Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Kimi K2.6 | Midjourney v6.1 |
|---|---|---|
| GPQA Diamond | 90.5 | — |
| Humanity's Last Exam | 36.4 | — |
coding
| Benchmark | Kimi K2.6 | Midjourney v6.1 |
|---|---|---|
| SWE-bench Verified | 80.2 | — |
| SWE-Bench Pro | 58.6 | — |
| SciCode | 52.2 | — |
multimodal
| Benchmark | Kimi K2.6 | Midjourney v6.1 |
|---|---|---|
| MMMU-Pro | 80.1 | — |
| CharXiv Reasoning | 86.7 | — |
agent
| Benchmark | Kimi K2.6 | Midjourney v6.1 |
|---|---|---|
| BrowseComp | 86.3 | — |
| Toolathlon | 50 | — |
| APEX Agents | 27.9 | — |
image_quality
| Benchmark | Kimi K2.6 | Midjourney v6.1 |
|---|---|---|
| Image Arena Elo | — | 1215 |
Category Winners
coding
M
Kimi K2.671.0
reasoning
M
Kimi K2.675.1
multimodal
M
Kimi K2.681.7
agent
M
Kimi K2.653.8