Moonshot AI releases Kimi K3.1 Pro, ranking fourth on global intelligence index
The new model scores 55 points, an 11-point jump over its predecessor, while cutting API costs by 33% and planning an open-weights release by November 4.
By Kevin Sanders ·
Moonshot AI has released Kimi K3.1 Pro, a reasoning model that ranks fourth on the Artificial Analysis Intelligence Index. The system scored 55 points, marking an 11-point improvement over the previous version, Kimi K3. It sits three points behind the leading proprietary systems.
Only three models currently outscore K3.1 Pro. Anthropic’s Claude Opus 5.5 leads with 58 points, followed by Claude Sonnet 5.5 and Muse Wonder Full at 56 points each. Moonshot plans to publish the model weights by November 4, 2026. If released, K3.1 Pro would become the highest-scoring open-weights model, narrowing the gap between open and proprietary systems from 12 points to three.
The company also introduced 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. API prices dropped by 33%, with input costs at $2 per million tokens and output at $10. Cache hits cost $0.20 per million tokens. Because the model generates 14% more output tokens, the cost per Intelligence Index task is $1.98, nearly identical to the $2.00 cost of K3.
Performance gains were most pronounced in agentic tasks. On the GDPval-AA benchmark, K3.1 Pro reached 1,846 Elo, a 312-point increase over K3. It trails only Claude Opus 5.5 and Muse Wonder Full. On Terminal-Bench 4.0, Moonshot reports a score of 65.7%, beating GPT-6 Astra at 58.2% and falling slightly short of Claude Opus 5.5 at 66.4%. The previous model, K3, scored only 13% on that test.
Moonshot reports a sharp decline in hallucinations. On its internal Kimi Hallu Bench Hard, claim-level hallucinations dropped from 23.4% with K3 to 8.3%. The company describes this benchmark as a stress test rather than a general error rate measure. GPT-6 Astra still leads this metric at 5.5%. On internal finance benchmarks, 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 model maintains the same architecture as K3, featuring 2.8 trillion total parameters with 104 billion active, a one-million-token context window, and support for text and images. Artificial Analysis places it at the top of the Pareto frontier for its size. Moonshot also detailed cybersecurity capabilities in its technical blog. On its internal xdev-bench-hard, the uncleaned model solved 90.5% of tasks, while the cleaned open-weights version solved 81.0%. DeepSeek-V4.1-Flash scored 85.7%, and Kimi K3 scored 33.3%.
Source: The Decoder
