Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
coding
| Benchmark | Gemini 3.6 Flash | LongCat-Flash-Thinking-2601 |
|---|---|---|
| SWE-Bench Pro | 58.7 | — |
| SWE-bench Verified | — | 70 |
multimodal
| Benchmark | Gemini 3.6 Flash | LongCat-Flash-Thinking-2601 |
|---|---|---|
| CharXiv Reasoning | 89.4 | — |
general
| Benchmark | Gemini 3.6 Flash | LongCat-Flash-Thinking-2601 |
|---|---|---|
| MRCR v2 | 54 | — |
reasoning
| Benchmark | Gemini 3.6 Flash | LongCat-Flash-Thinking-2601 |
|---|---|---|
| GPQA Diamond | — | 80.5 |
| Humanity's Last Exam | — | 25.2 |
math
| Benchmark | Gemini 3.6 Flash | LongCat-Flash-Thinking-2601 |
|---|---|---|
| AIME 2025 | — | 99.6 |
agent
| Benchmark | Gemini 3.6 Flash | LongCat-Flash-Thinking-2601 |
|---|---|---|
| BrowseComp | — | 56.6 |
Category Winners
coding
M
LongCat-Flash-Thinking-260160.1
math
M
LongCat-Flash-Thinking-260184.0
reasoning
M
LongCat-Flash-Thinking-260154.4
general
56.1
multimodal
84.1
agent
M
LongCat-Flash-Thinking-260130.7