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. | 256k | 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 | — | |
| These models have no shared benchmark scores. | ||
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. | 69.2% | — |
SWE-Bench MultilingualMultilingual coding — Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | 55.9% | — |
NL2Repo-BenchRepo-level code generation — Tests whether the AI can turn a natural-language requirement into working code across an entire repository, not just produce a single function or patch. Higher is better. | — | 42.9% |
Terminal-Bench 2.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | — | 65.4% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 7.4% | — |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | 7.9% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 51% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 74.2% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 81.9% | — |
| Overview | ||
| Company | Moonshot AI | Qwen |
| Release date | Sep 5 2025 | Apr 14 2026 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Kimi K2 (0905)vsClaude Fable 5.2Qwen3.6-Max-PreviewvsClaude Fable 5.2Kimi K2 (0905)vsGPT-6.2 AstraQwen3.6-Max-PreviewvsGPT-6.2 AstraKimi K2 (0905)vsGemini 4 NeonQwen3.6-Max-PreviewvsGemini 4 NeonKimi K2 (0905)vsMuse EmberQwen3.6-Max-PreviewvsMuse EmberKimi K2 (0905)vsGrok 4.7Qwen3.6-Max-PreviewvsGrok 4.7Kimi K2 (0905)vsDeepSeek-V4.1-Flash-1017Qwen3.6-Max-PreviewvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Kimi K2 (0905) and Qwen3.6-Max-Preview don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Kimi K2 (0905) shipped 221 days before Qwen3.6-Max-Preview, so benchmark comparisons should account for the intervening progress.
Context windows are 256k (Kimi K2 (0905)) vs 256k (Qwen3.6-Max-Preview). Kimi K2 (0905) is open weight, while Qwen3.6-Max-Preview is closed.
Direct benchmark comparisons are unavailable — Kimi K2 (0905) and Qwen3.6-Max-Preview don't publish scores on any of the same benchmarks.