Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Gemini 2.5 Pro Preview 06-05 | GPT-4o |
|---|---|---|
| GPQA Diamond | 86.4 | 53.6 |
| Humanity's Last Exam | 21.6 | — |
| ARC-Challenge | — | 96.4 |
| BigBench-Hard | — | 87.3 |
coding
| Benchmark | Gemini 2.5 Pro Preview 06-05 | GPT-4o |
|---|---|---|
| SWE-bench Verified | 67.2 | 33.2 |
| HumanEval | — | 90.2 |
multimodal
| Benchmark | Gemini 2.5 Pro Preview 06-05 | GPT-4o |
|---|---|---|
| MMMU | 82 | 69.1 |
general
| Benchmark | Gemini 2.5 Pro Preview 06-05 | GPT-4o |
|---|---|---|
| SimpleQA | 54 | — |
| MRCR v2 | 16.4 | — |
| IFEval | — | 83.6 |
| MMLU-Pro | — | 74.5 |
| Chatbot Arena Elo |
language
| Benchmark | Gemini 2.5 Pro Preview 06-05 | GPT-4o |
|---|---|---|
| HellaSwag | — | 96.4 |
| WinoGrande | — | 85.7 |
safety
| Benchmark | Gemini 2.5 Pro Preview 06-05 | GPT-4o |
|---|---|---|
| TruthfulQA | — | 73.5 |
Category Winners
coding
54.6
math
66.4
reasoning
57.4
general
70.5
language
79.9
multimodal
84.7
safety
94.3