Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | LongCat-Flash-Thinking | MiniMax M2.5 |
|---|---|---|
| GPQA Diamond | 81.5 | — |
math
| Benchmark | LongCat-Flash-Thinking | MiniMax M2.5 |
|---|---|---|
| AIME 2025 | 90.6 | — |
coding
| Benchmark | LongCat-Flash-Thinking | MiniMax M2.5 |
|---|---|---|
| SWE-bench Verified | 59.4 | 80.2 |
| SWE-Bench Pro | — | 55.4 |
agent
| Benchmark | LongCat-Flash-Thinking | MiniMax M2.5 |
|---|---|---|
| BrowseComp | — | 76.3 |
Category Winners
coding
57.4
math
M
LongCat-Flash-Thinking70.8
reasoning
M
LongCat-Flash-Thinking76.9
agent
70.9