Claude Sonnet 4vsKimi K2 (0905)
Claude Sonnet 4 | Kimi K2 (0905) | |
|---|---|---|
| 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 |
| 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. | 72.7% | 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. | 75.4% | 75.1% |
| BenchmarksPublished by one model only | ||
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. | 30% | — |
| Overview | ||
| Company | Anthropic | Moonshot AI |
| Release date | May 22 2025 | Sep 5 2025 |
| Access | Proprietary | Open Weight |
Frequently asked questions
Claude Sonnet 4 leads Kimi K2 (0905) on 2 of the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). Claude Sonnet 4 shipped 106 days before Kimi K2 (0905), so benchmark comparisons should account for the intervening progress.
Claude Sonnet 4 is proprietary, while Kimi K2 (0905) is open weight.
On SWE-Bench Verified, Claude Sonnet 4 leads at 72.7% vs Kimi K2 (0905) at 65.8%. On GPQA Diamond, Claude Sonnet 4 leads at 75.4% vs Kimi K2 (0905) at 75.1%.
Claude Sonnet 4 was released by Anthropic on May 22 2025.
Kimi K2 (0905) was released by Moonshot AI on Sep 5 2025.
Claude Sonnet 4 leads on SWE-Bench Verified — Claude Sonnet 4 72.7% vs Kimi K2 (0905) 65.8%.
Claude Sonnet 4 leads on GPQA Diamond — Claude Sonnet 4 75.4% vs Kimi K2 (0905) 75.1%.
Claude Sonnet 4 is a proprietary model released by Anthropic. Kimi K2 (0905) is an open weight model released by Moonshot AI.