Kimi K3 Max trails on pass@1 but beats Sol Max at pass@4 on SWE tasks
zainhas · x · 2026-07-23
A deep dive compares Kimi K3 Max with Sol Max on software-engineering tasks and argues that higher variability can translate into a better pass@k ceiling.
Key numbers from the chart:
- pass@1: Sol 72.7% vs Kimi 68.5%
- pass@2: Kimi 82.0% vs Sol 81.0%
- pass@4: Kimi 89.4% vs Sol 85.8%
The author’s takeaway is that Kimi’s higher variance hurts single-shot performance, but gives it a stronger portfolio outcome once multiple attempts are allowed.
Related event: Kimi K3 Max vs GPT-5.6 Sol Max: A Routing Problem in Coding(10 posts)→
More from Models
- 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
- Across 7 tasks, highest reasoning setting isn't the best for most open models — keunwoochoi · 2026-10-27
- Open Models Match GPT-6 on MedMCQA but Trail 17 Points on Hard Clinical Cases — keunwoochoi · 2026-10-27
- Health-Focused Benchmark Reranks LLMs: Muse Spark Open Jumps from #9 to #1 — keunwoochoi · 2026-10-27