Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | GPT-5.5 Instant | Qwen3.7-Plus |
|---|---|---|
| GPQA Diamond | 85.6 | 90.3 |
| Humanity's Last Exam | — | 34.7 |
math
| Benchmark | GPT-5.5 Instant | Qwen3.7-Plus |
|---|---|---|
| AIME 2025 | 81.2 | — |
multimodal
| Benchmark | GPT-5.5 Instant | Qwen3.7-Plus |
|---|---|---|
| MMMU-Pro | 76 | 79 |
| CharXiv Reasoning | 81.6 | 85.9 |
| ScreenSpot Pro | — | 79 |
coding
| Benchmark | GPT-5.5 Instant | Qwen3.7-Plus |
|---|---|---|
| SWE-bench Verified | — | 77.7 |
| SWE-Bench Pro | — | 57.6 |
| SciCode | — | 51.3 |
general
| Benchmark | GPT-5.5 Instant | Qwen3.7-Plus |
|---|---|---|
| MMMLU | — | 89 |
agent
| Benchmark | GPT-5.5 Instant | Qwen3.7-Plus |
|---|---|---|
| MCP Atlas | — | 73.2 |
Category Winners
coding
Q
Qwen3.7-Plus66.5
math
54.0
reasoning
82.7
general
Q
Qwen3.7-Plus72.2
multimodal
Q
Qwen3.7-Plus81.7
agent
Q
Qwen3.7-Plus59.5