Back to GalleryBack
Model Comparison
Model Comparison
Compare performance, benchmarks, and characteristics
Loading comparison...
Model Comparison
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $3 / 1M tokens | $3 / 1M tokens |
| Output Price | $12 / 1M tokens | $15 / 1M tokens |
Capabilities | ||
| Context Window | 128K tokens | 256K tokens |
| Capabilities | tools | |
| Input type | text | text |
Category Scores | ||
| Overall Average | 54.9 | 71.9 |
| Academia | 51.7 | 77.5 |
| Finance | 60.4 | 82.1 |
| Marketing | 52.4 | 53.0 |
| Maths | 77.4 | 96.7 |
| Programming | 44.9 | 63.8 |
| Science | 60.1 | 87.6 |
| Writing | 37.1 | 42.5 |
Benchmark Tests | ||
| AIME | 60.3 | 94.3 |
| AA Coding Index | 44.9 | 63.8 |
| AAII | 43.3 | 67.5 |
| AA Math Index | 77.4 | 96.7 |
| GPQA | 60.1 | 87.6 |
| HLE | 4.9 | 23.9 |
| HumanEval | 92.4 | _ |
| LiveCodeBench | 57.6 | 81.9 |
| MATH-500 | 94.4 | 99.0 |
| MMLU | 85.2 | _ |
| MMLU-Pro | 74.2 | 86.6 |
| SciCode | 32.3 | 45.7 |
o1-mini Advantages
grok-4 Advantages
- • Higher benchmark scores (71.9 vs 54.9)
- • Larger context window (256K tokens vs 128K tokens)