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. | 200k | 128k |
| 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. | $15.00Amazon Bedrock | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $75.00Amazon Bedrock | — |
| $6,750Amazon Bedrock | — | |
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 80.9% | 65.7% |
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | 43% | — |
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. | 74.5% | — |
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. | 46.5% | — |
MCP Atlas · original harnessMulti-step tool use — pass rate under the original tool-use harness, before Scale changed the judge and retry handling in April 2026 | 40.9% | — |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 40.8% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 76.8% |
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | 44.4% | — |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | — | 43.8% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 77.1% | — |
| Overview | ||
| Company | Anthropic | Mistral |
| Release date | Aug 5 2025 | Aug 12 2025 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Claude Opus 4.1vsGPT-6.2 AstraMistral Medium 3.1vsGPT-6.2 AstraClaude Opus 4.1vsGemini 4 HydrogenMistral Medium 3.1vsGemini 4 HydrogenClaude Opus 4.1vsMuse EmberMistral Medium 3.1vsMuse EmberClaude Opus 4.1vsGrok 4.7Mistral Medium 3.1vsGrok 4.7Claude Opus 4.1vsDeepSeek-V4.1-Flash-1017Mistral Medium 3.1vsDeepSeek-V4.1-Flash-1017Claude Opus 4.1vsKimi K3.1 ProMistral Medium 3.1vsKimi K3.1 ProFrequently asked questions
Claude Opus 4.1 leads Mistral Medium 3.1 on 1 of the 1 benchmark they both report (GPQA Diamond). Claude Opus 4.1 shipped 7 days before Mistral Medium 3.1, so benchmark comparisons should account for the intervening progress.
Context windows are 200k (Claude Opus 4.1) vs 128k (Mistral Medium 3.1).
On GPQA Diamond, Claude Opus 4.1 leads at 80.9% vs Mistral Medium 3.1 at 65.7%.