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 | >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 | 256k |
| 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% | — |
| Overview | ||
| Company | Moonshot AI | Qwen |
| Release date | Jun 17 2025 | Sep 24 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Kimi-DevvsClaude Haiku 5.5Qwen3-MaxvsClaude Haiku 5.5Kimi-DevvsGPT-6.1 TerraQwen3-MaxvsGPT-6.1 TerraKimi-DevvsGemini 4 CarbonQwen3-MaxvsGemini 4 CarbonKimi-DevvsMuse Spark OpenQwen3-MaxvsMuse Spark OpenKimi-DevvsGrok 4.7Qwen3-MaxvsGrok 4.7Kimi-DevvsDeepSeek-V4.1-Flash-1017Qwen3-MaxvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Kimi-Dev and Qwen3-Max don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Kimi-Dev shipped 99 days before Qwen3-Max, so benchmark comparisons should account for the intervening progress.
Kimi-Dev has 72B parameters, while Qwen3-Max has >1T. Context windows are 128k (Kimi-Dev) vs 256k (Qwen3-Max). Kimi-Dev is open weight, while Qwen3-Max is closed.
Direct benchmark comparisons are unavailable — Kimi-Dev and Qwen3-Max don't publish scores on any of the same benchmarks.