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.
More from Models
- Moonshot pauses Kimi K3 signups five days after launch as GPU demand surges — eyishazyer · 2026-07-21
- AI Diplomacy demo makes agents negotiate, ally, and betray each other — jamdac · 2026-07-21
- Newer models need a different prompting style, and old tricks can make outputs worse — emollick · 2026-07-21
- GLM-5.5 is said to arrive in 4 weeks with open weights — tanay_mehta · 2026-07-21
- Fable 5 is credited with a 3-variable counterexample to the Jacobian conjecture — Various-Affect4841 · 2026-07-21
- Ben’s Bites roundup highlights Kimi K3, Fable 5, Cursor costs and self-driving companies — Ben's Bites · 2026-07-21