Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | GPT-4.1 | MiniMax M1 80K |
|---|---|---|
| GPQA Diamond | 66.3 | 70 |
| Humanity's Last Exam | 5.4 | 8.4 |
math
| Benchmark | GPT-4.1 | MiniMax M1 80K |
|---|---|---|
| AIME 2025 | 46.4 | 76.9 |
coding
| Benchmark | GPT-4.1 | MiniMax M1 80K |
|---|---|---|
| SWE-bench Verified | 54.6 | 56 |
multimodal
| Benchmark | GPT-4.1 | MiniMax M1 80K |
|---|---|---|
| MMMU | 74.8 | — |
| CharXiv Reasoning | 56.7 | — |
agent
| Benchmark | GPT-4.1 | MiniMax M1 80K |
|---|---|---|
| TAU-Bench Retail | 68 | 63.5 |
Category Winners
coding
28.3
math
45.7
reasoning
32.2
general
66.0
multimodal
39.9
agent
50.7