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. | — | 7B |
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 | 64k |
| 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 | ||
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% | 83.5% |
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. | 30.3% | — |
IFEvalAgentic tasks — following verifiable instructions in generated responses | 89.4% | — |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | 91% | — |
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% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 77.2% | — |
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 | Apr 16 2024 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Mistral Medium 3vsClaude Fable 5.2CodeQwen1.5vsClaude Fable 5.2Mistral Medium 3vsGPT-6.2 AstraCodeQwen1.5vsGPT-6.2 AstraMistral Medium 3vsGemini 4 NeonCodeQwen1.5vsGemini 4 NeonMistral Medium 3vsMuse EmberCodeQwen1.5vsMuse EmberMistral Medium 3vsGrok 4.7CodeQwen1.5vsGrok 4.7Mistral Medium 3vsDeepSeek-V4.1-Flash-1017CodeQwen1.5vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Mistral Medium 3 leads CodeQwen1.5 on 1 of the 1 benchmark they both report (HumanEval). CodeQwen1.5 shipped 386 days before Mistral Medium 3, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (Mistral Medium 3) vs 64k (CodeQwen1.5). Mistral Medium 3 is closed, while CodeQwen1.5 is open weight.
On HumanEval, Mistral Medium 3 leads at 92.1% vs CodeQwen1.5 at 83.5%.