Moonshot AI: Kimi K3.1 Pro Benchmark Surge

Moonshot AI has released Kimi K3.1 Pro, a reasoning model that immediately secured fourth place on the Artificial Analysis Intelligence Index with a score of 55 points. The model is a post-trained version of its predecessor, Kimi K3, and the result represents an 11-point jump over the K3 score.

The new model's score places it just behind three other top systems: Claude Opus 5.5, which leads with 58 points, and Claude Sonnet 5.5 and Muse Wonder Full, both at 56. Moonshot AI has announced plans to release the model weights for K3.1 Pro by November 4, 2026. If that happens, K3.1 Pro would become the highest-scoring open-weights model available, reducing the gap between open and proprietary models to 3 points.

Alongside the main release, Moonshot is also shipping a variant called K3.1 Pro Highspeed, which the company says runs two to three times faster. Both models are available now through Kimi.ai, Kimi Work, Kimi Code, and the Kimi API.

The model shows its most significant performance gains in agentic tasks. On the GDPval-AA benchmark, K3.1 Pro reached an Elo score of 1,846, which is 312 points higher than K3. This score is just below Claude Opus 5.5 at 1,866 and Muse Wonder Full at 1,857. On the Terminal-Bench 4.0 test, Moonshot reports a score of 65.7 percent for K3.1 Pro, compared to 66.4 percent for Claude Opus 5.5 and 58.2 percent for GPT-6 Astra. The previous K3 model scored 13 percent on this test.

K3.1 Pro also shows improvements in coding and 3D modeling. On the BenchCAD benchmark, the model scored 92.7 percent with tools, close to Claude Opus 5.5 at 96.2 percent and GPT-6 Astra at 95.9 percent. Moonshot states the model is capable of writing and running scripts for Blender and CAD software. The company has also launched a feature called 3D Make on Kimi.com, which allows users to preview, edit, and export 3D models.

The model's architecture remains the same as its predecessor, with 2.8 trillion total parameters and 104 billion active ones. It supports a context window of one million tokens and handles both text and images. According to Artificial Analysis, K3.1 Pro sits at the top of the Pareto frontier, meaning no model with a comparable parameter count scores higher on the Intelligence Index.

Pricing for the model has been reduced, with API token prices dropping by 33 percent. Input costs are now $2 per million tokens, down from $3, while output costs are $10 per million, down from $15. The company also announced that it has stripped cyber-related data from the model's training phases for the open-weights release. On an internal test called xdev-bench-hard, the uncleaned version of the model solved 90.5 percent of tasks, while the version after data cleaning solved 81.0 percent.

Moonshot AI plans to release the model weights for K3.1 Pro by November 4, 2026. This release would make K3.1 Pro the highest-scoring open-weights model available on the Artificial Analysis Intelligence Index, narrowing the gap between open and proprietary models to 3 points. The model and its high-speed variant are available now through Kimi.ai, Kimi Work, Kimi Code, and the Kimi API.

Moonshot AI has released Kimi K3.1 Pro, a new reasoning model that scores 55 on the Artificial Analysis Intelligence Index, placing it fourth behind Claude Opus 5.5 at 58, Claude Sonnet 5.5 at 56, and Muse Wonder Full at 56. The company plans to release the model weights by November 4, 2026.