Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Claude Sonnet 4.6 | o1 |
|---|---|---|
| GPQA Diamond | 89.9 | 78 |
| Humanity's Last Exam | 49 | — |
| ARC-AGI v2 | 58.3 | — |
| BigBench-Hard | — | 91.5 |
coding
| Benchmark | Claude Sonnet 4.6 | o1 |
|---|---|---|
| SWE-bench Verified | 79.6 | 48.9 |
| HumanEval | — | 92.4 |
multimodal
| Benchmark | Claude Sonnet 4.6 | o1 |
|---|---|---|
| MMMU-Pro | 75.6 | — |
general
| Benchmark | Claude Sonnet 4.6 | o1 |
|---|---|---|
| MMMLU | 89.3 | — |
| IFEval | — | 86.3 |
| Chatbot Arena Elo | — | 1350 |
| MMLU-Pro | — | 79.2 |
agent
| Benchmark | Claude Sonnet 4.6 | o1 |
|---|---|---|
| OSWorld | 72.5 | — |
| BrowseComp | 74.7 | — |
| MCP Atlas | 61.3 | — |
Category Winners
coding
80.4
math
94.2
reasoning
79.3
general
86.7
multimodal
71.0
agent
58.9