---
title: "Compare alternatives to Mistral Large 2407 · Undominated.ai"
canonical: https://undominated.ai/alternatives/mistralai__mistral-large-2407/
description: "105 alternatives score at least as high as Mistral Large 2407 and cost no more under at least one listed workload. 16 preserve recorded capabilities; 89 have named trade-offs."
---

# Compare alternatives to Mistral Large 2407 · Undominated.ai

> 105 alternatives score at least as high as Mistral Large 2407 and cost no more under at least one listed workload. 16 preserve recorded capabilities; 89 have named trade-offs.

# Alternatives to Mistral Large 2407

Mistral · LMArena 1266.1 · $3.00/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.

## 16 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, **105** score at least as high as Mistral Large 2407 and cost no more under at least one listed workload, with at least one of those dimensions improved. **101** of them cost less; the rest match the price and have a higher score. **16** match or beat its recorded context, maximum output, input modes, tool use and extended reasoning. **89** 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 | Mistral Large 2407 $/M | Recorded capabilities preserved | Recorded capability losses |
| --- | --- | --- | --- |
| Balanced | $3.00 | 14 | 86 |
| Summarise | $1.69 | 12 | 89 |
| Chat | $3.06 | 10 | 83 |
| Code gen | $4.26 | 10 | 84 |
| Agentic | $1.53 | 10 | 83 |

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 | 1266.1 |
| --- | --- |
| Context window | 131K |
| Max output | 104K |
| Input modes | text, file |
| Tool use | yes |
| Extended reasoning | no |

Preserving recorded capabilities requires matching or beating these fields. [Full record for Mistral Large 2407](/models/mistralai__mistral-large-2407/), or [check Mistral Large 2407 against the whole catalogue](/check/mistralai__mistral-large-2407/).

## Recorded capabilities preserved 16

Each option has a higher score or a lower price, with neither dimension worse under the listed workloads. It matches or beats Mistral Large 2407 on recorded context, maximum output, input modes, tool use and extended reasoning.

| # | Model | Intelligence | $/M | Holds under |
| --- | --- | --- | --- | --- |
| 1 | [Muse Spark 1.3](/models/meta__muse-spark-1.3/) Meta | 1489.9 +223.8 | $2.00 | Balanced −33% Summarise −36% Chat −31% Code gen −30% Agentic −32% |
| 2 | [Muse Spark 1.2](/models/meta__muse-spark-1.2/) Meta | 1483.2 +217.1 | $2.00 | Balanced −33% Summarise −36% Chat −31% Code gen −30% Agentic −32% |
| 3 | [Muse Spark 1.1](/models/meta__muse-spark-1.1/) Meta | 1479.2 +213.1 | $2.00 | Balanced −33% Summarise −36% Chat −31% Code gen −30% Agentic −32% |
| 4 | [Grok 4.5](/models/x-ai__grok-4.5/) xAI | 1448.1 +182 | $3.00 | Balanced same price |
| 5 | [GPT-5.6 Luna](/models/openai__gpt-5.6-luna/) OpenAI | 1431 +164.9 | $0.450 | Balanced −85% Summarise −88% Chat −82% Code gen −82% Agentic −84% |
| 6 | [Grok 4.6](/models/x-ai__grok-4.6/) xAI | 1427.4 +161.3 | $3.00 | Balanced same price |
| 7 | [Mistral Medium 3.5](/models/mistralai__mistral-medium-3-5/) Mistral | 1421.2 +155.1 | $3.00 | Balanced same price |
| 8 | [GPT-5.4 Mini](/models/openai__gpt-5.4-mini/) OpenAI | 1411.4 +145.3 | $1.69 | Balanced −44% Summarise −56% Chat −33% Code gen −31% Agentic −40% |
| 9 | [Grok 4.3](/models/x-ai__grok-4.3/) xAI | 1396.7 +130.6 | $1.56 | Balanced −48% Summarise −40% Chat −53% Code gen −55% Agentic −47% |
| 10 | [GPT-6 Luna](/models/openai__gpt-6-luna/) OpenAI | 1391.5 +125.4 | $0.200 | Balanced −93% Summarise −94% Chat −92% Code gen −92% Agentic −93% |
| 11 | [Grok 4.7](/models/x-ai__grok-4.7/) xAI | 1399.9 +133.8 | $3.00 | Balanced same price |
| 12 | [GPT-5 Mini](/models/openai__gpt-5-mini/) OpenAI | 1373.2 +107.1 | $0.688 | Balanced −77% Summarise −84% Chat −71% Code gen −70% Agentic −75% |
| 13 | [GPT-5.4 Nano](/models/openai__gpt-5.4-nano/) OpenAI | 1372.1 +106 | $0.463 | Balanced −85% Summarise −88% Chat −82% Code gen −81% Agentic −84% |
| 14 | [GPT-5 Nano](/models/openai__gpt-5-nano/) OpenAI | 1320 +53.9 | $0.138 | Balanced −95% Summarise −97% Chat −94% Code gen −94% Agentic −95% |
| 15 | [GPT-5.1](/models/openai__gpt-5.1/) OpenAI | 1422.2 +156.1 | $1.37 summarise | Summarise −19% |
| 16 | [GPT-5](/models/openai__gpt-5/) OpenAI | 1406.1 +140 | $1.37 summarise | Summarise −19% |

## Alternatives with recorded capability losses 89

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 +224.9 | $0.540 | Balanced −82% Summarise −80% Chat −84% Code gen −84% Agentic −84% | no file input |
| [Gemini 3.8 Flash](/models/google__gemini-3.8-flash/) Google | 1497 +230.9 | $3.00 | Balanced same price Summarise −16% | 105K → 66K max output |
| [Gemini 3.7 Flash](/models/google__gemini-3.7-flash/) Google | 1487 +220.9 | $3.00 | Balanced same price Summarise −16% | 105K → 66K max output |
| [Gemini 3.6 Flash](/models/google__gemini-3.6-flash/) Google | 1479.5 +213.4 | $1.50 | Balanced −50% Summarise −58% Chat −43% Code gen −41% Agentic −48% | 105K → 66K max output |
| [GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) Z.ai | 1469.6 +203.5 | $0.238 | Balanced −92% Summarise −92% Chat −92% Code gen −92% Agentic −91% | no file input |
| [GLM 5.3](/models/z-ai__glm-5.3/) Z.ai | 1471.4 +205.3 | $1.00 | Balanced −67% Summarise −80% Chat −52% Code gen −50% Agentic −57% | no file input |
| [GLM 5.2](/models/z-ai__glm-5.2/) Z.ai | 1470.4 +204.3 | $1.12 | Balanced −63% Summarise −75% Chat −49% Code gen −47% Agentic −55% | no file input |
| [MiMo-V2.5-Pro](/models/xiaomi__mimo-v2.5-pro/) Xiaomi | 1465 +198.9 | $0.544 | Balanced −82% Summarise −80% Chat −84% Code gen −84% Agentic −84% | no file input |
| [DeepSeek V4.1 Flash](/models/deepseek__deepseek-v4.1-flash/) DeepSeek | 1462.5 +196.4 | $0.182 | Balanced −94% Summarise −96% Chat −92% Code gen −92% Agentic −93% | no file input |
| [MiMo-V2.6-Flash](/models/xiaomi__mimo-v2.6-flash/) Xiaomi | 1456.4 +190.3 | $0.175 | Balanced −94% Summarise −94% Chat −95% Code gen −95% Agentic −95% | no file input |
| [GLM 5.1](/models/z-ai__glm-5.1/) Z.ai | 1461.5 +195.4 | $1.83 | Balanced −39% Summarise −32% Chat −34% Code gen −37% Agentic −20% | no file input |
| [Qwen3.7 Plus](/models/qwen__qwen3.7-plus/) Qwen | 1454.6 +188.5 | $0.560 | Balanced −81% Summarise −83% Chat −80% Code gen −79% Agentic −80% | no file input |
| [Kimi K2.6](/models/moonshotai__kimi-k2.6/) Moonshot AI | 1455.5 +189.4 | $0.961 | Balanced −68% Summarise −73% Chat −62% Code gen −62% Agentic −64% | no file input |
| [Gemma 4 31B](/models/google__gemma-4-31b-it/) Google | 1443.4 +177.3 | $0.205 | Balanced −93% Summarise −91% Chat −92% Code gen −93% Agentic −88% | 105K → 16K max output no file input |
| [GLM 5](/models/z-ai__glm-5/) Z.ai | 1446.3 +180.2 | $1.09 | Balanced −64% Summarise −63% Chat −62% Code gen −63% Agentic −61% | no file input |
| [Kimi K2.5](/models/moonshotai__kimi-k2.5/) Moonshot AI | 1445.2 +179.1 | $1.20 | Balanced −60% Summarise −66% Chat −54% Code gen −53% Agentic −57% | no file input |
| [DeepSeek V4 Pro 0423](/models/deepseek__deepseek-v4-pro/) DeepSeek | 1445.2 +179.1 | $1.21 | Balanced −60% Summarise −70% Chat −49% Code gen −47% Agentic −54% | no file input |
| [Hy3](/models/tencent__hy3/) Tencent | 1440.7 +174.6 | $0.231 | Balanced −92% Summarise −93% Chat −91% Code gen −92% Agentic −91% | no file input |
| [Qwen3.6 Max Preview](/models/qwen__qwen3.6-max-preview/) Qwen | 1446.8 +180.7 | $2.31 | Balanced −23% Summarise −24% Code gen −3% | 105K → 66K max output no file input |
| [Qwen3.8 27B](/models/qwen__qwen3.8-27b/) Qwen | 1440.7 +174.6 | $0.562 | Balanced −81% Summarise −89% Chat −72% Code gen −71% Agentic −76% | no file input |
| [GLM 4.6](/models/z-ai__glm-4.6/) Z.ai | 1439.9 +173.8 | $0.760 | Balanced −75% Summarise −77% Chat −72% Code gen −72% Agentic −73% | 105K → 16K max output no file input |
| [Inkling](/models/thinkingmachines__inkling/) Thinking Machines | 1441.8 +175.7 | $1.73 | Balanced −43% Summarise −48% Chat −36% Code gen −35% Agentic −38% | no file input |
| [Qwen3.5 397B A17B](/models/qwen__qwen3.5-397b-a17b/) Qwen | 1438 +171.9 | $0.878 | Balanced −71% Summarise −71% Chat −62% Code gen −63% Agentic −55% | 105K → 82K max output no file input |
| [Qwen3.6 Plus](/models/qwen__qwen3.6-plus/) Qwen | 1436.7 +170.6 | $0.731 | Balanced −76% Summarise −76% Chat −68% Code gen −69% Agentic −63% | 105K → 66K max output no file input |
| [Gemma 4 26B A4B](/models/google__gemma-4-26b-a4b-it/) Google | 1433.9 +167.8 | $0.127 | Balanced −96% Summarise −96% Chat −95% Code gen −95% Agentic −95% | no file input |
| [GLM 4.7](/models/z-ai__glm-4.7/) Z.ai | 1435.5 +169.4 | $0.738 | Balanced −75% Summarise −78% Chat −72% Code gen −72% Agentic −73% | no file input |
| [Gemini 3.5 Flash Lite](/models/google__gemini-3.5-flash-lite/) Google | 1434.7 +168.6 | $0.850 | Balanced −72% Summarise −80% Chat −64% Code gen −62% Agentic −69% | 105K → 66K max output |
| [DeepSeek V4 Flash 0423](/models/deepseek__deepseek-v4-flash/) DeepSeek | 1432.1 +166 | $0.113 | Balanced −96% Summarise −96% Chat −97% Code gen −97% Agentic −96% | no file input |
| [GLM 5V Turbo](/models/z-ai__glm-5v-turbo/) Z.ai | 1437.2 +171.1 | $1.90 | Balanced −37% Summarise −37% Chat −34% Code gen −34% Agentic −31% | no file input |
| [MiniMax M3](/models/minimax__minimax-m3/) MiniMax | 1432.1 +166 | $0.485 | Balanced −84% Summarise −85% Chat −82% Code gen −82% Agentic −82% | no file input |
| [GLM 4.5](/models/z-ai__glm-4.5/) Z.ai | 1430.3 +164.2 | $1.00 | Balanced −67% Summarise −68% Chat −64% Code gen −64% Agentic −64% | 105K → 98K max output no file input |
| [MiMo-V2.5](/models/xiaomi__mimo-v2.5/) Xiaomi | 1427.5 +161.4 | $0.175 | Balanced −94% Summarise −94% Chat −95% Code gen −95% Agentic −95% | no file input |
| [R1 0528](/models/deepseek__deepseek-r1-0528/) DeepSeek | 1427.9 +161.8 | $0.920 | Balanced −69% Summarise −65% Chat −62% Code gen −65% Agentic −51% | 105K → 33K max output no file input |
| [DeepSeek V3.2](/models/deepseek__deepseek-v3.2/) DeepSeek | 1424.5 +158.4 | $0.290 | Balanced −90% Summarise −86% Chat −91% Code gen −92% Agentic −87% | 105K → 66K max output no file input |
| [DeepSeek V3.2 Exp](/models/deepseek__deepseek-v3.2-exp/) DeepSeek | 1422.4 +156.3 | $0.305 | Balanced −90% Summarise −84% Chat −89% Code gen −92% Agentic −81% | no file input |
| [Qwen3 VL 235B A22B Instruct](/models/qwen__qwen3-vl-235b-a22b-instruct/) Qwen | 1420.1 +154 | $0.370 | Balanced −88% Summarise −88% Chat −85% Code gen −86% Agentic −84% | 105K → 33K max output no file input |
| [Qwen3 235B A22B Instruct 2507](/models/qwen__qwen3-235b-a22b-2507/) Qwen | 1419.3 +153.2 | $0.205 | Balanced −93% Summarise −93% Chat −91% Code gen −91% Agentic −90% | 105K → 16K max output no file input |
| [DeepSeek V3.1](/models/deepseek__deepseek-chat-v3.1/) DeepSeek | 1419.7 +153.6 | $0.453 | Balanced −85% Summarise −82% Chat −82% Code gen −83% Agentic −75% | 105K → 33K max output no file input |
| [Qwen3 Next 80B A3B Instruct](/models/qwen__qwen3-next-80b-a3b-instruct/) Qwen | 1417.3 +151.2 | $0.268 | Balanced −91% Summarise −92% Chat −88% Code gen −88% Agentic −87% | no file input |
| [DeepSeek V3.1 Terminus](/models/deepseek__deepseek-v3.1-terminus/) DeepSeek | 1417.1 +151 | $0.453 | Balanced −85% Summarise −82% Chat −82% Code gen −83% Agentic −75% | no file input |
| [Qwen3.5-122B-A10B](/models/qwen__qwen3.5-122b-a10b/) Qwen | 1417.1 +151 | $0.715 | Balanced −76% Summarise −79% Chat −68% Code gen −68% Agentic −65% | 105K → 66K max output no file input |
| [Gemini 2.5 Flash](/models/google__gemini-2.5-flash/) Google | 1417 +150.9 | $0.850 | Balanced −72% Summarise −80% Chat −64% Code gen −62% Agentic −69% | 105K → 66K max output |
| [Gemini 3.1 Flash Lite Preview](/models/google__gemini-3.1-flash-lite-preview/) Google | 1415.7 +149.6 | $0.563 | Balanced −81% Summarise −85% Chat −78% Code gen −77% Agentic −80% | 105K → 66K max output |
| [Qwen3 235B A22B Thinking 2507](/models/qwen__qwen3-235b-a22b-thinking-2507/) Qwen | 1415.2 +149.1 | $0.748 | Balanced −75% Summarise −80% Chat −65% Code gen −65% Agentic −65% | no file input |
| [Inkling Small](/models/thinkingmachines__inkling-small/) Thinking Machines | 1413.7 +147.6 | $0.638 | Balanced −79% Summarise −77% Chat −79% Code gen −80% Agentic −77% | no file input |
| [Qwen3 Max](/models/qwen__qwen3-max/) Qwen | 1412.4 +146.3 | $1.56 | Balanced −48% Summarise −55% Chat −40% Code gen −39% Agentic −43% | 105K → 66K max output no file input |
| [Qwen3.5-27B](/models/qwen__qwen3.5-27b/) Qwen | 1408.9 +142.8 | $0.536 | Balanced −82% Summarise −84% Chat −76% Code gen −76% Agentic −74% | 105K → 66K max output no file input |
| [MiniMax M2.7](/models/minimax__minimax-m2.7/) MiniMax | 1404.6 +138.5 | $0.525 | Balanced −83% Summarise −84% Chat −81% Code gen −81% Agentic −81% | no file input |
| [Step 3.5 Flash](/models/stepfun__step-3.5-flash/) StepFun | 1403 +136.9 | $0.150 | Balanced −95% Summarise −93% Chat −94% Code gen −95% Agentic −91% | 105K → 66K max output no file input |
| [Qwen3.5-Flash](/models/qwen__qwen3.5-flash-02-23/) Qwen | 1397 +130.9 | $0.114 | Balanced −96% Summarise −96% Chat −95% Code gen −96% Agentic −94% | 105K → 66K max output no file input |
| [Qwen3 VL 235B A22B Thinking](/models/qwen__qwen3-vl-235b-a22b-thinking/) Qwen | 1400.7 +134.6 | $1.30 | Balanced −57% Summarise −66% Chat −40% Code gen −40% Agentic −39% | 105K → 33K max output no file input |
| [Qwen3.5-35B-A3B](/models/qwen__qwen3.5-35b-a3b/) Qwen | 1394.4 +128.3 | $0.355 | Balanced −88% Summarise −91% Chat −85% Code gen −85% Agentic −86% | 105K → 33K max output no file input |
| [Claude Haiku 4.5](/models/anthropic__claude-haiku-4.5/) Anthropic | 1396.1 +130 | $2.00 | Balanced −33% Summarise −44% Chat −24% Code gen −22% Agentic −30% | 105K → 64K max output |
| [Solar Pro 4](/models/upstage__solar-pro4/) Upstage | 1386.2 +120.1 | $0.525 | Balanced −83% Summarise −84% Chat −81% Code gen −81% Agentic −81% | no file input |
| [Qwen3 30B A3B Instruct 2507](/models/qwen__qwen3-30b-a3b-instruct-2507/) Qwen | 1384.1 +118 | $0.143 | Balanced −95% Summarise −94% Chat −94% Code gen −95% Agentic −92% | no file input |
| [GLM 4.5 Air](/models/z-ai__glm-4.5-air/) Z.ai | 1383.9 +117.8 | $0.310 | Balanced −90% Summarise −92% Chat −87% Code gen −87% Agentic −89% | 105K → 98K max output no file input |
| [GLM 4.6V](/models/z-ai__glm-4.6v/) Z.ai | 1376.8 +110.7 | $0.450 | Balanced −85% Summarise −85% Chat −85% Code gen −85% Agentic −84% | 105K → 33K max output no file input |
| [DeepSeek V3 0324](/models/deepseek__deepseek-chat-v3-0324/) DeepSeek | 1375 +108.9 | $0.438 | Balanced −85% Summarise −83% Chat −82% Code gen −84% Agentic −76% | no file input |
| [R1](/models/deepseek__deepseek-r1/) DeepSeek | 1372.7 +106.6 | $1.15 | Balanced −62% Summarise −53% Chat −54% Code gen −58% Agentic −37% | 131K → 64K context 105K → 16K max output no file input |
| [Qwen3 Next 80B A3B Thinking](/models/qwen__qwen3-next-80b-a3b-thinking/) Qwen | 1368.3 +102.2 | $0.413 | Balanced −86% Summarise −88% Chat −81% Code gen −82% Agentic −80% | 105K → 33K max output no file input |
| [gpt-oss-120b](/models/openai__gpt-oss-120b/) OpenAI | 1365.4 +99.3 | $0.065 | Balanced −98% Summarise −98% Chat −97% Code gen −97% Agentic −97% | no file input |
| [Qwen3 235B A22B](/models/qwen__qwen3-235b-a22b/) Qwen | 1366.6 +100.5 | $0.796 | Balanced −73% Summarise −69% Chat −67% Code gen −70% Agentic −57% | 105K → 8K max output no file input |
| [Nova 2 Lite](/models/amazon__nova-2-lite-v1/) Amazon | 1361.8 +95.7 | $0.850 | Balanced −72% Summarise −76% Chat −61% Code gen −62% Agentic −59% | 105K → 66K max output |
| [MiniMax M2.5](/models/minimax__minimax-m2.5/) MiniMax | 1359.3 +93.2 | $0.521 | Balanced −83% Summarise −84% Chat −81% Code gen −81% Agentic −81% | no file input |
| [Gemma 3 27B](/models/google__gemma-3-27b-it/) Google | 1357.8 +91.7 | $0.100 | Balanced −97% Summarise −95% Chat −96% Code gen −97% Agentic −94% | no file input |
| [Mercury 2](/models/inception__mercury-2/) Inception | 1355.2 +89.1 | $0.375 | Balanced −88% Summarise −88% Chat −88% Code gen −88% Agentic −88% | 131K → 128K context 105K → 50K max output no file input |
| [GLM 4.7 Flash](/models/z-ai__glm-4.7-flash/) Z.ai | 1350.9 +84.8 | $0.145 | Balanced −95% Summarise −96% Chat −94% Code gen −94% Agentic −95% | no file input |
| [o4 Mini](/models/openai__o4-mini/) OpenAI | 1353.2 +87.1 | $1.93 | Balanced −36% Summarise −39% Chat −29% Code gen −29% Agentic −28% | 105K → 100K max output |
| [MiniMax M1](/models/minimax__minimax-m1/) MiniMax | 1342.8 +76.7 | $0.850 | Balanced −72% Summarise −71% Chat −63% Code gen −65% Agentic −56% | 105K → 40K max output no file input |
| [Qwen3 32B](/models/qwen__qwen3-32b/) Qwen | 1340.1 +74 | $0.130 | Balanced −96% Summarise −95% Chat −95% Code gen −95% Agentic −93% | 105K → 16K max output no file input |
| [Trinity Large Thinking](/models/arcee-ai__trinity-large-thinking/) Arcee | 1340 +73.9 | $0.388 | Balanced −87% Summarise −87% Chat −87% Code gen −87% Agentic −86% | 105K → 80K max output no file input |
| [MiniMax M2](/models/minimax__minimax-m2/) MiniMax | 1339.9 +73.8 | $0.525 | Balanced −83% Summarise −84% Chat −81% Code gen −81% Agentic −82% | no file input |
| [GPT-4.1 Mini](/models/openai__gpt-4.1-mini/) OpenAI | 1340.4 +74.3 | $0.700 | Balanced −77% Summarise −78% Chat −74% Code gen −74% Agentic −74% | 105K → 33K max output |
| [Gemma 3 12B](/models/google__gemma-3-12b-it/) Google | 1334.2 +68.1 | $0.075 | Balanced −98% Summarise −97% Chat −97% Code gen −97% Agentic −96% | 105K → 16K max output no file input |
| [DeepSeek V3](/models/deepseek__deepseek-chat/) DeepSeek | 1332.5 +66.4 | $0.500 | Balanced −83% Summarise −81% Chat −79% Code gen −81% Agentic −73% | 105K → 16K max output no file input |
| [o3 Mini High](/models/openai__o3-mini-high/) OpenAI | 1336.6 +70.5 | $1.93 | Balanced −36% Summarise −34% Chat −26% Code gen −29% Agentic −17% | 105K → 100K max output |
| [GLM 4.5V](/models/z-ai__glm-4.5v/) Z.ai | 1332.8 +66.7 | $0.900 | Balanced −70% Summarise −69% Chat −70% Code gen −70% Agentic −68% | 131K → 66K context 105K → 16K max output no file input |
| [Granite 4.2 8B](/models/ibm-granite__granite-4.2-8b/) IBM | 1317.8 +51.7 | $0.108 | Balanced −96% Summarise −97% Chat −96% Code gen −96% Agentic −96% | no file input |
| [Qwen3 30B A3B](/models/qwen__qwen3-30b-a3b/) Qwen | 1316.6 +50.5 | $0.215 | Balanced −93% Summarise −92% Chat −91% Code gen −92% Agentic −88% | 105K → 16K max output no file input |
| [o3 Mini](/models/openai__o3-mini/) OpenAI | 1319.4 +53.3 | $1.93 | Balanced −36% Summarise −34% Chat −26% Code gen −29% Agentic −17% | 105K → 100K max output |
| [Gemma 3 4B](/models/google__gemma-3-4b-it/) Google | 1290.8 +24.7 | $0.063 | Balanced −98% Summarise −97% Chat −98% Code gen −98% Agentic −96% | 105K → 16K max output no file input no tool use |
| [gpt-oss-20b](/models/openai__gpt-oss-20b/) OpenAI | 1287.7 +21.6 | $0.036 | Balanced −99% Summarise −99% Chat −99% Code gen −99% Agentic −98% | 105K → 33K max output no file input |
| [GPT-4o-mini (2024-07-18)](/models/openai__gpt-4o-mini-2024-07-18/) OpenAI | 1286.4 +20.3 | $0.263 | Balanced −91% Summarise −91% Chat −90% Code gen −90% Agentic −89% | 131K → 128K context 105K → 16K max output |
| [GPT-4.1 Nano](/models/openai__gpt-4.1-nano/) OpenAI | 1284.8 +18.7 | $0.175 | Balanced −94% Summarise −94% Chat −94% Code gen −94% Agentic −93% | 105K → 33K max output |
| [Llama 3.3 70B Instruct](/models/meta-llama__llama-3.3-70b-instruct/) Meta | 1274.1 tie | $0.201 | Balanced −93% Summarise −91% Chat −92% Code gen −93% Agentic −89% | 105K → 16K max output no file input |
| [Qwen2.5 72B Instruct](/models/qwen__qwen-2.5-72b-instruct/) Qwen | 1269 tie | $0.370 | Balanced −88% Summarise −79% Chat −88% Code gen −91% Agentic −76% | 131K → 33K context 105K → 16K max output no file input |
| [Gemini 3.5 Flash](/models/google__gemini-3.5-flash/) Google | 1477.7 +211.6 | $1.49 summarise | Summarise −12% | 105K → 66K max output |
| [Kimi K3](/models/moonshotai__kimi-k3/) Moonshot AI | 1475.9 +209.8 | $1.23 summarise | Summarise −27% | no file input |
| [Gemini 2.5 Pro](/models/google__gemini-2.5-pro/) Google | 1457.8 +191.7 | $1.37 summarise | Summarise −19% | 105K → 66K max output |

## 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/)