Claude 4 Haiku — Benchmark Results
Anthropic Overall Score: 55/100
Performance Scores
Overall
55
Rank #32 of 45 — Top 29%
SWE-bench
48
Rank #32 of 45 — Top 29%
LiveCodeBench
58
Rank #32 of 45 — Top 29%
HumanEval
78
Rank #31 of 45 — Top 31%
BigCodeBench
40
Rank #32 of 45 — Top 29%
Strengths & Weaknesses
Strengths
- Fast
- Good value
- Improved over 3.5 Haiku
Weaknesses
- Limited reasoning depth
Compare with Similar-Priced Models
| Model | Overall Score | Input $/M |
|---|---|---|
| Claude 4 Haiku | 55 | $0.800 |
| Claude 3.5 Haiku | 52 | $0.800 |
| Claude 3 Haiku | 45 | $0.250 |
| GPT-4o mini | 58 | $0.150 |
| GPT-3.5 Turbo | 40 | $0.500 |
| OpenAI o1-mini | 70 | $1.10 |