Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Claude Sonnet 4 | GPT-4 Turbo |
|---|---|---|
| GPQA Diamond | 75.4 | 49.3 |
| BigBench-Hard | — | 85.1 |
| ARC-Challenge | — | 96.3 |
coding
| Benchmark | Claude Sonnet 4 | GPT-4 Turbo |
|---|---|---|
| SWE-bench Verified | 72.7 | — |
| TerminalBench | 35.5 | — |
| HumanEval | — | 87.6 |
multimodal
| Benchmark | Claude Sonnet 4 | GPT-4 Turbo |
|---|---|---|
| MMMU | 74.4 | — |
general
| Benchmark | Claude Sonnet 4 | GPT-4 Turbo |
|---|---|---|
| MMMLU | 86.5 | — |
| Chatbot Arena Elo | — | 1256 |
| MMLU-Pro | — | 64.1 |
| IFEval | — | 82.1 |
agent
| Benchmark | Claude Sonnet 4 | GPT-4 Turbo |
|---|---|---|
| TAU-Bench Retail | 80.5 | — |
language
| Benchmark | Claude Sonnet 4 | GPT-4 Turbo |
|---|---|---|
| HellaSwag | — | 95.3 |
| WinoGrande | — | 87.5 |
safety
| Benchmark | Claude Sonnet 4 | GPT-4 Turbo |
|---|---|---|
| TruthfulQA | — | 70.1 |
Category Winners
coding
63.4
math
60.3
reasoning
64.8
general
63.2
language
85.2
multimodal
67.3
safety
84.8
agent