Kimi K3.1 Pro benchmark sweep: tops SWE Marathon, HLE and 5 more, called best open-weight model
inductionheads · x · 2026-10-24
A shared benchmark comparison chart calling Kimi K3.1 Pro "the best open-weight model in the world."
- Wins: SWE Marathon 51.7 (vs Opus 5.5's 46.3), Agents' Last Exam 43.2, OfficeQA Pro v2 64.4, GDPVal-AA v2.1 1846, Humanity's Last Exam Full w/ tools 79.8, GDP.pdf 34.6, ZeroBench 63.9, among others.
- Trails: second on Terminal-Bench 4.0 at 65.7 (Opus 5.5: 66.4); only 38.1 on Terminal-Bench Science 0.1, well behind GPT-6 Astra (69.1) and Opus 5.5 (63.3).
- Chart notes all models were maxed out on thinking effort; Claude models may include fallbacks and GPT models cyberguards.
Related event: Moonshot Releases Kimi K3.1 Pro, Open-Weight Model Rivaling GPT-6(33 posts)→
More from Models
- Kimi 3.1 Pro priced like Argon but scores like DeepSeek V4.1 Flash on meme 'Runescape Bench' — scaling01 · 2026-10-24
- Jon Barron details his workflow: Gemini runs experiments, drafts the paper, then rewrites in his style — jon_barron · 2026-10-24
- Users praise Gem Argon for cultural fluency: a frontier model that roots for you — sebkrier · 2026-10-24
- User says Opus silently downgraded to 4.8 mid-task, then told him to talk to people — natesiggard · 2026-10-24
- Suspicious new GitHub accounts reference Qwen4 in Alibaba T-Head repo PRs — brainExploded99 · 2026-10-24
- Kimi K3.1 Pro takes on the pelican-on-a-bicycle 3D test: beats Opus 5, trails 5.5 — blaind0 · 2026-10-24