Compare performance, benchmarks, and characteristics
Loading comparison...
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $3 / 1M tokens | $0.1 / 1M tokens |
| Output Price | $15 / 1M tokens | $0.28 / 1M tokens |
Capabilities | ||
| Context Window | 200K tokens | 131072 tokens |
| Capabilities | tools, reasoning | tools |
| Input type | text, image | text |
Category Scores | ||
| Overall Average | 71.4 | 25.8 |
| Maths | 88.0 | 4.0 |
| Finance | 75.3 | 13.3 |
| Science | 77.7 | 47.2 |
| Writing | 66.9 | 33.6 |
| Academia | 73.0 | 31.9 |
| Marketing | 69.2 | 33.3 |
| Programming | 49.8 | 17.6 |
Benchmark Tests | ||
| HLE | 17.3 | 4.6 |
| AIME | _ | 17.3 |
| DROP | _ | 79.6 |
| GPQA | 83.4 | 41.3 |
| MMLU | _ | 83.6 |
| SciCode | 44.7 | 26.7 |
| MATH-500 | _ | 64.9 |
| MMLU-Pro | 87.5 | 67.0 |
| HumanEval | _ | 80.5 |
| LiveCodeBench | 71.4 | 23.2 |
| AA Math Index | 88.0 | 4.0 |
| AA Coding Index | 49.8 | 17.6 |
| AAII | 62.7 | 22.6 |