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. | — | >1T |
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. | 128k | 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. | $0.44Mistral | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $2.20Mistral | — |
| $198Mistral | — | |
| Benchmarks | ||
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. | 30.3% | 85.9% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 57.1% | 87.4% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 77.2% | 85.7% |
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | — | 75.3% |
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. | 92.1% | — |
IFEvalAgentic tasks — following verifiable instructions in generated responses | 89.4% | — |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | — | 30.2% |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | — | 49.8% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | 91% | — |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 70.9% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 66.1% | — |
| Overview | ||
| Company | Mistral | Qwen |
| Release date | May 7 2025 | Jan 26 2026 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Mistral Medium 3vsClaude Fable 5.2Qwen3-Max-ThinkingvsClaude Fable 5.2Mistral Medium 3vsGPT-6.2 AstraQwen3-Max-ThinkingvsGPT-6.2 AstraMistral Medium 3vsGemini 4 NeonQwen3-Max-ThinkingvsGemini 4 NeonMistral Medium 3vsMuse EmberQwen3-Max-ThinkingvsMuse EmberMistral Medium 3vsGrok 4.7Qwen3-Max-ThinkingvsGrok 4.7Mistral Medium 3vsDeepSeek-V4.1-Flash-1017Qwen3-Max-ThinkingvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Qwen3-Max-Thinking leads Mistral Medium 3 on 3 of the 3 benchmarks they both report (LiveCodeBench, GPQA Diamond, MMLU-Pro). Mistral Medium 3 shipped 264 days before Qwen3-Max-Thinking, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (Mistral Medium 3) vs 256k (Qwen3-Max-Thinking).
On LiveCodeBench, Qwen3-Max-Thinking leads at 85.9% vs Mistral Medium 3 at 30.3%. On GPQA Diamond, Qwen3-Max-Thinking leads at 87.4% vs Mistral Medium 3 at 57.1%. On MMLU-Pro, Qwen3-Max-Thinking leads at 85.7% vs Mistral Medium 3 at 77.2%.