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 | 6B |
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 | 8k |
| 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 · bf16 | — | |
| 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. | 71.3% | — |
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. | 61.1% | — |
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. | 83.1% | — |
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. | — | 35.9% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 60.2% | — |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | 23.9% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 94.5% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 84.5% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 84.6% | — |
| Overview | ||
| Company | Moonshot AI | Z.ai |
| Release date | Nov 6 2025 | Jul 25 2023 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Kimi K2 ThinkingvsClaude Fable 5.2CodeGeeX2-6BvsClaude Fable 5.2Kimi K2 ThinkingvsGPT-6.2 AstraCodeGeeX2-6BvsGPT-6.2 AstraKimi K2 ThinkingvsGemini 4 HydrogenCodeGeeX2-6BvsGemini 4 HydrogenKimi K2 ThinkingvsMuse EmberCodeGeeX2-6BvsMuse EmberKimi K2 ThinkingvsGrok 4.7CodeGeeX2-6BvsGrok 4.7Kimi K2 ThinkingvsDeepSeek-V4.1-Flash-1017CodeGeeX2-6BvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Kimi K2 Thinking and CodeGeeX2-6B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. CodeGeeX2-6B shipped 835 days before Kimi K2 Thinking, so benchmark comparisons should account for the intervening progress.
Kimi K2 Thinking has 1T parameters, while CodeGeeX2-6B has 6B. Context windows are 256k (Kimi K2 Thinking) vs 8k (CodeGeeX2-6B).
Direct benchmark comparisons are unavailable — Kimi K2 Thinking and CodeGeeX2-6B don't publish scores on any of the same benchmarks.