---
title: "Mistral Medium 3.5 vs Mistral Small 3 — Mistral Medium 3.5 scores higher, Mistral Small 3 costs less · Undominated.ai"
canonical: https://undominated.ai/compare/mistralai__mistral-medium-3-5--vs--mistralai__mistral-small-24b-instruct-2501/
description: "LMArena general score: Mistral Medium 3.5 1420.7 ±6.4, Mistral Small 3 1233.6 ±5.9. On a balanced workload (3 tokens in per 1 out), Mistral Medium 3.5 costs $3.00 and Mistral Small 3 $0.058 per 1M tokens. Neither is both better and cheaper."
---

# Mistral Medium 3.5 vs Mistral Small 3 — Mistral Medium 3.5 scores higher, Mistral Small 3 costs less · Undominated.ai

> LMArena general score: Mistral Medium 3.5 1420.7 ±6.4, Mistral Small 3 1233.6 ±5.9. On a balanced workload (3 tokens in per 1 out), Mistral Medium 3.5 costs $3.00 and Mistral Small 3 $0.058 per 1M tokens. Neither is both better and cheaper.

Model comparison · accepted catalogue facts 2026-11-22

# Mistral Medium 3.5 vs Mistral Small 3

Neither model has both an equal-or-higher measured score and an equal-or-lower estimated price in this pair. Retaining your current model is a valid outcome.

Both models belong to the [Mistral, Codestral, Devstral and Voxtral family](/families/mistral/). Inclusion does not recommend either model. This is a direct pair comparison; global frontier membership is not its verdict.

 [Technical deep dive](#deep-dive-heading)[Interactive decision workspace](#workspace)[All published comparisons](https://undominated.ai/compare/#catalogue-heading)
 [Mistral Medium 3.5](https://undominated.ai/models/mistralai__mistral-medium-3-5/)

LMArena general · Elo · higher is better

Scale starts at 1040 Elo

 **

1420.7

Balanced effective USD / 1M tokens · lower is better

 **

$3.00/M

 [Mistral Small 3](https://undominated.ai/models/mistralai__mistral-small-24b-instruct-2501/)

LMArena general · Elo · higher is better

Scale starts at 1040 Elo

 **

1233.6

Balanced effective USD / 1M tokens · lower is better

 **

$0.058/M

In-Depth Analysis

## Mistral Medium 3.5 vs Mistral Small 3: Measured Technical Breakdown

Comprehensive comparison across measured human-preference evaluation, effective production token costs, architectural limits, and migration trade-offs.

 Measured Capability (LMArena) **Mistral Medium 3.5** leads by **187.1 Elo**

Mistral Medium 3.5: **1420.7** ±6.4 · Mistral Small 3: **1233.6** ±5.88 Statistically significant preference separation

### Cost Comparison Across Canonical Production Workloads

Rates represent effective cost per 1M tokens under standard token blends. Cached prompt reads are factored according to workload context reuse.

| Workload & Ratio | Mistral Medium 3.5 | Mistral Small 3 | Cost Difference | Advantage |
| --- | --- | --- | --- | --- |
| Balanced 3 tokens in per 1 out | $3.00 /1M tokens | $0.058 /1M tokens | $2.94 (98% diff) | Mistral Small 3 costs less |
| Summarise Huge input, tiny output | $1.80 /1M tokens | $0.052 /1M tokens | $1.75 (97% diff) | Mistral Small 3 costs less |
| Chat Long cached system prompt | $3.90 /1M tokens | $0.062 /1M tokens | $3.84 (98% diff) | Mistral Small 3 costs less |
| Code gen Output dominates | $5.10 /1M tokens | $0.068 /1M tokens | $5.03 (99% diff) | Mistral Small 3 costs less |
| Agentic Context replayed each turn | $2.40 /1M tokens | $0.055 /1M tokens | $2.35 (98% diff) | Mistral Small 3 costs less |

### Architectural & Operational Specifications

| Specification | Mistral Medium 3.5 | Mistral Small 3 | Operational Note |
| --- | --- | --- | --- |
| Context window | 262,144 tokens | 32,768 tokens | Mistral Medium 3.5 has a 8.0× larger context window |
| Max output generation | 209,715 tokens | 16,384 tokens | Mistral Medium 3.5 allows longer single-turn completions |
| Base input price | $1.50 / 1M tokens | $0.050 / 1M tokens | Mistral Small 3 input rate is cheaper |
| Base output price | $7.50 / 1M tokens | $0.080 / 1M tokens | Mistral Small 3 output rate is cheaper |
| Cached input price | Not listed / standard rate | Not listed / standard rate | — |
| Reasoning & thinking tokens | Supported; standard rates | Standard generation | — |
| Input modalities | text, image, file | text | — |
| Tool calling / function use | Supported | Not listed | Mistral Medium 3.5 declares function calling / tool support |
| Open weights & licence | Proprietary (API-only) | Proprietary (API-only) | — |
| Provider & reseller market | Mistral · 2 provider offers | Mistral · 2 provider offers | — |

#### When to Choose Mistral Medium 3.5

 - Higher measured general capability (1420.7 Elo on human evaluation).
 - Larger context window (262,144 tokens) for long-document or repo-level context.
 - Higher maximum completion limit (209,715 tokens).
 - Broader multimodal input support: text, image, file.
 - Direct integration with Mistral tooling and API features.

#### When to Choose Mistral Small 3

 - Direct integration with Mistral tooling and API features.
 Risks when moving from Mistral Medium 3.5 → Mistral Small 3: - Context window: 262,144 → 32,768 tokens.
- Output limit: 209,715 → 16,384 tokens.
- Tool use is not supported by the candidate.
- Reasoning is not supported by the candidate.
- image input is not supported by the candidate.
- file input is not supported by the candidate.

### Detailed Evidence Passports & Independent Audits

 [Mistral Medium 3.5 Full model card, pricing ladder & provider offers →](https://undominated.ai/models/mistralai__mistral-medium-3-5/) [Mistral Small 3 Full model card, pricing ladder & provider offers →](https://undominated.ai/models/mistralai__mistral-small-24b-instruct-2501/) [Alternatives to Mistral Medium 3.5 Better-and-cheaper dominance audit →](https://undominated.ai/check/mistralai__mistral-medium-3-5/) [Alternatives to Mistral Small 3 Better-and-cheaper dominance audit →](https://undominated.ai/check/mistralai__mistral-small-24b-instruct-2501/)

Compare · model decision

## Choose two or three models

Inspect the differences, estimate your workload and keep the evidence. All standard catalogue models are available, including unrated ones.

Catalogue facts **2026-11-22**

 A · Current or starting model Choose a model Aion 3.5 · Aion Labs · unrated Aion 3.5 Mini · Aion Labs · unrated Aion-2.0 · Aion Labs · unrated Aion-3.0 · Aion Labs · unrated Aion-3.0-Mini · Aion Labs · unrated Aion-RP 1.0 (8B) · Aion Labs · unrated Auto Router · OpenRouter · unrated Auto Router (Beta) · OpenRouter · unrated Beam 1.0 501B A23B · Reflection Body Builder (beta) · OpenRouter · unrated Claude Fable 5 · Anthropic Claude Fable 5.1 · Anthropic Claude Fable 5.2 · Anthropic Claude Haiku 4.5 · Anthropic Claude Haiku 5.5 · Anthropic Claude Opus 4.1 · Anthropic Claude Opus 4.5 · Anthropic Claude Opus 4.6 · Anthropic Claude Opus 4.7 · Anthropic Claude Opus 4.8 · Anthropic Claude Opus 5 · Anthropic Claude Opus 5.5 · Anthropic Claude Sonnet 4.5 · Anthropic Claude Sonnet 4.6 · Anthropic Claude Sonnet 5 · Anthropic Claude Sonnet 5.5 · Anthropic Codestral 2508 · Mistral · unrated Command A · Cohere · unrated Command A+ · Cohere · unrated Command R (08-2024) · Cohere Command R+ (08-2024) · Cohere Command R7B (12-2024) · Cohere · unrated Cydonia 24B V4.1 · Thedrummer · unrated DaisyRose 27B · Radixark · unrated DeepSeek V3 · DeepSeek DeepSeek V3 0324 · DeepSeek DeepSeek V3.1 · DeepSeek DeepSeek V3.1 Terminus · DeepSeek DeepSeek V3.2 · DeepSeek DeepSeek V3.2 Exp · DeepSeek DeepSeek V4 Flash 0423 · DeepSeek DeepSeek V4 Flash 0731 · DeepSeek · unrated DeepSeek V4 Flash Vision Exp · DeepSeek · unrated DeepSeek V4 Pro 0423 · DeepSeek DeepSeek V4 Pro 0813 · DeepSeek · unrated DeepSeek V4.1 Flash · DeepSeek DeepSeek V4.1 Flash 1017 · DeepSeek · unrated Ember-1 · Fireworks · unrated ERNIE-Light-DT-1.0 · Baidu · unrated Extract · Scaledown · unrated Free Models Router · OpenRouter · unrated Fugu Max · Sakana AI · unrated Fugu Ultra · Sakana AI · unrated Fugu Ultra v2 · Sakana AI · unrated Fusion · OpenRouter · unrated Gemini 2.5 Flash · Google Gemini 2.5 Flash Lite · Google · unrated Gemini 2.5 Pro · Google Gemini 2.5 Pro Preview 06-05 · Google · unrated Gemini 3 Flash Preview · Google · unrated Gemini 3.1 Flash Lite · Google · unrated Gemini 3.1 Flash Lite Preview · Google Gemini 3.1 Pro Preview · Google Gemini 3.1 Pro Preview Custom Tools · Google · unrated Gemini 3.5 Flash · Google Gemini 3.5 Flash Lite · Google Gemini 3.6 Flash · Google Gemini 3.7 Flash · Google Gemini 3.8 Flash · Google Gemini 4 Argon · Google Gemini 4 Carbon · Google Gemini 4 Hydrogen · Google Gemini 4 Neon · Google Gemini Omni 1.1 Flash · Google · unrated Gemini Omni 1.2 Flash · Google · unrated Gemma 2 27B · Google Gemma 3 12B · Google Gemma 3 27B · Google Gemma 3 4B · Google Gemma 4 26B A4B · Google Gemma 4 31B · Google Glimpse · Elorian · unrated GLM 4.5 · Z.ai GLM 4.5 Air · Z.ai GLM 4.5V · Z.ai GLM 4.6 · Z.ai GLM 4.6V · Z.ai GLM 4.7 · Z.ai GLM 4.7 Flash · Z.ai GLM 5 · Z.ai GLM 5 Turbo · Z.ai · unrated GLM 5.1 · Z.ai GLM 5.2 · Z.ai GLM 5.3 · Z.ai GLM 5.3 Flash · Z.ai GLM 5.3 FlashX · Z.ai · unrated GLM 5.3 FlashX Legal · Z.ai · unrated GLM 5.3 Prime · Z.ai · unrated GLM 5V Turbo · Z.ai · unrated GPT Audio · OpenAI · unrated GPT Audio Mini · OpenAI · unrated GPT Chat Latest · OpenAI · unrated GPT-3.5 Turbo (older v0613) · OpenAI · unrated GPT-3.5 Turbo 16k · OpenAI · unrated GPT-4 · OpenAI · unrated GPT-4.1 · OpenAI GPT-4.1 Mini · OpenAI GPT-4.1 Nano · OpenAI GPT-4o · OpenAI · unrated GPT-4o (2024-05-13) · OpenAI GPT-4o (2024-08-06) · OpenAI GPT-4o (2024-11-20) · OpenAI · unrated GPT-4o-mini · OpenAI · unrated GPT-4o-mini (2024-07-18) · OpenAI GPT-5 · OpenAI GPT-5 Image · OpenAI · unrated GPT-5 Image Mini · OpenAI · unrated GPT-5 Mini · OpenAI GPT-5 Nano · OpenAI GPT-5 Pro · OpenAI · unrated GPT-5.1 · OpenAI GPT-5.1-Codex · OpenAI · unrated GPT-5.1-Codex-Max · OpenAI · unrated GPT-5.1-Codex-Mini · OpenAI · unrated GPT-5.2 · OpenAI GPT-5.2 Chat · OpenAI · unrated GPT-5.2 Pro · OpenAI · unrated GPT-5.2-Codex · OpenAI · unrated GPT-5.3-Codex · OpenAI · unrated GPT-5.4 · OpenAI GPT-5.4 Image 2 · OpenAI · unrated GPT-5.4 Mini · OpenAI GPT-5.4 Nano · OpenAI GPT-5.4 Pro · OpenAI · unrated GPT-5.5 · OpenAI GPT-5.5 Pro · OpenAI · unrated GPT-5.6 Luna · OpenAI GPT-5.6 Luna Pro · OpenAI · unrated GPT-5.6 Sol · OpenAI GPT-5.6 Sol Pro · OpenAI · unrated GPT-5.6 Terra · OpenAI GPT-5.6 Terra Pro · OpenAI · unrated GPT-6 Astra · OpenAI GPT-6 Astra Pro · OpenAI · unrated GPT-6 Luna · OpenAI GPT-6 Luna Pro · OpenAI · unrated GPT-6 Sol · OpenAI GPT-6 Sol Pro · OpenAI · unrated GPT-6.1 Sol · OpenAI GPT-6.1 Sol Pro · OpenAI · unrated GPT-6.1 Terra · OpenAI GPT-6.1 Terra Pro · OpenAI · unrated GPT-6.2 Astra · OpenAI GPT-6.2 Astra Pro · OpenAI · unrated GPT-6.2 Sol · OpenAI GPT-6.2 Sol Pro · OpenAI · unrated gpt-oss-120b · OpenAI gpt-oss-20b · OpenAI gpt-oss-safeguard-20b · OpenAI · unrated Granite 4.2 8B · IBM Grok 4.20 · xAI · unrated Grok 4.20 Multi-Agent · xAI · unrated Grok 4.3 · xAI Grok 4.5 · xAI Grok 4.6 · xAI Grok 4.7 · xAI Hermes 4 405B · Nous Research · unrated Hy-MT2-1.8B · Tencent · unrated Hy-MT2-30B-A3B · Tencent · unrated Hy-MT2-7B · Tencent · unrated Hy3 · Tencent Hy4 · Tencent · unrated Hy4 flash · Tencent · unrated Hy4 preview · Tencent · unrated Inkling · Thinking Machines Inkling 2 Mini · Thinking Machines · unrated Inkling 2 Small · Thinking Machines Inkling Small · Thinking Machines Jev Router · Typesafe · unrated Kimi K2 0711 · Moonshot AI · unrated Kimi K2 0905 · Moonshot AI · unrated Kimi K2 Thinking · Moonshot AI · unrated Kimi K2.5 · Moonshot AI Kimi K2.6 · Moonshot AI Kimi K2.7 Code · Moonshot AI · unrated Kimi K3 · Moonshot AI Kimi K3.1 Pro · Moonshot AI LFM2.5-24B-A2B · Liquid AI · unrated LFM3-1.7B · Liquid AI · unrated Ling 3.0 Flash · inclusionAI · unrated Ling 3.0 Flash VL · inclusionAI · unrated Ling 3.0 Tiny · inclusionAI · unrated Ling 3.1 Flash · inclusionAI · unrated Llama 3 8B Lunaris · Sao10k · unrated Llama 3.1 70B Instruct · Meta Llama 3.1 8B Instruct · Meta Llama 3.1 Euryale 70B v2.2 · Sao10k · unrated Llama 3.2 3B Instruct · Meta Llama 3.3 70B Instruct · Meta Llama 4 Maverick · Meta · unrated Llama 4 Scout · Meta · unrated Llama Guard 4 12B · Meta · unrated Lyria 3 Clip Preview · Google · unrated Lyria 3 Pro Preview · Google · unrated Magnum v4 72B · Anthracite Org · unrated Mi:dm K 3.0 Pro · Kt · unrated MiMo-V2.5 · Xiaomi MiMo-V2.5-Pro · Xiaomi MiMo-V2.6-Flash · Xiaomi MiMo-V2.6-Pro · Xiaomi MiMo-V2.6-Pro-UltraSpeed · Xiaomi · unrated MiniMax M2.5 · MiniMax MiniMax M2.7 · MiniMax MiniMax M3 · MiniMax MiniMax M3.1 Flash · MiniMax · unrated Ministral 3 14B 2512 · Mistral · unrated Ministral 3 3B 2512 · Mistral · unrated Ministral 3 8B 2512 · Mistral · unrated Mistral Large · Mistral · unrated Mistral Large 2407 · Mistral Mistral Large 3 2512 · Mistral · unrated Mistral Large 4 · Mistral Mistral Medium 3 · Mistral · unrated Mistral Medium 3.1 · Mistral · unrated Mistral Medium 3.5 · Mistral Mistral Nemo · Mistral · unrated Mistral Small 3 · Mistral Mistral Small 3.1 24B · Mistral · unrated Mistral Small 3.2 24B · Mistral · unrated Mistral Small 4 · Mistral · unrated Mixtral 8x22B Instruct · Mistral · unrated Moondream 3 Preview · Moondream · unrated Moondream 3.1 · Moondream · unrated Morph V3 Fast · Morph · unrated Morph V3 Large · Morph · unrated Motif 3 · Motif Technologies · unrated Muse Ember · Meta · unrated Muse Glimmer 30B · Meta · unrated Muse Spark 1.1 · Meta Muse Spark 1.2 · Meta Muse Spark 1.2 Contributor · Meta · unrated Muse Spark 1.3 · Meta Muse Spark 1.3 Contributor · Meta · unrated Muse Spark Open · Meta · unrated Muse Wonder · Meta MythoMax 13B · Gryphe · unrated Nano Banana (Gemini 2.5 Flash Image) · Google · unrated Nano Banana 2 (Gemini 3.1 Flash Image Preview) · Google · unrated Nano Banana 2 (Gemini 3.1 Flash Image) · Google · unrated Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) · Google · unrated Nano Banana 2.1 · Google · unrated Nano Banana Pro (Gemini 3 Pro Image Preview) · Google · unrated Nano Banana Pro (Gemini 3 Pro Image) · Google · unrated Nemotron 3 Nano 30B A3B · NVIDIA · unrated Nemotron 3 Super · NVIDIA · unrated Nemotron 3 Ultra · NVIDIA · unrated Nemotron 3.5 Content Safety · NVIDIA · unrated Nemotron 3.5 Lightning · NVIDIA · unrated Nemotron 3.5 Super VL · NVIDIA · unrated Nex-N2.5-Mini · Nex Agi · unrated Nex-N2.5-Pro · Nex Agi · unrated Nex-N2.6 · Nex Agi · unrated Nova 2 Lite · Amazon Nova Lite 1.0 · Amazon Nova Micro 1.0 · Amazon Nova Premier 1.0 · Amazon · unrated Nova Pro 1.0 · Amazon o3 · OpenAI o3 Pro · OpenAI · unrated Palmyra X5 · Writer · unrated Pareto 26.10 · Unbiased · unrated Pareto 26.10 Preview · Unbiased · unrated Pareto 26.9 · Unbiased · unrated Pareto Code Router · OpenRouter · unrated Particle-1 · Particle Ai · unrated Perceptron Mk1 · Perceptron · unrated Perceptron Mk1.5 · Perceptron · unrated Phi 4 · Microsoft Pixtral Large 2502 · Mistral · unrated Qwen-Plus · Qwen · unrated Qwen2.5 72B Instruct · Qwen Qwen2.5 Coder 32B Instruct · Qwen Qwen2.5 VL 72B Instruct · Qwen · unrated Qwen3 14B · Qwen · unrated Qwen3 235B A22B Instruct 2507 · Qwen Qwen3 235B A22B Thinking 2507 · Qwen Qwen3 30B A3B · Qwen Qwen3 30B A3B Instruct 2507 · Qwen Qwen3 32B · Qwen Qwen3 Coder 30B A3B Instruct · Qwen · unrated Qwen3 Coder 480B A35B · Qwen · unrated Qwen3 Coder Flash · Qwen · unrated Qwen3 Coder Next · Qwen · unrated Qwen3 Next 80B A3B Instruct · Qwen Qwen3 VL 235B A22B Instruct · Qwen Qwen3 VL 30B A3B Instruct · Qwen · unrated Qwen3 VL 8B Instruct · Qwen · unrated Qwen3.5 397B A17B · Qwen Qwen3.5 Plus 2026-02-15 · Qwen · unrated Qwen3.5 Plus 2026-04-20 · Qwen · unrated Qwen3.5-122B-A10B · Qwen Qwen3.5-27B · Qwen Qwen3.5-35B-A3B · Qwen Qwen3.5-9B · Qwen · unrated Qwen3.5-Flash · Qwen Qwen3.6 27B · Qwen · unrated Qwen3.6 35B A3B · Qwen · unrated Qwen3.6 Flash · Qwen · unrated Qwen3.6 Plus · Qwen Qwen3.7 Flash · Qwen · unrated Qwen3.7 Max · Qwen · unrated Qwen3.7 Plus · Qwen Qwen3.8 2.4T A95B · Qwen · unrated Qwen3.8 27B · Qwen Qwen3.8 Flash · Qwen · unrated Qwen3.8 Max (0902) · Qwen · unrated Qwen3.8 Max Prime · Qwen · unrated Qwen3.8 Omni Flash · Qwen · unrated Qwen4 Max · Qwen · unrated R1 0528 · DeepSeek Reka Edge · Reka · unrated Reka Flash 3 · Reka · unrated Relace Apply 3 · Relace · unrated Relace Search · Relace · unrated ReMM SLERP 13B · Undi95 · unrated Ripple 65B Preview · Ricursiveai · unrated Saba · Mistral · unrated Sakana Namazu · Sakana AI · unrated Schematron V2 Small · Inference Net · unrated Schematron V2 Turbo · Inference Net · unrated Seed 2.1 Turbo · ByteDance · unrated Seed-2.0-Lite · ByteDance · unrated Seed-2.0-Mini · ByteDance · unrated Skyfall 36B V2 · Thedrummer · unrated Solar Mini 4 · Upstage · unrated Solar Pro 4 · Upstage Sonar · Perplexity · unrated Sonar Deep Research · Perplexity · unrated Sonar Pro · Perplexity · unrated Sonar Pro Search · Perplexity · unrated Sonar Reasoning Pro · Perplexity · unrated Step 3.7 Flash · StepFun · unrated Step 5 Preview · StepFun Summarize · Scaledown · unrated Switchyard · NVIDIA · unrated Ternary Bonsai 2 27B · Prism Ml · unrated Ternary Bonsai 2 9B · Prism Ml · unrated UI-TARS 7B · ByteDance · unrated Uncensored · Cognitivecomputations · unrated UnslopNemo 12B · Thedrummer · unrated Voxtral Small 24B 2507 · Mistral · unrated Weaver (alpha) · Mancer · unrated B · Comparison model Choose a model Aion 3.5 · Aion Labs · unrated Aion 3.5 Mini · Aion Labs · unrated Aion-2.0 · Aion Labs · unrated Aion-3.0 · Aion Labs · unrated Aion-3.0-Mini · Aion Labs · unrated Aion-RP 1.0 (8B) · Aion Labs · unrated Auto Router · OpenRouter · unrated Auto Router (Beta) · OpenRouter · unrated Beam 1.0 501B A23B · Reflection Body Builder (beta) · OpenRouter · unrated Claude Fable 5 · Anthropic Claude Fable 5.1 · Anthropic Claude Fable 5.2 · Anthropic Claude Haiku 4.5 · Anthropic Claude Haiku 5.5 · Anthropic Claude Opus 4.1 · Anthropic Claude Opus 4.5 · Anthropic Claude Opus 4.6 · Anthropic Claude Opus 4.7 · Anthropic Claude Opus 4.8 · Anthropic Claude Opus 5 · Anthropic Claude Opus 5.5 · Anthropic Claude Sonnet 4.5 · Anthropic Claude Sonnet 4.6 · Anthropic Claude Sonnet 5 · Anthropic Claude Sonnet 5.5 · Anthropic Codestral 2508 · Mistral · unrated Command A · Cohere · unrated Command A+ · Cohere · unrated Command R (08-2024) · Cohere Command R+ (08-2024) · Cohere Command R7B (12-2024) · Cohere · unrated Cydonia 24B V4.1 · Thedrummer · unrated DaisyRose 27B · Radixark · unrated DeepSeek V3 · DeepSeek DeepSeek V3 0324 · DeepSeek DeepSeek V3.1 · DeepSeek DeepSeek V3.1 Terminus · DeepSeek DeepSeek V3.2 · DeepSeek DeepSeek V3.2 Exp · DeepSeek DeepSeek V4 Flash 0423 · DeepSeek DeepSeek V4 Flash 0731 · DeepSeek · unrated DeepSeek V4 Flash Vision Exp · DeepSeek · unrated DeepSeek V4 Pro 0423 · DeepSeek DeepSeek V4 Pro 0813 · DeepSeek · unrated DeepSeek V4.1 Flash · DeepSeek DeepSeek V4.1 Flash 1017 · DeepSeek · unrated Ember-1 · Fireworks · unrated ERNIE-Light-DT-1.0 · Baidu · unrated Extract · Scaledown · unrated Free Models Router · OpenRouter · unrated Fugu Max · Sakana AI · unrated Fugu Ultra · Sakana AI · unrated Fugu Ultra v2 · Sakana AI · unrated Fusion · OpenRouter · unrated Gemini 2.5 Flash · Google Gemini 2.5 Flash Lite · Google · unrated Gemini 2.5 Pro · Google Gemini 2.5 Pro Preview 06-05 · Google · unrated Gemini 3 Flash Preview · Google · unrated Gemini 3.1 Flash Lite · Google · unrated Gemini 3.1 Flash Lite Preview · Google Gemini 3.1 Pro Preview · Google Gemini 3.1 Pro Preview Custom Tools · Google · unrated Gemini 3.5 Flash · Google Gemini 3.5 Flash Lite · Google Gemini 3.6 Flash · Google Gemini 3.7 Flash · Google Gemini 3.8 Flash · Google Gemini 4 Argon · Google Gemini 4 Carbon · Google Gemini 4 Hydrogen · Google Gemini 4 Neon · Google Gemini Omni 1.1 Flash · Google · unrated Gemini Omni 1.2 Flash · Google · unrated Gemma 2 27B · Google Gemma 3 12B · Google Gemma 3 27B · Google Gemma 3 4B · Google Gemma 4 26B A4B · Google Gemma 4 31B · Google Glimpse · Elorian · unrated GLM 4.5 · Z.ai GLM 4.5 Air · Z.ai GLM 4.5V · Z.ai GLM 4.6 · Z.ai GLM 4.6V · Z.ai GLM 4.7 · Z.ai GLM 4.7 Flash · Z.ai GLM 5 · Z.ai GLM 5 Turbo · Z.ai · unrated GLM 5.1 · Z.ai GLM 5.2 · Z.ai GLM 5.3 · Z.ai GLM 5.3 Flash · Z.ai GLM 5.3 FlashX · Z.ai · unrated GLM 5.3 FlashX Legal · Z.ai · unrated GLM 5.3 Prime · Z.ai · unrated GLM 5V Turbo · Z.ai · unrated GPT Audio · OpenAI · unrated GPT Audio Mini · OpenAI · unrated GPT Chat Latest · OpenAI · unrated GPT-3.5 Turbo (older v0613) · OpenAI · unrated GPT-3.5 Turbo 16k · OpenAI · unrated GPT-4 · OpenAI · unrated GPT-4.1 · OpenAI GPT-4.1 Mini · OpenAI GPT-4.1 Nano · OpenAI GPT-4o · OpenAI · unrated GPT-4o (2024-05-13) · OpenAI GPT-4o (2024-08-06) · OpenAI GPT-4o (2024-11-20) · OpenAI · unrated GPT-4o-mini · OpenAI · unrated GPT-4o-mini (2024-07-18) · OpenAI GPT-5 · OpenAI GPT-5 Image · OpenAI · unrated GPT-5 Image Mini · OpenAI · unrated GPT-5 Mini · OpenAI GPT-5 Nano · OpenAI GPT-5 Pro · OpenAI · unrated GPT-5.1 · OpenAI GPT-5.1-Codex · OpenAI · unrated GPT-5.1-Codex-Max · OpenAI · unrated GPT-5.1-Codex-Mini · OpenAI · unrated GPT-5.2 · OpenAI GPT-5.2 Chat · OpenAI · unrated GPT-5.2 Pro · OpenAI · unrated GPT-5.2-Codex · OpenAI · unrated GPT-5.3-Codex · OpenAI · unrated GPT-5.4 · OpenAI GPT-5.4 Image 2 · OpenAI · unrated GPT-5.4 Mini · OpenAI GPT-5.4 Nano · OpenAI GPT-5.4 Pro · OpenAI · unrated GPT-5.5 · OpenAI GPT-5.5 Pro · OpenAI · unrated GPT-5.6 Luna · OpenAI GPT-5.6 Luna Pro · OpenAI · unrated GPT-5.6 Sol · OpenAI GPT-5.6 Sol Pro · OpenAI · unrated GPT-5.6 Terra · OpenAI GPT-5.6 Terra Pro · OpenAI · unrated GPT-6 Astra · OpenAI GPT-6 Astra Pro · OpenAI · unrated GPT-6 Luna · OpenAI GPT-6 Luna Pro · OpenAI · unrated GPT-6 Sol · OpenAI GPT-6 Sol Pro · OpenAI · unrated GPT-6.1 Sol · OpenAI GPT-6.1 Sol Pro · OpenAI · unrated GPT-6.1 Terra · OpenAI GPT-6.1 Terra Pro · OpenAI · unrated GPT-6.2 Astra · OpenAI GPT-6.2 Astra Pro · OpenAI · unrated GPT-6.2 Sol · OpenAI GPT-6.2 Sol Pro · OpenAI · unrated gpt-oss-120b · OpenAI gpt-oss-20b · OpenAI gpt-oss-safeguard-20b · OpenAI · unrated Granite 4.2 8B · IBM Grok 4.20 · xAI · unrated Grok 4.20 Multi-Agent · xAI · unrated Grok 4.3 · xAI Grok 4.5 · xAI Grok 4.6 · xAI Grok 4.7 · xAI Hermes 4 405B · Nous Research · unrated Hy-MT2-1.8B · Tencent · unrated Hy-MT2-30B-A3B · Tencent · unrated Hy-MT2-7B · Tencent · unrated Hy3 · Tencent Hy4 · Tencent · unrated Hy4 flash · Tencent · unrated Hy4 preview · Tencent · unrated Inkling · Thinking Machines Inkling 2 Mini · Thinking Machines · unrated Inkling 2 Small · Thinking Machines Inkling Small · Thinking Machines Jev Router · Typesafe · unrated Kimi K2 0711 · Moonshot AI · unrated Kimi K2 0905 · Moonshot AI · unrated Kimi K2 Thinking · Moonshot AI · unrated Kimi K2.5 · Moonshot AI Kimi K2.6 · Moonshot AI Kimi K2.7 Code · Moonshot AI · unrated Kimi K3 · Moonshot AI Kimi K3.1 Pro · Moonshot AI LFM2.5-24B-A2B · Liquid AI · unrated LFM3-1.7B · Liquid AI · unrated Ling 3.0 Flash · inclusionAI · unrated Ling 3.0 Flash VL · inclusionAI · unrated Ling 3.0 Tiny · inclusionAI · unrated Ling 3.1 Flash · inclusionAI · unrated Llama 3 8B Lunaris · Sao10k · unrated Llama 3.1 70B Instruct · Meta Llama 3.1 8B Instruct · Meta Llama 3.1 Euryale 70B v2.2 · Sao10k · unrated Llama 3.2 3B Instruct · Meta Llama 3.3 70B Instruct · Meta Llama 4 Maverick · Meta · unrated Llama 4 Scout · Meta · unrated Llama Guard 4 12B · Meta · unrated Lyria 3 Clip Preview · Google · unrated Lyria 3 Pro Preview · Google · unrated Magnum v4 72B · Anthracite Org · unrated Mi:dm K 3.0 Pro · Kt · unrated MiMo-V2.5 · Xiaomi MiMo-V2.5-Pro · Xiaomi MiMo-V2.6-Flash · Xiaomi MiMo-V2.6-Pro · Xiaomi MiMo-V2.6-Pro-UltraSpeed · Xiaomi · unrated MiniMax M2.5 · MiniMax MiniMax M2.7 · MiniMax MiniMax M3 · MiniMax MiniMax M3.1 Flash · MiniMax · unrated Ministral 3 14B 2512 · Mistral · unrated Ministral 3 3B 2512 · Mistral · unrated Ministral 3 8B 2512 · Mistral · unrated Mistral Large · Mistral · unrated Mistral Large 2407 · Mistral Mistral Large 3 2512 · Mistral · unrated Mistral Large 4 · Mistral Mistral Medium 3 · Mistral · unrated Mistral Medium 3.1 · Mistral · unrated Mistral Medium 3.5 · Mistral Mistral Nemo · Mistral · unrated Mistral Small 3 · Mistral Mistral Small 3.1 24B · Mistral · unrated Mistral Small 3.2 24B · Mistral · unrated Mistral Small 4 · Mistral · unrated Mixtral 8x22B Instruct · Mistral · unrated Moondream 3 Preview · Moondream · unrated Moondream 3.1 · Moondream · unrated Morph V3 Fast · Morph · unrated Morph V3 Large · Morph · unrated Motif 3 · Motif Technologies · unrated Muse Ember · Meta · unrated Muse Glimmer 30B · Meta · unrated Muse Spark 1.1 · Meta Muse Spark 1.2 · Meta Muse Spark 1.2 Contributor · Meta · unrated Muse Spark 1.3 · Meta Muse Spark 1.3 Contributor · Meta · unrated Muse Spark Open · Meta · unrated Muse Wonder · Meta MythoMax 13B · Gryphe · unrated Nano Banana (Gemini 2.5 Flash Image) · Google · unrated Nano Banana 2 (Gemini 3.1 Flash Image Preview) · Google · unrated Nano Banana 2 (Gemini 3.1 Flash Image) · Google · unrated Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) · Google · unrated Nano Banana 2.1 · Google · unrated Nano Banana Pro (Gemini 3 Pro Image Preview) · Google · unrated Nano Banana Pro (Gemini 3 Pro Image) · Google · unrated Nemotron 3 Nano 30B A3B · NVIDIA · unrated Nemotron 3 Super · NVIDIA · unrated Nemotron 3 Ultra · NVIDIA · unrated Nemotron 3.5 Content Safety · NVIDIA · unrated Nemotron 3.5 Lightning · NVIDIA · unrated Nemotron 3.5 Super VL · NVIDIA · unrated Nex-N2.5-Mini · Nex Agi · unrated Nex-N2.5-Pro · Nex Agi · unrated Nex-N2.6 · Nex Agi · unrated Nova 2 Lite · Amazon Nova Lite 1.0 · Amazon Nova Micro 1.0 · Amazon Nova Premier 1.0 · Amazon · unrated Nova Pro 1.0 · Amazon o3 · OpenAI o3 Pro · OpenAI · unrated Palmyra X5 · Writer · unrated Pareto 26.10 · Unbiased · unrated Pareto 26.10 Preview · Unbiased · unrated Pareto 26.9 · Unbiased · unrated Pareto Code Router · OpenRouter · unrated Particle-1 · Particle Ai · unrated Perceptron Mk1 · Perceptron · unrated Perceptron Mk1.5 · Perceptron · unrated Phi 4 · Microsoft Pixtral Large 2502 · Mistral · unrated Qwen-Plus · Qwen · unrated Qwen2.5 72B Instruct · Qwen Qwen2.5 Coder 32B Instruct · Qwen Qwen2.5 VL 72B Instruct · Qwen · unrated Qwen3 14B · Qwen · unrated Qwen3 235B A22B Instruct 2507 · Qwen Qwen3 235B A22B Thinking 2507 · Qwen Qwen3 30B A3B · Qwen Qwen3 30B A3B Instruct 2507 · Qwen Qwen3 32B · Qwen Qwen3 Coder 30B A3B Instruct · Qwen · unrated Qwen3 Coder 480B A35B · Qwen · unrated Qwen3 Coder Flash · Qwen · unrated Qwen3 Coder Next · Qwen · unrated Qwen3 Next 80B A3B Instruct · Qwen Qwen3 VL 235B A22B Instruct · Qwen Qwen3 VL 30B A3B Instruct · Qwen · unrated Qwen3 VL 8B Instruct · Qwen · unrated Qwen3.5 397B A17B · Qwen Qwen3.5 Plus 2026-02-15 · Qwen · unrated Qwen3.5 Plus 2026-04-20 · Qwen · unrated Qwen3.5-122B-A10B · Qwen Qwen3.5-27B · Qwen Qwen3.5-35B-A3B · Qwen Qwen3.5-9B · Qwen · unrated Qwen3.5-Flash · Qwen Qwen3.6 27B · Qwen · unrated Qwen3.6 35B A3B · Qwen · unrated Qwen3.6 Flash · Qwen · unrated Qwen3.6 Plus · Qwen Qwen3.7 Flash · Qwen · unrated Qwen3.7 Max · Qwen · unrated Qwen3.7 Plus · Qwen Qwen3.8 2.4T A95B · Qwen · unrated Qwen3.8 27B · Qwen Qwen3.8 Flash · Qwen · unrated Qwen3.8 Max (0902) · Qwen · unrated Qwen3.8 Max Prime · Qwen · unrated Qwen3.8 Omni Flash · Qwen · unrated Qwen4 Max · Qwen · unrated R1 0528 · DeepSeek Reka Edge · Reka · unrated Reka Flash 3 · Reka · unrated Relace Apply 3 · Relace · unrated Relace Search · Relace · unrated ReMM SLERP 13B · Undi95 · unrated Ripple 65B Preview · Ricursiveai · unrated Saba · Mistral · unrated Sakana Namazu · Sakana AI · unrated Schematron V2 Small · Inference Net · unrated Schematron V2 Turbo · Inference Net · unrated Seed 2.1 Turbo · ByteDance · unrated Seed-2.0-Lite · ByteDance · unrated Seed-2.0-Mini · ByteDance · unrated Skyfall 36B V2 · Thedrummer · unrated Solar Mini 4 · Upstage · unrated Solar Pro 4 · Upstage Sonar · Perplexity · unrated Sonar Deep Research · Perplexity · unrated Sonar Pro · Perplexity · unrated Sonar Pro Search · Perplexity · unrated Sonar Reasoning Pro · Perplexity · unrated Step 3.7 Flash · StepFun · unrated Step 5 Preview · StepFun Summarize · Scaledown · unrated Switchyard · NVIDIA · unrated Ternary Bonsai 2 27B · Prism Ml · unrated Ternary Bonsai 2 9B · Prism Ml · unrated UI-TARS 7B · ByteDance · unrated Uncensored · Cognitivecomputations · unrated UnslopNemo 12B · Thedrummer · unrated Voxtral Small 24B 2507 · Mistral · unrated Weaver (alpha) · Mancer · unrated C · Optional third model No third model Aion 3.5 · Aion Labs · unrated Aion 3.5 Mini · Aion Labs · unrated Aion-2.0 · Aion Labs · unrated Aion-3.0 · Aion Labs · unrated Aion-3.0-Mini · Aion Labs · unrated Aion-RP 1.0 (8B) · Aion Labs · unrated Auto Router · OpenRouter · unrated Auto Router (Beta) · OpenRouter · unrated Beam 1.0 501B A23B · Reflection Body Builder (beta) · OpenRouter · unrated Claude Fable 5 · Anthropic Claude Fable 5.1 · Anthropic Claude Fable 5.2 · Anthropic Claude Haiku 4.5 · Anthropic Claude Haiku 5.5 · Anthropic Claude Opus 4.1 · Anthropic Claude Opus 4.5 · Anthropic Claude Opus 4.6 · Anthropic Claude Opus 4.7 · Anthropic Claude Opus 4.8 · Anthropic Claude Opus 5 · Anthropic Claude Opus 5.5 · Anthropic Claude Sonnet 4.5 · Anthropic Claude Sonnet 4.6 · Anthropic Claude Sonnet 5 · Anthropic Claude Sonnet 5.5 · Anthropic Codestral 2508 · Mistral · unrated Command A · Cohere · unrated Command A+ · Cohere · unrated Command R (08-2024) · Cohere Command R+ (08-2024) · Cohere Command R7B (12-2024) · Cohere · unrated Cydonia 24B V4.1 · Thedrummer · unrated DaisyRose 27B · Radixark · unrated DeepSeek V3 · DeepSeek DeepSeek V3 0324 · DeepSeek DeepSeek V3.1 · DeepSeek DeepSeek V3.1 Terminus · DeepSeek DeepSeek V3.2 · DeepSeek DeepSeek V3.2 Exp · DeepSeek DeepSeek V4 Flash 0423 · DeepSeek DeepSeek V4 Flash 0731 · DeepSeek · unrated DeepSeek V4 Flash Vision Exp · DeepSeek · unrated DeepSeek V4 Pro 0423 · DeepSeek DeepSeek V4 Pro 0813 · DeepSeek · unrated DeepSeek V4.1 Flash · DeepSeek DeepSeek V4.1 Flash 1017 · DeepSeek · unrated Ember-1 · Fireworks · unrated ERNIE-Light-DT-1.0 · Baidu · unrated Extract · Scaledown · unrated Free Models Router · OpenRouter · unrated Fugu Max · Sakana AI · unrated Fugu Ultra · Sakana AI · unrated Fugu Ultra v2 · Sakana AI · unrated Fusion · OpenRouter · unrated Gemini 2.5 Flash · Google Gemini 2.5 Flash Lite · Google · unrated Gemini 2.5 Pro · Google Gemini 2.5 Pro Preview 06-05 · Google · unrated Gemini 3 Flash Preview · Google · unrated Gemini 3.1 Flash Lite · Google · unrated Gemini 3.1 Flash Lite Preview · Google Gemini 3.1 Pro Preview · Google Gemini 3.1 Pro Preview Custom Tools · Google · unrated Gemini 3.5 Flash · Google Gemini 3.5 Flash Lite · Google Gemini 3.6 Flash · Google Gemini 3.7 Flash · Google Gemini 3.8 Flash · Google Gemini 4 Argon · Google Gemini 4 Carbon · Google Gemini 4 Hydrogen · Google Gemini 4 Neon · Google Gemini Omni 1.1 Flash · Google · unrated Gemini Omni 1.2 Flash · Google · unrated Gemma 2 27B · Google Gemma 3 12B · Google Gemma 3 27B · Google Gemma 3 4B · Google Gemma 4 26B A4B · Google Gemma 4 31B · Google Glimpse · Elorian · unrated GLM 4.5 · Z.ai GLM 4.5 Air · Z.ai GLM 4.5V · Z.ai GLM 4.6 · Z.ai GLM 4.6V · Z.ai GLM 4.7 · Z.ai GLM 4.7 Flash · Z.ai GLM 5 · Z.ai GLM 5 Turbo · Z.ai · unrated GLM 5.1 · Z.ai GLM 5.2 · Z.ai GLM 5.3 · Z.ai GLM 5.3 Flash · Z.ai GLM 5.3 FlashX · Z.ai · unrated GLM 5.3 FlashX Legal · Z.ai · unrated GLM 5.3 Prime · Z.ai · unrated GLM 5V Turbo · Z.ai · unrated GPT Audio · OpenAI · unrated GPT Audio Mini · OpenAI · unrated GPT Chat Latest · OpenAI · unrated GPT-3.5 Turbo (older v0613) · OpenAI · unrated GPT-3.5 Turbo 16k · OpenAI · unrated GPT-4 · OpenAI · unrated GPT-4.1 · OpenAI GPT-4.1 Mini · OpenAI GPT-4.1 Nano · OpenAI GPT-4o · OpenAI · unrated GPT-4o (2024-05-13) · OpenAI GPT-4o (2024-08-06) · OpenAI GPT-4o (2024-11-20) · OpenAI · unrated GPT-4o-mini · OpenAI · unrated GPT-4o-mini (2024-07-18) · OpenAI GPT-5 · OpenAI GPT-5 Image · OpenAI · unrated GPT-5 Image Mini · OpenAI · unrated GPT-5 Mini · OpenAI GPT-5 Nano · OpenAI GPT-5 Pro · OpenAI · unrated GPT-5.1 · OpenAI GPT-5.1-Codex · OpenAI · unrated GPT-5.1-Codex-Max · OpenAI · unrated GPT-5.1-Codex-Mini · OpenAI · unrated GPT-5.2 · OpenAI GPT-5.2 Chat · OpenAI · unrated GPT-5.2 Pro · OpenAI · unrated GPT-5.2-Codex · OpenAI · unrated GPT-5.3-Codex · OpenAI · unrated GPT-5.4 · OpenAI GPT-5.4 Image 2 · OpenAI · unrated GPT-5.4 Mini · OpenAI GPT-5.4 Nano · OpenAI GPT-5.4 Pro · OpenAI · unrated GPT-5.5 · OpenAI GPT-5.5 Pro · OpenAI · unrated GPT-5.6 Luna · OpenAI GPT-5.6 Luna Pro · OpenAI · unrated GPT-5.6 Sol · OpenAI GPT-5.6 Sol Pro · OpenAI · unrated GPT-5.6 Terra · OpenAI GPT-5.6 Terra Pro · OpenAI · unrated GPT-6 Astra · OpenAI GPT-6 Astra Pro · OpenAI · unrated GPT-6 Luna · OpenAI GPT-6 Luna Pro · OpenAI · unrated GPT-6 Sol · OpenAI GPT-6 Sol Pro · OpenAI · unrated GPT-6.1 Sol · OpenAI GPT-6.1 Sol Pro · OpenAI · unrated GPT-6.1 Terra · OpenAI GPT-6.1 Terra Pro · OpenAI · unrated GPT-6.2 Astra · OpenAI GPT-6.2 Astra Pro · OpenAI · unrated GPT-6.2 Sol · OpenAI GPT-6.2 Sol Pro · OpenAI · unrated gpt-oss-120b · OpenAI gpt-oss-20b · OpenAI gpt-oss-safeguard-20b · OpenAI · unrated Granite 4.2 8B · IBM Grok 4.20 · xAI · unrated Grok 4.20 Multi-Agent · xAI · unrated Grok 4.3 · xAI Grok 4.5 · xAI Grok 4.6 · xAI Grok 4.7 · xAI Hermes 4 405B · Nous Research · unrated Hy-MT2-1.8B · Tencent · unrated Hy-MT2-30B-A3B · Tencent · unrated Hy-MT2-7B · Tencent · unrated Hy3 · Tencent Hy4 · Tencent · unrated Hy4 flash · Tencent · unrated Hy4 preview · Tencent · unrated Inkling · Thinking Machines Inkling 2 Mini · Thinking Machines · unrated Inkling 2 Small · Thinking Machines Inkling Small · Thinking Machines Jev Router · Typesafe · unrated Kimi K2 0711 · Moonshot AI · unrated Kimi K2 0905 · Moonshot AI · unrated Kimi K2 Thinking · Moonshot AI · unrated Kimi K2.5 · Moonshot AI Kimi K2.6 · Moonshot AI Kimi K2.7 Code · Moonshot AI · unrated Kimi K3 · Moonshot AI Kimi K3.1 Pro · Moonshot AI LFM2.5-24B-A2B · Liquid AI · unrated LFM3-1.7B · Liquid AI · unrated Ling 3.0 Flash · inclusionAI · unrated Ling 3.0 Flash VL · inclusionAI · unrated Ling 3.0 Tiny · inclusionAI · unrated Ling 3.1 Flash · inclusionAI · unrated Llama 3 8B Lunaris · Sao10k · unrated Llama 3.1 70B Instruct · Meta Llama 3.1 8B Instruct · Meta Llama 3.1 Euryale 70B v2.2 · Sao10k · unrated Llama 3.2 3B Instruct · Meta Llama 3.3 70B Instruct · Meta Llama 4 Maverick · Meta · unrated Llama 4 Scout · Meta · unrated Llama Guard 4 12B · Meta · unrated Lyria 3 Clip Preview · Google · unrated Lyria 3 Pro Preview · Google · unrated Magnum v4 72B · Anthracite Org · unrated Mi:dm K 3.0 Pro · Kt · unrated MiMo-V2.5 · Xiaomi MiMo-V2.5-Pro · Xiaomi MiMo-V2.6-Flash · Xiaomi MiMo-V2.6-Pro · Xiaomi MiMo-V2.6-Pro-UltraSpeed · Xiaomi · unrated MiniMax M2.5 · MiniMax MiniMax M2.7 · MiniMax MiniMax M3 · MiniMax MiniMax M3.1 Flash · MiniMax · unrated Ministral 3 14B 2512 · Mistral · unrated Ministral 3 3B 2512 · Mistral · unrated Ministral 3 8B 2512 · Mistral · unrated Mistral Large · Mistral · unrated Mistral Large 2407 · Mistral Mistral Large 3 2512 · Mistral · unrated Mistral Large 4 · Mistral Mistral Medium 3 · Mistral · unrated Mistral Medium 3.1 · Mistral · unrated Mistral Medium 3.5 · Mistral Mistral Nemo · Mistral · unrated Mistral Small 3 · Mistral Mistral Small 3.1 24B · Mistral · unrated Mistral Small 3.2 24B · Mistral · unrated Mistral Small 4 · Mistral · unrated Mixtral 8x22B Instruct · Mistral · unrated Moondream 3 Preview · Moondream · unrated Moondream 3.1 · Moondream · unrated Morph V3 Fast · Morph · unrated Morph V3 Large · Morph · unrated Motif 3 · Motif Technologies · unrated Muse Ember · Meta · unrated Muse Glimmer 30B · Meta · unrated Muse Spark 1.1 · Meta Muse Spark 1.2 · Meta Muse Spark 1.2 Contributor · Meta · unrated Muse Spark 1.3 · Meta Muse Spark 1.3 Contributor · Meta · unrated Muse Spark Open · Meta · unrated Muse Wonder · Meta MythoMax 13B · Gryphe · unrated Nano Banana (Gemini 2.5 Flash Image) · Google · unrated Nano Banana 2 (Gemini 3.1 Flash Image Preview) · Google · unrated Nano Banana 2 (Gemini 3.1 Flash Image) · Google · unrated Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) · Google · unrated Nano Banana 2.1 · Google · unrated Nano Banana Pro (Gemini 3 Pro Image Preview) · Google · unrated Nano Banana Pro (Gemini 3 Pro Image) · Google · unrated Nemotron 3 Nano 30B A3B · NVIDIA · unrated Nemotron 3 Super · NVIDIA · unrated Nemotron 3 Ultra · NVIDIA · unrated Nemotron 3.5 Content Safety · NVIDIA · unrated Nemotron 3.5 Lightning · NVIDIA · unrated Nemotron 3.5 Super VL · NVIDIA · unrated Nex-N2.5-Mini · Nex Agi · unrated Nex-N2.5-Pro · Nex Agi · unrated Nex-N2.6 · Nex Agi · unrated Nova 2 Lite · Amazon Nova Lite 1.0 · Amazon Nova Micro 1.0 · Amazon Nova Premier 1.0 · Amazon · unrated Nova Pro 1.0 · Amazon o3 · OpenAI o3 Pro · OpenAI · unrated Palmyra X5 · Writer · unrated Pareto 26.10 · Unbiased · unrated Pareto 26.10 Preview · Unbiased · unrated Pareto 26.9 · Unbiased · unrated Pareto Code Router · OpenRouter · unrated Particle-1 · Particle Ai · unrated Perceptron Mk1 · Perceptron · unrated Perceptron Mk1.5 · Perceptron · unrated Phi 4 · Microsoft Pixtral Large 2502 · Mistral · unrated Qwen-Plus · Qwen · unrated Qwen2.5 72B Instruct · Qwen Qwen2.5 Coder 32B Instruct · Qwen Qwen2.5 VL 72B Instruct · Qwen · unrated Qwen3 14B · Qwen · unrated Qwen3 235B A22B Instruct 2507 · Qwen Qwen3 235B A22B Thinking 2507 · Qwen Qwen3 30B A3B · Qwen Qwen3 30B A3B Instruct 2507 · Qwen Qwen3 32B · Qwen Qwen3 Coder 30B A3B Instruct · Qwen · unrated Qwen3 Coder 480B A35B · Qwen · unrated Qwen3 Coder Flash · Qwen · unrated Qwen3 Coder Next · Qwen · unrated Qwen3 Next 80B A3B Instruct · Qwen Qwen3 VL 235B A22B Instruct · Qwen Qwen3 VL 30B A3B Instruct · Qwen · unrated Qwen3 VL 8B Instruct · Qwen · unrated Qwen3.5 397B A17B · Qwen Qwen3.5 Plus 2026-02-15 · Qwen · unrated Qwen3.5 Plus 2026-04-20 · Qwen · unrated Qwen3.5-122B-A10B · Qwen Qwen3.5-27B · Qwen Qwen3.5-35B-A3B · Qwen Qwen3.5-9B · Qwen · unrated Qwen3.5-Flash · Qwen Qwen3.6 27B · Qwen · unrated Qwen3.6 35B A3B · Qwen · unrated Qwen3.6 Flash · Qwen · unrated Qwen3.6 Plus · Qwen Qwen3.7 Flash · Qwen · unrated Qwen3.7 Max · Qwen · unrated Qwen3.7 Plus · Qwen Qwen3.8 2.4T A95B · Qwen · unrated Qwen3.8 27B · Qwen Qwen3.8 Flash · Qwen · unrated Qwen3.8 Max (0902) · Qwen · unrated Qwen3.8 Max Prime · Qwen · unrated Qwen3.8 Omni Flash · Qwen · unrated Qwen4 Max · Qwen · unrated R1 0528 · DeepSeek Reka Edge · Reka · unrated Reka Flash 3 · Reka · unrated Relace Apply 3 · Relace · unrated Relace Search · Relace · unrated ReMM SLERP 13B · Undi95 · unrated Ripple 65B Preview · Ricursiveai · unrated Saba · Mistral · unrated Sakana Namazu · Sakana AI · unrated Schematron V2 Small · Inference Net · unrated Schematron V2 Turbo · Inference Net · unrated Seed 2.1 Turbo · ByteDance · unrated Seed-2.0-Lite · ByteDance · unrated Seed-2.0-Mini · ByteDance · unrated Skyfall 36B V2 · Thedrummer · unrated Solar Mini 4 · Upstage · unrated Solar Pro 4 · Upstage Sonar · Perplexity · unrated Sonar Deep Research · Perplexity · unrated Sonar Pro · Perplexity · unrated Sonar Pro Search · Perplexity · unrated Sonar Reasoning Pro · Perplexity · unrated Step 3.7 Flash · StepFun · unrated Step 5 Preview · StepFun Summarize · Scaledown · unrated Switchyard · NVIDIA · unrated Ternary Bonsai 2 27B · Prism Ml · unrated Ternary Bonsai 2 9B · Prism Ml · unrated UI-TARS 7B · ByteDance · unrated Uncensored · Cognitivecomputations · unrated UnslopNemo 12B · Thedrummer · unrated Voxtral Small 24B 2507 · Mistral · unrated Weaver (alpha) · Mancer · unrated
 2 / 3 selected · 0 requirements Copy public link [Open public comparison link](https://undominated.ai/compare/?models=mistralai%2Fmistral-medium-3-5%2Cmistralai%2Fmistral-small-24b-instruct-2501) Clear shortlist

 Public workload and requirements

These settings are included in the share link. The fixed-request scenario and private evaluation data below are excluded.

 Workload Balanced · 3 tokens in per 1 out Summarise · Huge input, tiny output Chat · Long cached system prompt Code gen · Output dominates Agentic · Context replayed each turn Public prompt length (tokens) Required context (tokens) Required output limit (tokens) Required input modality No requirement text image audio video file
 Tool use Reasoning Open weights
 **A ↔ B**

Neither model has both an equal-or-higher measured score and an equal-or-lower estimated price in this pair. Retaining your current model is a valid outcome.

Estimated blend: 75% input, 25% output; 0% cached input. Base context tier. Prompt length selects the billing tier. An unlisted cache-read rate uses that tier’s full input rate in this blend; missing required input or output rates prevent an estimate. The fixed-request estimate below validates actual context and output limits and requires a published cache-read rate when cache hits are assumed.

### What changes between these models

Quality first, then estimated price. LMArena scores are human-preference measurements, not a benchmark of your application. A missing score is unrated.

 - **Mistral Medium 3.5** · Meets the stated model requirements
- **Mistral Small 3** · Meets the stated model requirements

Material differences and unknown evidence. Deltas compare each model with model A. Unknown facts remain visible.

| Measured fact | A [Mistral Medium 3.5](https://undominated.ai/models/mistralai__mistral-medium-3-5/?models=mistralai%2Fmistral-medium-3-5%2Cmistralai%2Fmistral-small-24b-instruct-2501) | B [Mistral Small 3](https://undominated.ai/models/mistralai__mistral-small-24b-instruct-2501/?models=mistralai%2Fmistral-medium-3-5%2Cmistralai%2Fmistral-small-24b-instruct-2501) |
| --- | --- | --- |
| LMArena general score (Elo) | 1,420.7 | 1,233.6 Δ vs A: -187.1 Elo |
| Score interval half-width (± Elo) | 6.4 | 5.88 Δ vs A: -0.52 Elo |
| LMArena document score (Elo) | Unknown | Unknown |
| Estimated effective USD / 1M tokens | $3 | $0.0575 Δ vs A: -2.9425 USD/M |
| Base input USD / 1M tokens | $1.5 | $0.05 Δ vs A: -1.45 USD/M |
| Base output USD / 1M tokens | $7.5 | $0.08 Δ vs A: -7.42 USD/M |
| Base cached-input USD / 1M tokens | Unknown | Unknown |
| Context window (tokens) | 262,144 | 32,768 Δ vs A: -229,376 tokens |
| Output limit (tokens) | 209,715 | 16,384 Δ vs A: -193,331 tokens |
| Input modalities | text, image, file | text |
| Tool use | Supported | Not supported Δ vs A: -1 |
| Reasoning | Supported | Not supported Δ vs A: -1 |
| Open weights | Unknown | Unknown |
| Recorded licence | Unknown | Unknown |
| Retirement evidence | retirement date recorded | None announced; not a guarantee |
| Recorded retirement date | 2027-01-31 | Unknown |

 4 shared measured facts

Shared measured facts. Deltas compare each model with model A. Unknown facts remain visible.

| Measured fact | A [Mistral Medium 3.5](https://undominated.ai/models/mistralai__mistral-medium-3-5/?models=mistralai%2Fmistral-medium-3-5%2Cmistralai%2Fmistral-small-24b-instruct-2501) | B [Mistral Small 3](https://undominated.ai/models/mistralai__mistral-small-24b-instruct-2501/?models=mistralai%2Fmistral-medium-3-5%2Cmistralai%2Fmistral-small-24b-instruct-2501) |
| --- | --- | --- |
| Benchmark reasoning effort | default | default |
| Model provider | Mistral | Mistral |
| Distinct sellers in the catalogue | 1 | 1 Δ vs A: 0 |
| Serving precision differs across offers | Not supported | Not supported Δ vs A: 0 |

Provider counts and precision flags describe catalogue offers. They do not establish the precision, availability, region, tool behaviour or limits of your chosen endpoint. Open each model’s provider table before switching.

 Complete price ladders and billing conditions

#### [Mistral Medium 3.5](https://undominated.ai/models/mistralai__mistral-medium-3-5/?models=mistralai%2Fmistral-medium-3-5%2Cmistralai%2Fmistral-small-24b-instruct-2501)

Rates below are USD per 1M tokens. A threshold selects that whole input/output rate pair.

| Input-token threshold | Input | Output | Cached input |
| --- | --- | --- | --- |
| Base, up to and including first threshold | $1.5 | $7.5 | Unknown |

#### [Mistral Small 3](https://undominated.ai/models/mistralai__mistral-small-24b-instruct-2501/?models=mistralai%2Fmistral-medium-3-5%2Cmistralai%2Fmistral-small-24b-instruct-2501)

Rates below are USD per 1M tokens. A threshold selects that whole input/output rate pair.

| Input-token threshold | Input | Output | Cached input |
| --- | --- | --- | --- |
| Base, up to and including first threshold | $0.05 | $0.08 | Unknown |

 Migration preflight · compare each candidate with model A

Keeping Mistral Medium 3.5 is a valid decision. No pairwise comparison certifies a drop-in replacement.

#### Mistral Medium 3.5 → Mistral Small 3

Known loss or failed requirement

 - Context window: 262,144 → 32,768 tokens.
- Output limit: 209,715 → 16,384 tokens.
- Tool use is not supported by the candidate.
- Reasoning is not supported by the candidate.
- image input is not supported by the candidate.
- file input is not supported by the candidate.
 - Provider endpoint, serving precision, availability and task success need your own verification. Catalogue model capabilities do not certify an endpoint.
 [Check alternatives to Mistral Medium 3.5](https://undominated.ai/check/mistralai__mistral-medium-3-5/)

### Estimate a fixed request shape

Private to this tab unless you save locally or explicitly export private details. These are estimates, not observed invoices. Cross-model token counts and task success are assumptions.

 Requests Input tokens per request Output tokens per request Cached share of input (%) Extra attempts per request

0.1 extra attempts means 10 extra full attempts per 100 requests. Cache writes, tool charges, taxes and unlisted charges are excluded.

 - **Mistral Medium 3.5** Estimated total: $6.75 1,000 full attempts · base rates
- **Mistral Small 3** Estimated total: $0.14 1,000 full attempts · base rates
 Prompt and output sensitivity · sampled scenarios

Every point recalculates the entire request shape. Tier-boundary samples include one token below, at and above each threshold. Ordering between samples is not guaranteed. Lowest known cost excludes unknown estimates and is not a replacement recommendation.

Vary input; hold output, requests, cache and retries fixed.

| Input tokens | Mistral Medium 3.5 | Mistral Small 3 | Coverage |
| --- | --- | --- | --- |
| 2,000 | $6.75 | $0.14 Lowest known | All computed |
| 4,096 | $9.894 | $0.2448 Lowest known | All computed |
| 32,768 | $52.902 Lowest known | ineligible Input plus output exceeds the published context window. | Incomplete |
| 131,072 | $200.358 Lowest known | ineligible Input plus output exceeds the published context window. | Incomplete |

Vary output; hold input, requests, cache and retries fixed.

| Output tokens | Mistral Medium 3.5 | Mistral Small 3 |
| --- | --- | --- |
| 128 | $3.96 | $0.11024 |
| 2,048 | $18.36 | $0.26384 |
| 8,192 | $64.44 | $0.75536 |

### Bring your observed evaluation results

JSON is parsed locally. Prompts, filenames, individual responses and extra fields are not retained. Import only aggregate measurements for selected models. Task/version labels do not establish that two evaluations used the same dataset.

 Import private evaluation JSON Expected format [{"model":"provider/exact-model-id","task":"support-answer","version":"rubric-1","attempts":100,"successes":84,"costUsd":2.4,"latencyMs":950}]

Use the exact catalogue ID. Replace the example values with observed measurements. Omit costUsd or latencyMs when they are unknown. No public score is inferred from these observations.

### Keep the decision and its evidence

A portable record retains selected facts, complete tier ladders, public requirements and the publication manifest. It also embeds the full permitted public catalogue to verify the input artifact checksum. Files are larger for this reason (up to 2 MB); local storage is limited to 12 records. Team review is local to this browser; there is no hosted collaboration.

 Owner (private) Review date (private) Recorded choice (private) Retain current: Mistral Medium 3.5 Mistral Small 3 Rationale (private)
 Include private review fields, scenario and observations in downloaded files Download decision JSON Download decision Markdown
 Store private decision records on this device Save in this browser

Saving is opt-in and includes private review fields. Shared comparison links never include them. Version 1 Check references remain separate and are not overwritten or guessed into this format.

 Import a v2 decision JSON file

#### Saved local decisions · 0

No version 2 decision records are stored in this browser.

## Questions this page answers

 Is Mistral Medium 3.5 a better-and-cheaper replacement for Mistral Small 3?

Neither model has both an equal-or-higher measured score and an equal-or-lower estimated price in this pair. Retaining your current model is a valid outcome.

 Which model is higher rated: Mistral Medium 3.5 or Mistral Small 3?

Mistral Medium 3.5 scores higher on LMArena general (1420.7 ±6.4) compared to Mistral Small 3 (1233.6 ±5.9), a margin of 187.1 Elo points. The measured confidence intervals do not overlap, demonstrating a statistically significant preference lead on human evaluations.

 Which model is more cost-effective: Mistral Medium 3.5 or Mistral Small 3?

On a standard balanced workload (3 prompt tokens per 1 generated token), Mistral Small 3 costs $0.058 per 1M tokens versus $3.00 for Mistral Medium 3.5. Mistral Medium 3.5 is approximately 52.2× the price of Mistral Small 3. Base input rates are $1.50 for Mistral Medium 3.5 and $0.050 for Mistral Small 3; base output rates are $7.50 for Mistral Medium 3.5 and $0.080 for Mistral Small 3.

 How do their context windows and generation limits compare?

Mistral Medium 3.5 provides a 262,144-token context window with a maximum output limit of 209,715 tokens. Mistral Small 3 provides a 32,768-token context window with a maximum output of 16,384 tokens. Mistral Medium 3.5 offers a 8.0× larger context capacity, making it suitable for larger repositories and multi-document workflows.

 What capabilities are lost when switching between Mistral Medium 3.5 and Mistral Small 3?

Switching from Mistral Medium 3.5 to Mistral Small 3 involves: Context window: 262,144 → 32,768 tokens; Output limit: 209,715 → 16,384 tokens; Tool use is not supported by the candidate; Reasoning is not supported by the candidate; image input is not supported by the candidate; file input is not supported by the candidate. Run test suites on your specific prompt templates and tool declarations before cutting over production traffic.

 Can Mistral Medium 3.5 or Mistral Small 3 be self-hosted or deployed privately?

Both Mistral Medium 3.5 and Mistral Small 3 are proprietary cloud models offered via managed API endpoints. Mistral Medium 3.5 is served by Mistral and 2 catalogue offers, while Mistral Small 3 is served by Mistral and 2 catalogue offers.

 What is included in this comparison?

Accepted model capabilities, context and output limits, complete price-tier ladders, independent LMArena measurements and missing evidence. Provider endpoint precision and application success still need verification.

 Can I compare a different workload or keep a decision record?

Yes. Change the public workload, prompt length and requirements in the comparison workspace. Fixed-request scenarios, aggregate evaluations and review notes stay local unless explicitly exported.

## Continue your investigation

 - [Find related models](/families/)
- [Check context tiers](/cliffs/)
- [Use observed usage](/audit/)
- [Understand score differences](/significance/)
