Neura Intelligence Index
| Benchmark | Kimi K2-Thinking-0905 | Qwen3.8 Flash |
|---|---|---|
| GPQA Diamond | 84.5 | 91.7 |
| Humanity's Last Exam | 51 | 35.9 |
| Benchmark | Kimi K2-Thinking-0905 | Qwen3.8 Flash |
|---|---|---|
| AIME 2025 | 100 | — |
| Benchmark | Kimi K2-Thinking-0905 | Qwen3.8 Flash |
|---|---|---|
| SWE-bench Verified | 71.3 | — |
| TerminalBench | 47.1 | — |
| SciCode | 44.8 | — |
| SWE-Bench Pro | — | 62.5 |
| Benchmark | Kimi K2-Thinking-0905 | Qwen3.8 Flash |
|---|---|---|
| BrowseComp | 60.2 | — |
| Toolathlon | — | 73.5 |
| Benchmark | Kimi K2-Thinking-0905 | Qwen3.8 Flash |
|---|---|---|
| CharXiv Reasoning | — | 90.6 |