Kimi K3.1 Pro benchmarks: 65.7% on Terminal-Bench 4.0, near Claude Opus 5.5
Scobleizer · x · 2026-10-24
Kimi K3.1 Pro details: 1M-token context, MoE with 2.8T total/104B active params, multimodal. Benchmark charts show 65.7% on Terminal-Bench 4.0 (ahead of GPT-6 Astra's 58.2%, just behind Claude Opus 5.5's 66.4%), top score of 51.7% on SWE Marathon, 78.0% on Humanity's Last Exam with tools, plus leads on OfficeQA Pro v2 and Agents' Last Exam. Highlights full-project coding (Unreal/Unity/Godot), Blender/CAD 3D modeling, and finance hallucinations down 65%. K3.1 Pro and a 2-3x faster Highspeed variant are live on Kimi.ai, Kimi Work, Kimi Code and the API, with open weights by Nov 4.
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