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 | 1.5B/7B/72B |
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 | 4k |
| 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. | 68% | — |
SWE-Bench MultilingualMultilingual coding — Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | 55.7% | — |
Terminal-Bench 2.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | 22.5% | — |
MATHReasoning — accuracy on the original competition mathematics test set | — | 85.9% |
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. | — | 95.9% |
| Overview | ||
| Company | Mistral | Qwen |
| Release date | Dec 9 2025 | Sep 19 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Devstral Small 2 (24B)vsClaude Fable 5.2Qwen2.5-MathvsClaude Fable 5.2Devstral Small 2 (24B)vsGPT-6.2 AstraQwen2.5-MathvsGPT-6.2 AstraDevstral Small 2 (24B)vsGemini 4 NeonQwen2.5-MathvsGemini 4 NeonDevstral Small 2 (24B)vsMuse EmberQwen2.5-MathvsMuse EmberDevstral Small 2 (24B)vsGrok 4.7Qwen2.5-MathvsGrok 4.7Devstral Small 2 (24B)vsDeepSeek-V4.1-Flash-1017Qwen2.5-MathvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Devstral Small 2 (24B) and Qwen2.5-Math don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen2.5-Math shipped 446 days before Devstral Small 2 (24B), so benchmark comparisons should account for the intervening progress.
Devstral Small 2 (24B) has 24B parameters, while Qwen2.5-Math has 1.5B/7B/72B. Context windows are 256k (Devstral Small 2 (24B)) vs 4k (Qwen2.5-Math).
Direct benchmark comparisons are unavailable — Devstral Small 2 (24B) and Qwen2.5-Math don't publish scores on any of the same benchmarks.