Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Claude Sonnet 4.5 | Seed 2.0 Pro |
|---|---|---|
| GPQA Diamond | 83.4 | 88.9 |
math
| Benchmark | Claude Sonnet 4.5 | Seed 2.0 Pro |
|---|---|---|
| AIME 2025 | 87 | 98.3 |
general
| Benchmark | Claude Sonnet 4.5 | Seed 2.0 Pro |
|---|---|---|
| MMMLU | 89.1 | — |
agent
| Benchmark | Claude Sonnet 4.5 | Seed 2.0 Pro |
|---|---|---|
| OSWorld | 61.4 | — |
| TAU-Bench Retail | 86.2 | — |
| BrowseComp | — | 77.3 |
coding
| Benchmark | Claude Sonnet 4.5 | Seed 2.0 Pro |
|---|---|---|
| TerminalBench | 50 | — |
| SWE-bench Verified | — | 76.5 |
Category Winners
coding
92.8
math
B
Seed 2.0 Pro82.0
reasoning
B
Seed 2.0 Pro86.7
general
72.5
agent
84.0