Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Gemini 3.5 Flash | Llama 3.1 Nemotron Ultra 253B v1 |
|---|---|---|
| Humanity's Last Exam | 40.2 | — |
| ARC-AGI v2 | 72.1 | — |
| GPQA Diamond | — | 76.0 |
coding
| Benchmark | Gemini 3.5 Flash | Llama 3.1 Nemotron Ultra 253B v1 |
|---|---|---|
| SWE-Bench Pro | 55.1 | — |
multimodal
| Benchmark | Gemini 3.5 Flash | Llama 3.1 Nemotron Ultra 253B v1 |
|---|---|---|
| MMMU-Pro | 83.6 | — |
| CharXiv Reasoning | 84.2 | — |
agent
| Benchmark | Gemini 3.5 Flash | Llama 3.1 Nemotron Ultra 253B v1 |
|---|---|---|
| Toolathlon | 56.5 | — |
| MCP Atlas | 83.6 | — |
general
| Benchmark | Gemini 3.5 Flash | Llama 3.1 Nemotron Ultra 253B v1 |
|---|---|---|
| MRCR v2 | 26.6 | — |
math
| Benchmark | Gemini 3.5 Flash | Llama 3.1 Nemotron Ultra 253B v1 |
|---|---|---|
| AIME 2025 | — | 72.5 |
Category Winners
coding
38.4
math
37.1
reasoning
75.4
general
20.3
multimodal
80.5
agent
73.0