Compare AI models
| Specifications | ||
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. | 256k | 1M |
| 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. | 37.9% | 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% | 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 | Jan 13 2025 | Nov 15 2024 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Codestral 25.01vsClaude Fable 5.2Qwen2.5-Turbo (1M)vsClaude Fable 5.2Codestral 25.01vsGPT-6.2 AstraQwen2.5-Turbo (1M)vsGPT-6.2 AstraCodestral 25.01vsGemini 4 NeonQwen2.5-Turbo (1M)vsGemini 4 NeonCodestral 25.01vsMuse EmberQwen2.5-Turbo (1M)vsMuse EmberCodestral 25.01vsGrok 4.7Qwen2.5-Turbo (1M)vsGrok 4.7Codestral 25.01vsDeepSeek-V4.1-Flash-1017Qwen2.5-Turbo (1M)vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Codestral 25.01 leads Qwen2.5-Turbo (1M) on 1 of the 2 benchmarks they both report (LiveCodeBench, HumanEval). Qwen2.5-Turbo (1M) shipped 59 days before Codestral 25.01, so benchmark comparisons should account for the intervening progress.
Context windows are 256k (Codestral 25.01) vs 1M (Qwen2.5-Turbo (1M)).
On LiveCodeBench, Codestral 25.01 leads at 37.9% vs Qwen2.5-Turbo (1M) at 37.8%. On HumanEval, both models score 86.6%.