Back to GalleryBack
Model Comparison
Model Comparison
Compare performance, benchmarks, and characteristics
qwen-2.5-72b-instruct
deepinfra
Context32768 tokens
Input Price$0.12 / 1M tokens
Output Price$0.39 / 1M tokens
Loading comparison...
Model Comparison
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $0.12 / 1M tokens | $3 / 1M tokens |
| Output Price | $0.39 / 1M tokens | $15 / 1M tokens |
Capabilities | ||
| Context Window | 32768 tokens | 256K tokens |
| Capabilities | tools | tools |
| Input type | text | text |
Category Scores | ||
| Overall Average | 34.5 | 71.3 |
| Academia | 38.5 | 76.4 |
| Finance | 39.4 | 81.0 |
| Marketing | 20.0 | 51.5 |
| Maths | 50.9 | 96.7 |
| Programming | 27.2 | 63.8 |
| Science | 49.0 | 87.6 |
| Writing | 16.3 | 42.2 |
Benchmark Tests | ||
| AIME | 16.0 | 94.3 |
| AA Coding Index | 27.2 | 63.8 |
| AAII | 27.9 | 65.3 |
| AA Math Index | 50.9 | 96.7 |
| GPQA | 49.0 | 87.6 |
| HLE | 4.2 | 23.9 |
| HumanEval | 86.6 | _ |
| LiveCodeBench | 27.6 | 81.9 |
| MATH-500 | 85.8 | 99.0 |
| MMLU-Pro | 71.5 | 86.6 |
| SciCode | 26.7 | 45.7 |
qwen-2.5-72b-instruct Advantages
- • Lower input token cost ($0.12 / 1M tokens vs $3 / 1M tokens)
grok-4 Advantages
- • Higher benchmark scores (71.3 vs 34.5)
- • Larger context window (256K tokens vs 32768 tokens)