76% Agentic −81% | no file input |
| [GLM 5](/models/z-ai__glm-5/) Z.ai | 1446.3 +163.8 | $1.09 | Balanced −75% Summarise −75% Chat −78% Code gen −77% Agentic −79% | no image, file input |
| [Gemma 4 31B](/models/google__gemma-4-31b-it/) Google | 1443.4 +160.9 | $0.205 | Balanced −95% Summarise −94% Chat −95% Code gen −96% Agentic −94% | no file input |
| [Kimi K2.5](/models/moonshotai__kimi-k2.5/) Moonshot AI | 1445.2 +162.7 | $1.20 | Balanced −73% Summarise −77% Chat −72% Code gen −71% Agentic −77% | no file input |
| [DeepSeek V4 Pro 0423](/models/deepseek__deepseek-v4-pro/) DeepSeek | 1445.2 +162.7 | $1.21 | Balanced −72% Summarise −80% Chat −70% Code gen −68% Agentic −76% | no image, file input |
| [Qwen3.6 Max Preview](/models/qwen__qwen3.6-max-preview/) Qwen | 1446.8 +164.3 | $2.31 | Balanced −47% Summarise −49% Chat −40% Code gen −40% Agentic −38% | no image, file input |
| [Hy3](/models/tencent__hy3/) Tencent | 1440.7 +158.2 | $0.231 | Balanced −95% Summarise −95% Chat −95% Code gen −95% Agentic −95% | no image, file input |
| [Qwen3.8 27B](/models/qwen__qwen3.8-27b/) Qwen | 1440.7 +158.2 | $0.562 | Balanced −87% Summarise −93% Chat −84% Code gen −82% Agentic −87% | no file input |
| [GLM 4.6](/models/z-ai__glm-4.6/) Z.ai | 1439.9 +157.4 | $0.760 | Balanced −83% Summarise −84% Chat −83% Code gen −83% Agentic −85% | no image, file input |
| [Inkling](/models/thinkingmachines__inkling/) Thinking Machines | 1441.8 +159.3 | $1.73 | Balanced −61% Summarise −65% Chat −62% Code gen −60% Agentic −67% | no file input |
| [Qwen3.5 397B A17B](/models/qwen__qwen3.5-397b-a17b/) Qwen | 1438 +155.5 | $0.878 | Balanced −80% Summarise −81% Chat −77% Code gen −77% Agentic −76% | no file input |
| [Qwen3.6 Plus](/models/qwen__qwen3.6-plus/) Qwen | 1436.7 +154.2 | $0.731 | Balanced −83% Summarise −84% Chat −81% Code gen −81% Agentic −80% | no file input |
| [GLM 4.7](/models/z-ai__glm-4.7/) Z.ai | 1435.5 +153 | $0.738 | Balanced −83% Summarise −85% Chat −84% Code gen −83% Agentic −86% | no image, file input |
| [Gemma 4 26B A4B](/models/google__gemma-4-26b-a4b-it/) Google | 1433.9 +151.4 | $0.127 | Balanced −97% Summarise −97% Chat −97% Code gen −97% Agentic −97% | no file input |
| [GLM 5V Turbo](/models/z-ai__glm-5v-turbo/) Z.ai | 1437.2 +154.7 | $1.90 | Balanced −57% Summarise −58% Chat −60% Code gen −59% Agentic −64% | no file input |
| [DeepSeek V4 Flash 0423](/models/deepseek__deepseek-v4-flash/) DeepSeek | 1432.1 +149.6 | $0.113 | Balanced −97% Summarise −97% Chat −98% Code gen −98% Agentic −98% | no image, file input |
| [MiniMax M3](/models/minimax__minimax-m3/) MiniMax | 1432.1 +149.6 | $0.485 | Balanced −89% Summarise −90% Chat −89% Code gen −89% Agentic −91% | no file input |
| [GLM 4.5](/models/z-ai__glm-4.5/) Z.ai | 1430.3 +147.8 | $1.00 | Balanced −77% Summarise −79% Chat −79% Code gen −78% Agentic −81% | no image, file input |
| [MiMo-V2.5](/models/xiaomi__mimo-v2.5/) Xiaomi | 1427.5 +145 | $0.175 | Balanced −96% Summarise −96% Chat −97% Code gen −97% Agentic −97% | no file input |
| [R1 0528](/models/deepseek__deepseek-r1-0528/) DeepSeek | 1427.9 +145.4 | $0.920 | Balanced −79% Summarise −77% Chat −77% Code gen −78% Agentic −74% | no image, file input |
| [DeepSeek V3.2](/models/deepseek__deepseek-v3.2/) DeepSeek | 1424.5 +142 | $0.290 | Balanced −93% Summarise −91% Chat −95% Code gen −95% Agentic −93% | no image, file input |
| [DeepSeek V3.2 Exp](/models/deepseek__deepseek-v3.2-exp/) DeepSeek | 1422.4 +139.9 | $0.305 | Balanced −93% Summarise −89% Chat −94% Code gen −95% Agentic −90% | no image, file input |
| [Qwen3 VL 235B A22B Instruct](/models/qwen__qwen3-vl-235b-a22b-instruct/) Qwen | 1420.1 +137.6 | $0.370 | Balanced −92% Summarise −92% Chat −91% Code gen −91% Agentic −91% | no file input |
| [Qwen3 235B A22B Instruct 2507](/models/qwen__qwen3-235b-a22b-2507/) Qwen | 1419.3 +136.8 | $0.205 | Balanced −95% Summarise −96% Chat −95% Code gen −95% Agentic −94% | no image, file input |
| [DeepSeek V3.1](/models/deepseek__deepseek-chat-v3.1/) DeepSeek | 1419.7 +137.2 | $0.453 | Balanced −90% Summarise −88% Chat −89% Code gen −90% Agentic −87% | no image, file input |
| [Qwen3 Next 80B A3B Instruct](/models/qwen__qwen3-next-80b-a3b-instruct/) Qwen | 1417.3 +134.8 | $0.268 | Balanced −94% Summarise −95% Chat −93% Code gen −93% Agentic −93% | no image, file input |
| [DeepSeek V3.1 Terminus](/models/deepseek__deepseek-v3.1-terminus/) DeepSeek | 1417.1 +134.6 | $0.453 | Balanced −90% Summarise −88% Chat −89% Code gen −90% Agentic −87% | no image, file input |
| [Qwen3.5-122B-A10B](/models/qwen__qwen3.5-122b-a10b/) Qwen | 1417.1 +134.6 | $0.715 | Balanced −84% Summarise −86% Chat −81% Code gen −80% Agentic −82% | no file input |
| [Qwen3 235B A22B Thinking 2507](/models/qwen__qwen3-235b-a22b-thinking-2507/) Qwen | 1415.2 +132.7 | $0.748 | Balanced −83% Summarise −87% Chat −79% Code gen −79% Agentic −81% | no image, file input |
| [Inkling Small](/models/thinkingmachines__inkling-small/) Thinking Machines | 1413.7 +131.2 | $0.638 | Balanced −85% Summarise −85% Chat −87% Code gen −87% Agentic −88% | no file input |
| [Qwen3 Max](/models/qwen__qwen3-max/) Qwen | 1412.4 +129.9 | $1.56 | Balanced −64% Summarise −70% Chat −64% Code gen −62% Agentic −70% | no image, file input |
| [Qwen3.5-27B](/models/qwen__qwen3.5-27b/) Qwen | 1408.9 +126.4 | $0.536 | Balanced −88% Summarise −90% Chat −86% Code gen −85% Agentic −86% | no file input |
| [MiniMax M2.7](/models/minimax__minimax-m2.7/) MiniMax | 1404.6 +122.1 | $0.525 | Balanced −88% Summarise −89% Chat −89% Code gen −88% Agentic −90% | no image, file input |
| [Step 3.5 Flash](/models/stepfun__step-3.5-flash/) StepFun | 1403 +120.5 | $0.150 | Balanced −97% Summarise −96% Chat −96% Code gen −97% Agentic −95% | no image, file input |
| [Qwen3 VL 235B A22B Thinking](/models/qwen__qwen3-vl-235b-a22b-thinking/) Qwen | 1400.7 +118.2 | $1.30 | Balanced −70% Summarise −77% Chat −64% Code gen −63% Agentic −67% | no file input |
| [Qwen3.5-Flash](/models/qwen__qwen3.5-flash-02-23/) Qwen | 1397 +114.5 | $0.114 | Balanced −97% Summarise −97% Chat −97% Code gen −97% Agentic −97% | no file input |
| [Qwen3.5-35B-A3B](/models/qwen__qwen3.5-35b-a3b/) Qwen | 1394.4 +111.9 | $0.355 | Balanced −92% Summarise −94% Chat −91% Code gen −91% Agentic −93% | no file input |
| [Solar Pro 4](/models/upstage__solar-pro4/) Upstage | 1386.2 +103.7 | $0.525 | Balanced −88% Summarise −89% Chat −89% Code gen −88% Agentic −90% | no image, file input |
| [Qwen3 30B A3B Instruct 2507](/models/qwen__qwen3-30b-a3b-instruct-2507/) Qwen | 1384.1 +101.6 | $0.143 | Balanced −97% Summarise −96% Chat −97% Code gen −97% Agentic −96% | no image, file input |
| [GLM 4.5 Air](/models/z-ai__glm-4.5-air/) Z.ai | 1383.9 +101.4 | $0.310 | Balanced −93% Summarise −95% Chat −92% Code gen −92% Agentic −94% | no image, file input |
| [GLM 4.6V](/models/z-ai__glm-4.6v/) Z.ai | 1376.8 +94.3 | $0.450 | Balanced −90% Summarise −90% Chat −91% Code gen −91% Agentic −92% | no file input |
| [DeepSeek V3 0324](/models/deepseek__deepseek-chat-v3-0324/) DeepSeek | 1375 +92.5 | $0.438 | Balanced −90% Summarise −89% Chat −89% Code gen −90% Agentic −87% | no image, file input |
| [R1](/models/deepseek__deepseek-r1/) DeepSeek | 1372.7 +90.2 | $1.15 | Balanced −74% Summarise −69% Chat −72% Code gen −74% Agentic −66% | 128K → 64K context 16K → 16K max output no image, file input |
| [Qwen3 Next 80B A3B Thinking](/models/qwen__qwen3-next-80b-a3b-thinking/) Qwen | 1368.3 +85.8 | $0.413 | Balanced −91% Summarise −92% Chat −89% Code gen −89% Agentic −89% | no image, file input |
| [gpt-oss-120b](/models/openai__gpt-oss-120b/) OpenAI | 1365.4 +82.9 | $0.065 | Balanced −99% Summarise −99% Chat −98% Code gen −98% Agentic −98% | no image, file input |
| [Qwen3 235B A22B](/models/qwen__qwen3-235b-a22b/) Qwen | 1366.6 +84.1 | $0.796 | Balanced −82% Summarise −79% Chat −80% Code gen −82% Agentic −77% | 16K → 8K max output no image, file input |
| [MiniMax M2.5](/models/minimax__minimax-m2.5/) MiniMax | 1359.3 +76.8 | $0.521 | Balanced −88% Summarise −89% Chat −89% Code gen −88% Agentic −90% | no image, file input |
| [Gemma 3 27B](/models/google__gemma-3-27b-it/) Google | 1357.8 +75.3 | $0.100 | Balanced −98% Summarise −97% Chat −98% Code gen −98% Agentic −97% | no file input |
| [Mercury 2](/models/inception__mercury-2/) Inception | 1355.2 +72.7 | $0.375 | Balanced −91% Summarise −92% Chat −93% Code gen −92% Agentic −93% | no image, file input |
| [GLM 4.7 Flash](/models/z-ai__glm-4.7-flash/) Z.ai | 1350.9 +68.4 | $0.145 | Balanced −97% Summarise −98% Chat −96% Code gen −96% Agentic −97% | no image, file input |
| [MiniMax M1](/models/minimax__minimax-m1/) MiniMax | 1342.8 +60.3 | $0.850 | Balanced −81% Summarise −81% Chat −78% Code gen −79% Agentic −77% | no image, file input |
| [Qwen3 32B](/models/qwen__qwen3-32b/) Qwen | 1340.1 +57.6 | $0.130 | Balanced −97% Summarise −96% Chat −97% Code gen −97% Agentic −96% | no image, file input |
| [Trinity Large Thinking](/models/arcee-ai__trinity-large-thinking/) Arcee | 1340 +57.5 | $0.388 | Balanced −91% Summarise −91% Chat −92% Code gen −92% Agentic −92% | no image, file input |
| [MiniMax M2](/models/minimax__minimax-m2/) MiniMax | 1339.9 +57.4 | $0.525 | Balanced −88% Summarise −89% Chat −89% Code gen −88% Agentic −90% | no image, file input |
| [Gemma 3 12B](/models/google__gemma-3-12b-it/) Google | 1334.2 +51.7 | $0.075 | Balanced −98% Summarise −98% Chat −98% Code gen −98% Agentic −98% | no file input |
| [o3 Mini High](/models/openai__o3-mini-high/) OpenAI | 1336.6 +54.1 | $1.93 | Balanced −56% Summarise −56% Chat −56% Code gen −56% Agentic −56% | no image input |
| [DeepSeek V3](/models/deepseek__deepseek-chat/) DeepSeek | 1332.5 +50 | $0.500 | Balanced −89% Summarise −87% Chat −88% Code gen −88% Agentic −86% | 16K → 16K max output no image, file input |
| [GLM 4.5V](/models/z-ai__glm-4.5v/) Z.ai | 1332.8 +50.3 | $0.900 | Balanced −79% Summarise −79% Chat −82% Code gen −81% Agentic −83% | 128K → 66K context no file input |
| [Granite 4.2 8B](/models/ibm-granite__granite-4.2-8b/) IBM | 1317.8 +35.3 | $0.108 | Balanced −98% Summarise −98% Chat −98% Code gen −98% Agentic −98% | no image, file input |
| [Qwen3 30B A3B](/models/qwen__qwen3-30b-a3b/) Qwen | 1316.6 +34.1 | $0.215 | Balanced −95% Summarise −94% Chat −95% Code gen −95% Agentic −94% | no image, file input |
| [o3 Mini](/models/openai__o3-mini/) OpenAI | 1319.4 +36.9 | $1.93 | Balanced −56% Summarise −56% Chat −56% Code gen −56% Agentic −56% | no image input |
| [Gemma 3 4B](/models/google__gemma-3-4b-it/) Google | 1290.8 tie | $0.063 | Balanced −99% Summarise −98% Chat −99% Code gen −99% Agentic −98% | no file input no tool use |
| [gpt-oss-20b](/models/openai__gpt-oss-20b/) OpenAI | 1287.7 tie | $0.036 | Balanced −99% Summarise −99% Chat −99% Code gen −99% Agentic −99% | no image, file 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/)