Compare AI models
| Specifications | ||
ParametersA rough measure of how big the model is. More parameters usually means more capable and more expensive to run, though it is a poor guide on its own — a smaller, newer model often beats a larger, older one. | — | 1T |
Context windowHow much text the model can hold in mind at once — your question, any documents you attach, the conversation so far, and its own reply. Go past it and the earliest part falls out of view. | — | 256k |
| 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. | — | $0.60Novita |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $2.50Novita |
| — | $245Novita · fp8 | |
| Benchmarks | ||
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. | 76.2% | 65.8% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 91.9% | 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. | 48% | — |
Next.js EvalsNext.js coding — Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | 52% | — |
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | 31.1% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 81% | — |
| Overview | ||
| Company | Moonshot AI | |
| Release date | Nov 18 2025 | Sep 5 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Gemini 3.0 ProvsClaude Haiku 5.5Kimi K2 (0905)vsClaude Haiku 5.5Gemini 3.0 ProvsGPT-6.1 SolKimi K2 (0905)vsGPT-6.1 SolGemini 3.0 ProvsMuse WonderKimi K2 (0905)vsMuse WonderGemini 3.0 ProvsGrok 4.7Kimi K2 (0905)vsGrok 4.7Gemini 3.0 ProvsDeepSeek-V4.1-FlashKimi K2 (0905)vsDeepSeek-V4.1-FlashGemini 3.0 ProvsMistral Large 4Kimi K2 (0905)vsMistral Large 4Frequently asked questions
Gemini 3.0 Pro leads Kimi K2 (0905) on 2 of the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). Kimi K2 (0905) shipped 74 days before Gemini 3.0 Pro, so benchmark comparisons should account for the intervening progress.
Gemini 3.0 Pro is closed, while Kimi K2 (0905) is open weight.
On SWE-Bench Verified, Gemini 3.0 Pro leads at 76.2% vs Kimi K2 (0905) at 65.8%. On GPQA Diamond, Gemini 3.0 Pro leads at 91.9% vs Kimi K2 (0905) at 75.1%.