Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | 24B | 0.8B/2B/4B/9B |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 32k | 256k |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.04DeepInfra | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.064DeepInfra | — |
| $14.00DeepInfra · fp8 | — | |
| Benchmarks | ||
IFEvalAgentic tasks — following verifiable instructions in generated responses | 82.9% | 91.5% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 66.3% | 82.5% |
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | — | 65.6% |
HumanEvalFunction synthesis — 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | 84.8% | — |
MATHReasoning — accuracy on the original competition mathematics test set | 70.6% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 81.7% |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 64.5% |
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | — | 41.8% |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | — | 73% |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | — | 70.1% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | — | 78.4% |
| Overview | ||
| Company | Mistral | Qwen |
| Release date | Jan 30 2025 | Mar 2 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Mistral Small 3vsClaude Fable 5.2Qwen3.5 SmallvsClaude Fable 5.2Mistral Small 3vsGPT-6.2 AstraQwen3.5 SmallvsGPT-6.2 AstraMistral Small 3vsGemini 4 NeonQwen3.5 SmallvsGemini 4 NeonMistral Small 3vsMuse EmberQwen3.5 SmallvsMuse EmberMistral Small 3vsGrok 4.7Qwen3.5 SmallvsGrok 4.7Mistral Small 3vsDeepSeek-V4.1-Flash-1017Qwen3.5 SmallvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Qwen3.5 Small leads Mistral Small 3 on 2 of the 2 benchmarks they both report (IFEval, MMLU-Pro). Mistral Small 3 shipped 396 days before Qwen3.5 Small, so benchmark comparisons should account for the intervening progress.
Mistral Small 3 has 24B parameters, while Qwen3.5 Small has 0.8B/2B/4B/9B. Context windows are 32k (Mistral Small 3) vs 256k (Qwen3.5 Small).
On IFEval, Qwen3.5 Small leads at 91.5% vs Mistral Small 3 at 82.9%. On MMLU-Pro, Qwen3.5 Small leads at 82.5% vs Mistral Small 3 at 66.3%.