Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Claude Sonnet 4.6 | Seed 2.0 Lite |
|---|---|---|
| GPQA Diamond | 89.9 | 85.1 |
| Humanity's Last Exam | 49 | — |
| ARC-AGI v2 | 58.3 | — |
coding
| Benchmark | Claude Sonnet 4.6 | Seed 2.0 Lite |
|---|---|---|
| SWE-bench Verified | 79.6 | 73.5 |
multimodal
| Benchmark | Claude Sonnet 4.6 | Seed 2.0 Lite |
|---|---|---|
| MMMU-Pro | 75.6 | — |
general
| Benchmark | Claude Sonnet 4.6 | Seed 2.0 Lite |
|---|---|---|
| MMMLU | 89.3 | — |
agent
| Benchmark | Claude Sonnet 4.6 | Seed 2.0 Lite |
|---|---|---|
| OSWorld | 72.5 | — |
| BrowseComp | 74.7 | — |
| MCP Atlas | 61.3 | — |
math
| Benchmark | Claude Sonnet 4.6 | Seed 2.0 Lite |
|---|---|---|
| AIME 2025 | — | 93 |
Category Winners
coding
80.4
math
B
Seed 2.0 Lite74.6
reasoning
B
Seed 2.0 Lite82.2
general
73.2
multimodal
71.3
agent
60.3