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. | 72B | 9B |
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 |
| 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. | 60.4% | — |
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. | — | 28.5% |
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. | — | 82.3% |
| Overview | ||
| Company | Moonshot AI | Z.ai |
| Release date | Jun 17 2025 | Jul 5 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Kimi-DevvsClaude Fable 5.2CodeGeeX4-ALL-9BvsClaude Fable 5.2Kimi-DevvsGPT-6.2 AstraCodeGeeX4-ALL-9BvsGPT-6.2 AstraKimi-DevvsGemini 4 HydrogenCodeGeeX4-ALL-9BvsGemini 4 HydrogenKimi-DevvsMuse EmberCodeGeeX4-ALL-9BvsMuse EmberKimi-DevvsGrok 4.7CodeGeeX4-ALL-9BvsGrok 4.7Kimi-DevvsDeepSeek-V4.1-Flash-1017CodeGeeX4-ALL-9BvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Kimi-Dev and CodeGeeX4-ALL-9B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. CodeGeeX4-ALL-9B shipped 347 days before Kimi-Dev, so benchmark comparisons should account for the intervening progress.
Kimi-Dev has 72B parameters, while CodeGeeX4-ALL-9B has 9B. Context windows are 128k (Kimi-Dev) vs 128k (CodeGeeX4-ALL-9B).
Direct benchmark comparisons are unavailable — Kimi-Dev and CodeGeeX4-ALL-9B don't publish scores on any of the same benchmarks.