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. | 1M | 128k |
| API pricingUSD per 1M tokens · lower wins · base tier | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $1.25 | — |
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. | $10.00 | — |
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. | $0.125 | — |
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. | $0.625Google AI Studio | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $5.00Google AI Studio | — |
| $750Google list price | — | |
| 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. | 70.4% | 70.88% |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 92% | 86.14% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 86.7% | 77.34% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 84% | 70.07% |
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. | 20% | — |
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. | 63.8% | — |
Aider Polyglot (diff)Coding — editing code in six languages using the diff edit format | 68.6% | — |
Humanity's Last Exam · no toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | 18.8% | — |
SimpleQAKnowledge — accuracy on short, fact-seeking questions in the original SimpleQA set | 52.9% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 81.7% | — |
| Overview | ||
| Company | Mistral | |
| Release date | Mar 25 2025 | Sep 17 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Gemini 2.5 ProvsClaude Fable 5.2Magistral Small 1.2vsClaude Fable 5.2Gemini 2.5 ProvsGPT-6.2 AstraMagistral Small 1.2vsGPT-6.2 AstraGemini 2.5 ProvsMuse EmberMagistral Small 1.2vsMuse EmberGemini 2.5 ProvsGrok 4.7Magistral Small 1.2vsGrok 4.7Gemini 2.5 ProvsDeepSeek-V4.1-Flash-1017Magistral Small 1.2vsDeepSeek-V4.1-Flash-1017Gemini 2.5 ProvsKimi K3.1 ProMagistral Small 1.2vsKimi K3.1 ProFrequently asked questions
Gemini 2.5 Pro leads Magistral Small 1.2 on 3 of the 4 benchmarks they both report (LiveCodeBench, AIME 2024, AIME 2025, GPQA Diamond). Only Gemini 2.5 Pro has a verified first-party price for an available API: $1.25 per million input tokens and $10.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for Magistral Small 1.2. Gemini 2.5 Pro shipped 176 days before Magistral Small 1.2, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Gemini 2.5 Pro) vs 128k (Magistral Small 1.2). Gemini 2.5 Pro is closed, while Magistral Small 1.2 is open weight.
On LiveCodeBench, Magistral Small 1.2 leads at 70.88% vs Gemini 2.5 Pro at 70.4%. On AIME 2024, Gemini 2.5 Pro leads at 92% vs Magistral Small 1.2 at 86.14%. On AIME 2025, Gemini 2.5 Pro leads at 86.7% vs Magistral Small 1.2 at 77.34%. On GPQA Diamond, Gemini 2.5 Pro leads at 84% vs Magistral Small 1.2 at 70.07%.