Back to GalleryBack
Model Comparison
Model Comparison
Compare performance, benchmarks, and characteristics
claude-3-haiku-20240307
anthropic
Context200K tokens
Input Price$0.25 / 1M tokens
Output Price$1.25 / 1M tokens
Loading comparison...
Model Comparison
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $0.25 / 1M tokens | $3 / 1M tokens |
| Output Price | $1.25 / 1M tokens | $15 / 1M tokens |
Capabilities | ||
| Context Window | 200K tokens | 256K tokens |
| Capabilities | tools | tools |
| Input type | text, image | text |
Category Scores | ||
| Overall Average | 35.4 | 75.5 |
| Academia | 21.5 | 76.4 |
| Marketing | 53.6 | 69.1 |
| Programming | 17.0 | 63.8 |
| Science | 51.6 | 80.1 |
| Writing | 33.3 | 67.6 |
| Finance | N/A | 79.0 |
| Maths | N/A | 92.7 |
Benchmark Tests | ||
| AIME | 1.0 | 94.3 |
| AA Coding Index | 17.0 | 63.8 |
| AAII | 9.6 | 65.3 |
| AA Math Index | _ | 92.7 |
| DROP | 78.4 | _ |
| GPQA | 33.3 | 87.6 |
| HLE | _ | 23.9 |
| HumanEval | 75.9 | _ |
| LiveCodeBench | 15.4 | 81.9 |
| MATH-500 | 39.4 | 99.0 |
| MMLU | 75.2 | _ |
| MMLU-Pro | _ | 86.6 |
| SciCode | 18.6 | 45.7 |
claude-3-haiku-20240307 Advantages
- • Lower input token cost ($0.25 / 1M tokens vs $3 / 1M tokens)
grok-4 Advantages
- • Higher benchmark scores (75.5 vs 35.4)
- • Larger context window (256K tokens vs 200K tokens)