Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
math
| Benchmark | Mistral Medium 3.5 | Qwen3-Next-80B-A3B-Thinking |
|---|---|---|
| AIME 2025 | 86.3 | 87.8 |
coding
| Benchmark | Mistral Medium 3.5 | Qwen3-Next-80B-A3B-Thinking |
|---|---|---|
| SWE-bench Verified | 77.6 | — |
agent
| Benchmark | Mistral Medium 3.5 | Qwen3-Next-80B-A3B-Thinking |
|---|---|---|
| BrowseComp | 48.6 | — |
| TAU-Bench Retail | — | 69.6 |
reasoning
| Benchmark | Mistral Medium 3.5 | Qwen3-Next-80B-A3B-Thinking |
|---|---|---|
| GPQA Diamond | — | 77.2 |
Category Winners
coding
76.9
math
Q
Qwen3-Next-80B-A3B-Thinking66.1
reasoning
Q
Qwen3-Next-80B-A3B-Thinking68.1
agent
Q
Qwen3-Next-80B-A3B-Thinking55.5