Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
multimodal
| Benchmark | QvQ-72B-Preview | Qwen 2.5 72B |
|---|---|---|
| MMMU | 70.3 | — |
language
| Benchmark | QvQ-72B-Preview | Qwen 2.5 72B |
|---|---|---|
| WinoGrande | — | 84.8 |
| HellaSwag | — | 94 |
reasoning
| Benchmark | QvQ-72B-Preview | Qwen 2.5 72B |
|---|---|---|
| BigBench-Hard | — | 83.5 |
| ARC-Challenge | — | 95.3 |
| GPQA Diamond | — | 49 |
general
| Benchmark | QvQ-72B-Preview | Qwen 2.5 72B |
|---|---|---|
| IFEval | — | 84.2 |
| Chatbot Arena Elo | — | 1261 |
| MMLU-Pro | — | 71.1 |
coding
| Benchmark | QvQ-72B-Preview | Qwen 2.5 72B |
|---|---|---|
| HumanEval | — | 86.6 |
safety
| Benchmark | QvQ-72B-Preview | Qwen 2.5 72B |
|---|---|---|
| TruthfulQA | — | 62.5 |
Category Winners
coding
59.0
math
78.5
reasoning
37.8
general
63.7
language
65.7
multimodal
Q
QvQ-72B-Preview57.8
safety
41.8