GPQA Diamond
?what it ishighest score on this metric 96.4%
61º / 198 · Epoch AI, latest version we checked
Benchmarks, price, context and versions
Kimi-K2.5
Direct answer: Kimi K2.5 is a model from Moonshot AI. 87.6% on GPQA Diamond, per Epoch AI. On OpenRouter, US$ 0.53 per 1 million input tokens and US$ 3.33 per 1 million output tokens.
This block follows a rule of this section, using source data: if the model is in the top 25% of the metric, the item goes under "Good for"; if it is in the bottom half, it goes under "Not the best for". The middle band appears in neither. Price and context use OpenRouter; scores use Epoch AI or OpenRouter Benchmarks, in the latest version we checked.
highest score on this metric 96.4%
61º / 198 · Epoch AI, latest version we checked
highest score on this metric 100%
56º / 186 · Epoch AI, latest version we checked
highest score on this metric 94%
57º / 87 · Epoch AI, latest version we checked
highest score on this metric 83.5%
18º / 32 · Epoch AI, latest version we checked
highest score on this metric 96.5%
38º / 135 · OpenRouter Benchmarks, latest version we checked
highest score on this metric 82%
65º / 131 · OpenRouter Benchmarks, latest version we checked
Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch.
Kimi K2.5 is a model from Moonshot AI, with open weights, used for text, agents, code.
On OpenRouter, US$ 0.53 per 1 million input tokens and US$ 3.33 per 1 million output tokens.
262,144 tokens, per OpenRouter.
Yes, it has open weights. License: other.
87.6% on GPQA Diamond, per Epoch AI.
It scores 73.8% on SWE-bench Verified, per Epoch AI.
It was made by Moonshot AI, a lab from China.
provisional data Questions under review: Semrush had no API balance during collection. Answers use source data only.
Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch. Family and version were grouped by rule from the name.