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 | — |
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 | 1M |
| These models have no shared benchmark scores. | ||
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. | 53.6% | — |
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. | — | 37.8% |
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. | — | 86.6% |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 76.3% |
MATHReasoning — accuracy on the original competition mathematics test set | — | 81.1% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 64.5% |
GSM8KGrade-school math — Grade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. | — | 93.8% |
| Overview | ||
| Company | Mistral | Qwen |
| Release date | Jul 10 2025 | Nov 15 2024 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Devstral Small 1.1vsClaude Fable 5.2Qwen2.5-Turbo (1M)vsClaude Fable 5.2Devstral Small 1.1vsGPT-6.2 AstraQwen2.5-Turbo (1M)vsGPT-6.2 AstraDevstral Small 1.1vsGemini 4 NeonQwen2.5-Turbo (1M)vsGemini 4 NeonDevstral Small 1.1vsMuse EmberQwen2.5-Turbo (1M)vsMuse EmberDevstral Small 1.1vsGrok 4.7Qwen2.5-Turbo (1M)vsGrok 4.7Devstral Small 1.1vsDeepSeek-V4.1-Flash-1017Qwen2.5-Turbo (1M)vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Devstral Small 1.1 and Qwen2.5-Turbo (1M) don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen2.5-Turbo (1M) shipped 237 days before Devstral Small 1.1, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (Devstral Small 1.1) vs 1M (Qwen2.5-Turbo (1M)). Devstral Small 1.1 is open weight, while Qwen2.5-Turbo (1M) is closed.
Direct benchmark comparisons are unavailable — Devstral Small 1.1 and Qwen2.5-Turbo (1M) don't publish scores on any of the same benchmarks.