Recent Papers / arXiv:2602.02276
Kimi K2.5: Visual Agentic Intelligence
Authors pending
Tasks
editResults
9 results reproduced from this paper.
Sorted instantly in-page
Results
8
SOTA rows
0
Models
1
Datasets
0
| # | Model | Vendor | Benchmark | Value | SOTA | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | Kimi-K2.5 | Moonshot.AI | AIME 2025 | 96.1% | — | source ↗ | |
| 02 | Kimi-K2.5 | Moonshot.AI | OmniDocBench | 88.8% | — | source ↗ | |
| 03 | Kimi-K2.5 | Moonshot.AI | GPQA Diamond | 87.6% | — | source ↗ | |
| 04 | Kimi-K2.5 | Moonshot.AI | Video-MME | 87.4% | — | source ↗ | |
| 05 | Kimi-K2.5 | Moonshot.AI | MMMU-Pro | 78.5% | — | source ↗ | |
| 06 | Kimi-K2.5 | Moonshot.AI | SWE-Bench Verified | 76.8% | — | source ↗ | |
| 07 | Kimi-K2.5 | Moonshot.AI | BrowseComp | 60.6% | — | source ↗ | |
| 08 | Kimi-K2.5 | Moonshot.AI | HLE | 30.1% | — | source ↗ |
CodeSOTA extraction
Benchmark evidence
Link this paper to benchmark rows, datasets, model cards, and reproduced results as evidence is extracted.