Back to GalleryBack
Model Comparison
Model Comparison
Compare performance, benchmarks, and characteristics
Loading comparison...
Model Comparison
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $2.5 / 1M tokens | $3 / 1M tokens |
| Output Price | $10 / 1M tokens | $15 / 1M tokens |
Capabilities | ||
| Context Window | 128K tokens | 256K tokens |
| Capabilities | tools | tools |
| Input type | text, image | text |
Category Scores | ||
| Overall Average | 35.6 | 71.9 |
| Academia | 42.0 | 77.5 |
| Finance | 37.5 | 82.1 |
| Marketing | 20.8 | 53.0 |
| Maths | 45.5 | 96.7 |
| Programming | 32.1 | 63.8 |
| Science | 54.3 | 87.6 |
| Writing | 17.0 | 42.5 |
Benchmark Tests | ||
| AIME | 15.0 | 94.3 |
| AA Coding Index | 32.1 | 63.8 |
| AAII | 29.6 | 67.5 |
| AA Math Index | 45.5 | 96.7 |
| GPQA | 54.3 | 87.6 |
| HLE | 3.3 | 23.9 |
| LiveCodeBench | 30.9 | 81.9 |
| MATH-500 | 75.9 | 99.0 |
| MMLU-Pro | 74.8 | 86.6 |
| SciCode | 33.3 | 45.7 |
gpt-4o Advantages
- • Lower input token cost ($2.5 / 1M tokens vs $3 / 1M tokens)
grok-4 Advantages
- • Higher benchmark scores (71.9 vs 35.6)
- • Larger context window (256K tokens vs 128K tokens)