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. | — | 1T |
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. | 128k | 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. | — | $0.57Novita |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $2.30Novita |
| — | $229Novita · fp8 | |
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 76.26% | 75.1% |
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. | — | 10% |
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. | — | 65.8% |
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. | 75% | — |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | — | 4.7% |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 91.82% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 83.48% | — |
| Overview | ||
| Company | Mistral | Moonshot AI |
| Release date | Sep 17 2025 | Jul 11 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Magistral Medium 1.2vsClaude Fable 5.2Kimi K2vsClaude Fable 5.2Magistral Medium 1.2vsGPT-6.2 AstraKimi K2vsGPT-6.2 AstraMagistral Medium 1.2vsGemini 4 HydrogenKimi K2vsGemini 4 HydrogenMagistral Medium 1.2vsMuse EmberKimi K2vsMuse EmberMagistral Medium 1.2vsGrok 4.7Kimi K2vsGrok 4.7Magistral Medium 1.2vsDeepSeek-V4.1-Flash-1017Kimi K2vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Magistral Medium 1.2 leads Kimi K2 on 1 of the 1 benchmark they both report (GPQA Diamond). Kimi K2 shipped 68 days before Magistral Medium 1.2, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (Magistral Medium 1.2) vs 128k (Kimi K2). Magistral Medium 1.2 is closed, while Kimi K2 is open weight.
On GPQA Diamond, Magistral Medium 1.2 leads at 76.26% vs Kimi K2 at 75.1%.