Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | LongCat-Flash-Thinking | Ministral 3 (14B Reasoning 2512) |
|---|---|---|
| GPQA Diamond | 81.5 | 71.2 |
math
| Benchmark | LongCat-Flash-Thinking | Ministral 3 (14B Reasoning 2512) |
|---|---|---|
| AIME 2025 | 90.6 | 85 |
coding
| Benchmark | LongCat-Flash-Thinking | Ministral 3 (14B Reasoning 2512) |
|---|---|---|
| SWE-bench Verified | 59.4 | — |
Category Winners
coding
M
LongCat-Flash-Thinking34.5
math
M
LongCat-Flash-Thinking71.3
reasoning
M
LongCat-Flash-Thinking74.4