Artificial Analysis Evaluates Kimi K3.1 Pro: Leading in Knowledge Work and Coding, with AA-3D Possibly Ranking Lower
Kimi K3.1 Pro is among the leading models in agentic knowledge work and coding, but early signs suggest it will rank lower on AA-3D
AI BriefingArtificial Analysis evaluated Kimi K3.1 Pro and said it ranks among the leaders in agentic knowledge work and coding on GDPval-AA and Terminal-Bench 4.0. Voting on its AA-3D preferences is still underway; the previous-generation Kimi K3 ranked 12th among 22 models on that benchmark. The article showcases a 492 m downhill mountain-bike 3D scene generated by the model and demonstrates that steering, pedaling, and braking can be taken over at any time.
Also reported by 3 other sources
- Moonshot AI releases Kimi K3.1 Pro, rising to fourth place on the Artificial Analysis rankingsThe Decoder:AI News · 24 days ago
- Kimi K3.1 Pro released, ranking 4th in the Artificial Analysis Intelligence Index with a score of 55Artificial Analysis Full Article · 24 days ago
- Kimi K3.1 Pro Ranks 4th on the Artificial Analysis Intelligence Index with a Score of 55Artificial Analysis · 24 days ago
Source: Artificial Analysis · x.com
Event follow-up3
View all event coverage- Moonshot AI's Kimi K3.1 Pro launches on OpenRouter, an open-weight multimodal model with a 1M contextOpenRouter · 24 days ago
- Kimi K3.1 Pro released, ranking 4th in the Artificial Analysis Intelligence Index with a score of 55Artificial Analysis Full Article · 24 days ago
- Moonshot AI releases Kimi K3.1 Pro with a 1-million-token context; open weights to be released by November 4Moonshot AI:Kimi Blog · 24 days ago