New benchmarks suggest Kimi K3.1 improves on hard tasks despite skipping SWE-maxxing
teortaxesTex · x · 2026-10-29
teortaxesTex shares more Artificial Analysis benchmark charts comparing Kimi's 1017/K3.1 models against DeepSeek V4 and Gemini 4 Carbon across Terminal-Bench-Science, FrontierCode 2.0, HLE-Diamond, GDP.pdf, Terminal-Bench 4.0 and CritpV v2. His take: he was too harsh on Kimi — the team isn't SWE-maxxing but is clearly improving on other hard tasks, e.g. Kimi K3.1 Pro tops GDP.pdf all-pass at 31% and scores 37% on HLE-Diamond.
More from Models
- DeepMind slammed for announcing models weeks before availability amid Gemini Xenon chatter — adonis_singh · 2026-10-29
- Alphabet Q3 call: Gemini Carbon frontier model, MCP apps in Search, AI Mode ads expand — lilyraynyc · 2026-10-29
- gpt-6.1-terra runs 4-hour browser session at ~1 action/second on 10% of quota — prd_008 · 2026-10-29
- AA Index revamp right before Gemini Carbon release raises benchmark timing eyebrows — stablequan · 2026-10-29
- Gemini 4 Carbon debuts #1 on Text Arena, #2 on Agent Arena at 72% less cost — prajdabre · 2026-10-29
- Google mocked for element-named models; unreleased Barium model rumored — andrew_n_carr · 2026-10-29