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 | 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. | $0.351Cloudflare | $0.57Novita |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.555Cloudflare | $2.30Novita |
| $97.95Cloudflare | $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. | 45.96% | 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% |
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. | 88.41% | — |
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% |
MMLUGeneral knowledge — A 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. | 80.62% | — |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 49.25% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 64% | — |
| Overview | ||
| Company | Mistral | Moonshot AI |
| Release date | Mar 17 2025 | Jul 11 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Mistral Small 3.1vsClaude Haiku 5.5Kimi K2vsClaude Haiku 5.5Mistral Small 3.1vsGPT-6.1 SolKimi K2vsGPT-6.1 SolMistral Small 3.1vsGemini 4 ArgonKimi K2vsGemini 4 ArgonMistral Small 3.1vsMuse Spark OpenKimi K2vsMuse Spark OpenMistral Small 3.1vsGrok 4.7Kimi K2vsGrok 4.7Mistral Small 3.1vsDeepSeek-V4.1-Flash-1017Kimi K2vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Kimi K2 leads Mistral Small 3.1 on 1 of the 1 benchmark they both report (GPQA Diamond). Mistral Small 3.1 shipped 116 days before Kimi K2, so benchmark comparisons should account for the intervening progress.
Mistral Small 3.1 has 24B parameters, while Kimi K2 has 1T. Context windows are 128k (Mistral Small 3.1) vs 128k (Kimi K2).
On GPQA Diamond, Kimi K2 leads at 75.1% vs Mistral Small 3.1 at 45.96%.