Kimi K3.1 Pro Scores 55 Points, Ranking Fourth on AI Index

Moonshot AI released Kimi K3.1 Pro on Thursday, a reasoning model that ranks fourth on the Artificial Analysis Intelligence Index.

The model scored 55 points, an 11-point increase over its predecessor, Kimi K3. It sits three points behind the leading proprietary systems. Anthropic’s Claude Opus 5.5 leads with 58 points, followed by Claude Sonnet 5.5 and Muse Wonder Full at 56 points each.

K3.1 Pro is a post-trained version of K3 that received substantially more compute. Moonshot plans to publish the model weights by November 4, 2026. If released, it would become the highest-scoring open-weights model available. This move would reduce the performance gap between open and proprietary models from 12 points to 3, assuming no other changes occur.

The company is also offering K3.1 Pro Highspeed, a variant it says runs two to three times faster. Both versions are available through Kimi.ai, Kimi Work, Kimi Code, and the Kimi API.

Performance gains were most visible in agentic tasks. On the GDPval-AA benchmark, K3.1 Pro reached 1,846 Elo, a 312-point jump from K3. It trails only Claude Opus 5.5 at 1,866 Elo and Muse Wonder Full at 1,857 Elo. On Terminal-Bench 4.0, the new model scored 65.7 percent, surpassing GPT-6 Astra at 58.2 percent and falling slightly below Claude Opus 5.5 at 66.4 percent. The previous K3 model managed only 13 percent on that test.

Moonshot reports a sharp drop in hallucinations. On its internal Kimi Hallu Bench Hard, claim-level hallucinations fell from 23.4 percent with K3 to 8.3 percent. The company describes this as a stress test rather than a general error rate. GPT-6 Astra still leads this benchmark at 5.5 percent. On internal finance tests, the model gained 7.2 points on Financial Modeling and 11.6 points on Financial Research. Moonshot states it tops all tested models on OfficeQA Pro v2.

The architecture remains unchanged from K3, featuring 2.8 trillion total parameters, 104 billion active parameters, and a one-million-token context window. API prices dropped by 33 percent, with input costs at $2 per million tokens, output at $10, and cache hits at $0.20. The cost per Intelligence Index task is $1.98, nearly identical to K3’s $2.00.

In its technical blog, Moonshot addressed cybersecurity capabilities. The company stated that vulnerability research improved as post-training scaled. For the open-weights release, it removed cyber-related data from both training phases. On its internal xdev-bench-hard, the uncleaned model solved 90.5 percent of tasks, compared to 81.0 percent after cleaning. DeepSeek-V4.1-Flash scored 85.7 percent, while Kimi K3 scored 33.3 percent.