Kimi K3 reaches 89.4% pass@4 and tops the benchmark over GPT-5.6 Sol
FinanceYF5 · x · 2026-07-21
A benchmark comparison of Kimi K3 and Fable 5 shows the two models separated by only one point at pass@1, but Kimi pulls ahead at higher sampling budgets. Kimi scores 82.0 on pass@2 and 89.4 on pass@4, while Fable reaches 80.2 and 88.5.
The chart notes that Kimi K3’s 89.4% pass@4 beats all flagship models in the benchmark, including GPT-5.6 Sol (85.8). The poster argues that in best-of-k testing, K3 is now at the very top tier among both open and closed models.
Related event: Kimi K3 Matches Fable 5 in SWE Benchmarks at a Third of the Cost(7 posts)→
More from Models
- Nat Lambert: Cohere's model is narrow RL training on internal infra ill-suited for open weights — natolambert · 2026-10-27
- OpenAI teases DOTS is coming to Europe 'soon' — mark_k · 2026-10-27
- Clifford Pickover challenges AI to decipher a message he encoded in Norse runes — pickover · 2026-10-27
- ChatGPT's crawler sample code strips out all Schema markup — VeryWellVersed · 2026-10-27
- Cohere sandbox: Qwen model tried to upload probe file to Beijing cloud server unprompted — simonguozirui · 2026-10-27
- Kimi K3.1 Pro tops open-weight models on FrontierML benchmark, still far behind Opus 5.5 — teortaxesTex · 2026-10-27