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. | 7B | 675B |
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. | 32k | 256k |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $0.50 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | — | $1.50 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | — | $0.05 |
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. | — | $0.50Mistral |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $1.50Mistral |
| — | $175Mistral list price | |
| These models have no shared benchmark scores. | ||
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. | — | 2% |
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. | 38.4% | — |
MATHReasoning — accuracy on the original competition mathematics test set | 13.2% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 64.1% |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 37.8% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 80.9% |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | — | 54% |
| Overview | ||
| Company | Mistral | Mistral |
| Release date | May 22 2024 | Dec 2 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Mistral 7B v0.3vsClaude Fable 5.2Mistral Large 3vsClaude Fable 5.2Mistral 7B v0.3vsGPT-6.2 AstraMistral Large 3vsGPT-6.2 AstraMistral 7B v0.3vsGemini 4 HydrogenMistral Large 3vsGemini 4 HydrogenMistral 7B v0.3vsMuse EmberMistral Large 3vsMuse EmberMistral 7B v0.3vsGrok 4.7Mistral Large 3vsGrok 4.7Mistral 7B v0.3vsDeepSeek-V4.1-Flash-1017Mistral Large 3vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Mistral 7B v0.3 and Mistral Large 3 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only Mistral Large 3 has a verified first-party price for an available API: $0.50 per million input tokens and $1.50 per million output tokens. No currently available pay-as-you-go API rate is tracked for Mistral 7B v0.3. Mistral 7B v0.3 shipped 559 days before Mistral Large 3, so benchmark comparisons should account for the intervening progress.
Mistral 7B v0.3 has 7B parameters, while Mistral Large 3 has 675B. Context windows are 32k (Mistral 7B v0.3) vs 256k (Mistral Large 3).
Direct benchmark comparisons are unavailable — Mistral 7B v0.3 and Mistral Large 3 don't publish scores on any of the same benchmarks.