Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | GPT-5.5 Instant | Qwen3.5-122B-A10B |
|---|---|---|
| GPQA Diamond | 85.6 | 86.6 |
| Humanity's Last Exam | — | 47.5 |
math
| Benchmark | GPT-5.5 Instant | Qwen3.5-122B-A10B |
|---|---|---|
| AIME 2025 | 81.2 | — |
multimodal
| Benchmark | GPT-5.5 Instant | Qwen3.5-122B-A10B |
|---|---|---|
| MMMU-Pro | 76 | 76.9 |
| CharXiv Reasoning | 81.6 | 77.2 |
| MMMU | — | 83.9 |
| ScreenSpot Pro | — | 70.4 |
coding
| Benchmark | GPT-5.5 Instant | Qwen3.5-122B-A10B |
|---|---|---|
| SWE-bench Verified | — | 72 |
general
| Benchmark | GPT-5.5 Instant | Qwen3.5-122B-A10B |
|---|---|---|
| MMMLU | — | 86.7 |
agent
| Benchmark | GPT-5.5 Instant | Qwen3.5-122B-A10B |
|---|---|---|
| BrowseComp | — | 63.8 |
Category Winners
coding
Q
Qwen3.5-122B-A10B65.6
math
54.0
reasoning
Q
Qwen3.5-122B-A10B83.6
general
Q
Qwen3.5-122B-A10B63.7
multimodal
Q
Qwen3.5-122B-A10B73.8
agent
Q
Qwen3.5-122B-A10B48.4