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. | 200k | 128k |
| 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% |
Okapi Multilingual MMLUMultilingual knowledge — five-shot accuracy on the Okapi translations of MMLU used in the Claude 3 model card | 63.4% | — |
| Overview | ||
| Company | Anthropic | Mistral |
| Release date | Nov 21 2023 | Jul 10 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Claude 2.1vsGPT-6.2 AstraDevstral Small 1.1vsGPT-6.2 AstraClaude 2.1vsGemini 4 HydrogenDevstral Small 1.1vsGemini 4 HydrogenClaude 2.1vsMuse EmberDevstral Small 1.1vsMuse EmberClaude 2.1vsGrok 4.7Devstral Small 1.1vsGrok 4.7Claude 2.1vsDeepSeek-V4.1-Flash-1017Devstral Small 1.1vsDeepSeek-V4.1-Flash-1017Claude 2.1vsKimi K3.1 ProDevstral Small 1.1vsKimi K3.1 ProFrequently asked questions
Claude 2.1 and Devstral Small 1.1 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Claude 2.1 shipped 597 days before Devstral Small 1.1, so benchmark comparisons should account for the intervening progress.
Context windows are 200k (Claude 2.1) vs 128k (Devstral Small 1.1). Claude 2.1 is closed, while Devstral Small 1.1 is open weight.
Direct benchmark comparisons are unavailable — Claude 2.1 and Devstral Small 1.1 don't publish scores on any of the same benchmarks.