Moonshot AI K3.1 Pro ranks fourth on intelligence index
The new Chinese model scores 55 points, placing it three points behind the top proprietary systems while reducing API costs by a third.
By Fatima Laurent ·
Global artificial intelligence benchmarks currently show a tight cluster of high-performing proprietary systems. Moonshot AI has entered that tier with the release of Kimi K3.1 Pro, a reasoning model that now holds the fourth position on the Artificial Analysis Intelligence Index.
The model achieved a score of 55, representing an 11-point increase over its predecessor, Kimi K3. According to Artificial Analysis, only three systems currently outperform K3.1 Pro: Anthropic's Claude Opus 5.5 with 58 points, and Claude Sonnet 5.5 and Muse Wonder Full, both at 56 points.
K3.1 Pro is a post-trained variant of K3 that utilized a larger amount of post-training compute. Moonshot plans to publish the model weights by November 4, 2026. If released on schedule, it would become the highest-scoring open-weights model available. That release would narrow the performance gap between open and proprietary systems from 12 points to three, assuming no other changes occur in the interim.
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 and Muse Wonder Full at 1,857. In Terminal-Bench 4.0, Moonshot reports a score of 65.7 percent. This exceeds GPT-6 Astra at 58.2 percent but remains slightly below Claude Opus 5.5 at 66.4 percent, whereas K3 managed only 13 percent on the same test.
The company also reports a reduction in hallucinations. On its internal Kimi Hallu Bench Hard, claim-level hallucinations dropped from 23.4 percent with K3 to 8.3 percent. Moonshot describes this benchmark as a stress test rather than a general error measure, noting that GPT-6 Astra still leads with a 5.5 percent rate.
Pricing for the API has decreased by 33 percent. Input costs are set at $2 per million tokens, with output at $10 and cache hits at $0.20. Although the model generates 14 percent more output tokens, the total cost to run each Intelligence Index task is $1.98, nearly identical to K3's $2.00. Both the standard K3.1 Pro and a faster variant called K3.1 Pro Highspeed are available through Kimi.ai, Kimi Work, Kimi Code, and the Kimi API.
The architecture remains unchanged from K3, featuring 2.8 trillion total parameters, 104 billion active parameters, and a one-million-token context window. Artificial Analysis places the model at the top of the Pareto frontier, indicating no model of comparable size scores higher on its index. Moonshot also highlights capabilities in 3D modeling and coding, stating the model can write and run scripts for Blender and CAD software without MCP connectors.
Source: The Decoder
