Open Weights
- Params
- 1T
- Context
- 256K
- Released
- Jan 2026
Moonshot AI's largest open-weight model with 1T parameters and Agent Swarm capabilities..
Full Kimi K2.5 specs →
🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// COMPARISON
Kimi K2.5
A head-to-head benchmark comparison of Kimi K2.5 across 3 evaluations.
The models
Benchmark comparison
| Benchmark | Kimi K2.5 |
|---|---|
| code | |
| SWE-bench Pro | 54.2% |
| SWE-bench Verified | 75.6% |
| reasoning | |
| Humanity's Last Exam | 50.2% |
Best result per row highlighted in cyan. Each benchmark links to its definition and sources; each model links to its full scorecard.
Frequently asked questions
Which of these models is best for coding? ▶
Kimi K2.5 has the strongest result on SWE-bench Pro among the models compared here. See the code-category rows in the table for the full picture.
How many benchmarks are compared? ▶
This comparison covers 3 benchmarks on which at least one of the selected models has a published score.
Where do the benchmark scores come from? ▶
Scores are aggregated from official model cards, technical reports and standard public evaluations, and link back to each benchmark's source. They are updated as new results are published.
Explore further
Build a different comparison
Models (0 selected)
Benchmarks (auto)
Select at least two models.