Codesota · Models · Kimi K2.66 results · 6 benchmarks
Model card
Kimi K2.6.
unknown1 current SOTA
§ 02 · Benchmarks
Every benchmark Kimi K2.6 has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | HLE | Reasoning · Multi-step Reasoning | accuracy | 54.0% | #1 | — | source ↗ |
| 02 | BrowseComp | Natural Language Processing · Question Answering | accuracy | 83.2% | #2 | — | source ↗ |
| 03 | SWE-Bench Verified | Computer Code · Code Generation | accuracy | 80.2% | #2 | — | source ↗ |
| 04 | GPQA Diamond | Reasoning · Multi-step Reasoning | accuracy | 90.5% | #3 | — | source ↗ |
| 05 | LiveCodeBench | Computer Code · Code Generation | pass-1 | 89.6% | #3 | — | source ↗ |
| 06 | MMMU-Pro | Multimodal · Visual Question Answering | accuracy | 79.4% | #4 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area
Where Kimi K2.6 actually performs.
§ 06 · Sources & freshness
Where these numbers come from.
pwc-dump
6
results
0 of 6 rows marked verified.