Back to GalleryBack
Model Comparison
Model Comparison
Compare performance, benchmarks, and characteristics
claude-3.5-haiku
anthropic
Context200K tokens
Input Price$0.8 / 1M tokens
Output Price$4 / 1M tokens
Loading comparison...
Model Comparison
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $0.8 / 1M tokens | $3 / 1M tokens |
| Output Price | $4 / 1M tokens | $15 / 1M tokens |
Capabilities | ||
| Context Window | 200K tokens | 256K tokens |
| Capabilities | tools | tools |
| Input type | text, image | text |
Category Scores | ||
| Overall Average | 43.0 | 74.3 |
| Science | 46.0 | 80.1 |
| Writing | 45.2 | 67.6 |
| Academia | 30.7 | 76.4 |
| Marketing | 50.3 | 69.1 |
| Maths | N/A | 92.7 |
| Finance | N/A | 79.0 |
| Programming | N/A | 55.1 |
Benchmark Tests | ||
| HLE | 3.5 | 23.9 |
| AIME | 3.3 | 94.3 |
| DROP | 83.1 | _ |
| GPQA | 41.2 | 87.6 |
| SciCode | 27.4 | 45.7 |
| MATH-500 | 72.1 | 99.0 |
| MMLU-Pro | 64.2 | 86.6 |
| HumanEval | 88.1 | _ |
| LiveCodeBench | 31.4 | 81.9 |
| AA Math Index | _ | 92.7 |
| AA Coding Index | _ | 55.1 |
| AAII | 20.2 | 65.3 |
claude-3.5-haiku Advantages
- • Lower input token cost ($0.8 / 1M tokens vs $3 / 1M tokens)
grok-4 Advantages
- • Higher benchmark scores (74.3 vs 43.0)
- • Larger context window (256K tokens vs 200K tokens)