Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | GPT-5.2 | Kimi K2-Thinking-0905 |
|---|---|---|
| GPQA Diamond | 92.4 | 84.5 |
| Humanity's Last Exam | 34.5 | 51 |
| ARC-AGI v2 | 52.9 | — |
math
| Benchmark | GPT-5.2 | Kimi K2-Thinking-0905 |
|---|---|---|
| AIME 2025 | 100 | 100 |
| FrontierMath | 40.3 | — |
coding
| Benchmark | GPT-5.2 | Kimi K2-Thinking-0905 |
|---|---|---|
| SWE-bench Verified | 80 | 71.3 |
| TerminalBench | — | 47.1 |
| SciCode | — | 44.8 |
multimodal
| Benchmark | GPT-5.2 | Kimi K2-Thinking-0905 |
|---|---|---|
| MMMU-Pro | 79.5 | — |
| CharXiv Reasoning | 82.1 | — |
| ScreenSpot Pro | 86.3 | — |
general
| Benchmark | GPT-5.2 | Kimi K2-Thinking-0905 |
|---|---|---|
| MMMLU | 89.6 | — |
agent
| Benchmark | GPT-5.2 | Kimi K2-Thinking-0905 |
|---|---|---|
| BrowseComp | 65.8 | 60.2 |
| Toolathlon | 46.3 | — |
| MCP Atlas | 60.6 | — |
Category Winners
coding
81.1
math
M
Kimi K2-Thinking-090584.0
reasoning
M
Kimi K2-Thinking-090584.5
general
74.2
multimodal
83.1
agent
M
Kimi K2-Thinking-090541.4