Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Gemini 3 Flash | GPT-5.1 Codex |
|---|---|---|
| GPQA Diamond | 90.4 | — |
| Humanity's Last Exam | 43.5 | — |
| ARC-AGI v2 | 33.6 | — |
math
| Benchmark | Gemini 3 Flash | GPT-5.1 Codex |
|---|---|---|
| AIME 2025 | 99.7 | — |
coding
| Benchmark | Gemini 3 Flash | GPT-5.1 Codex |
|---|---|---|
| SWE-bench Verified | 78 | 73.7 |
multimodal
| Benchmark | Gemini 3 Flash | GPT-5.1 Codex |
|---|---|---|
| MMMU-Pro | 81.2 | — |
| CharXiv Reasoning | 80.3 | — |
| ScreenSpot Pro | 69.1 | — |
agent
| Benchmark | Gemini 3 Flash | GPT-5.1 Codex |
|---|---|---|
| Toolathlon | 49.4 | — |
| MCP Atlas | 57.4 | — |
Category Winners
coding
77.7
math
83.7
reasoning
66.0
general
62.6
multimodal
73.7
agent
33.9