Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | ChatGPT-4o Latest | Seed 2.1 Pro |
|---|---|---|
| GPQA Diamond | 84 | — |
| Humanity's Last Exam | — | 55.7 |
agent
| Benchmark | ChatGPT-4o Latest | Seed 2.1 Pro |
|---|---|---|
| APEX Agents | — | 33.8 |
| OSWorld | — | 78.8 |
| BrowseComp | — | 86.2 |
| Toolathlon | — | 50.6 |
| MCP Atlas |
coding
| Benchmark | ChatGPT-4o Latest | Seed 2.1 Pro |
|---|---|---|
| SWE-Bench Pro | — | 57.5 |
| SciCode | — | 59.8 |
multimodal
| Benchmark | ChatGPT-4o Latest | Seed 2.1 Pro |
|---|---|---|
| MMMU-Pro | — | 82.7 |
| CharXiv Reasoning | — | 86.4 |
Category Winners
coding
B
Seed 2.1 Pro70.6
reasoning
B
Seed 2.1 Pro91.6
multimodal
B
Seed 2.1 Pro83.8
agent
B
Seed 2.1 Pro79.6