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 | $2.5 / 1M tokens | $0.8 / 1M tokens |
| Output Price | $10 / 1M tokens | $4 / 1M tokens |
Capabilities | ||
| Context Window | 128K tokens | 200K tokens |
| Capabilities | tools | tools |
| Input type | text, image | text, image |
Category Scores | ||
| Overall Average | 30.6 | 42.7 |
| Academia | 40.7 | 30.7 |
| Finance | 16.5 | N/A |
| Marketing | 34.4 | 49.8 |
| Maths | 6.0 | N/A |
| Programming | 24.0 | N/A |
| Science | 56.6 | 45.6 |
| Writing | 35.8 | 44.8 |
Benchmark Tests | ||
| AIME | 15.0 | 3.3 |
| AA Coding Index | 24.0 | _ |
| AAII | 27.0 | 20.2 |
| AA Math Index | 6.0 | _ |
| DROP | _ | 83.1 |
| GPQA | 54.3 | 41.2 |
| HLE | 3.3 | 3.5 |
| HumanEval | _ | 88.1 |
| LiveCodeBench | 30.9 | 31.4 |
| MATH-500 | 75.9 | 72.1 |
| MMLU-Pro | 74.8 | 63.4 |
| SciCode | 33.3 | 27.4 |
gpt-4o Advantages
claude-3.5-haiku Advantages
- • Higher benchmark scores (42.7 vs 30.6)
- • Lower input token cost ($0.8 / 1M tokens vs $2.5 / 1M tokens)
- • Larger context window (200K tokens vs 128K tokens)