Kimi K3.1 Pro tops Science's Last Exam among open models at 28.92, trailing only GPT-6.1 Sol and Claude Opus 5
NielsRogge · x · 2026-11-17
Papers with Code's open-weights leaderboard for Science's Last Exam (SLE) shows Kimi K3.1 Pro as the best open model at 28.92, ahead of DeepSeek-V4.1-Flash (26.83), MiMo-V2.6-Pro (26.4), and Qwen3.8-Max (23.3).
- The benchmark covers 113 real research tasks
- Only closed models score higher overall: GPT-6.1 Sol (44.66) and Claude Opus 5 (37.5)
- Open models still trail the closed frontier by roughly 9-16 points on scientific reasoning
More from Models
- gemini-4-neon surfaces in Gemini web app code as Google's next unreleased model — imjustnewatai · 2026-11-17
- Pangram is polarizing but the author measured ~1 false positive in thousands of runs — ctjlewis · 2026-11-17
- GradeBench: best frontier model matches instructors only 57% on real handwritten physics — scaling01 · 2026-11-17
- Gemini 4 Carbon opens to paying API customers and enterprises, plus 2027 superhuman-coder forecast — thione · 2026-11-17
- Anthropic launches Claude Fable 5.2 and restricted Mythos 5.2, formalized Fermat's proof in 30 hours — thione · 2026-11-17
- Marker OCR upgrade lifts rotated-page pass rate from 81.4% to 87.3% — VikParuchuri · 2026-11-17