Claude Haiku 4.5 High (October 2025)
Performance overview across all HAL benchmarks
2
Benchmarks
2
Agents
1
Pareto Optimal Benchmarks
Token Pricing
$1
Input Tokens
per 1M tokens
$5
Output Tokens
per 1M tokens
Benchmark Performance
On the Pareto Frontier? indicates whether this model achieved a Pareto-optimal trade-off between accuracy and cost on that benchmark. Models on the Pareto frontier represent the current state-of-the-art efficiency for their performance level.
| Benchmark | Agent | Accuracy | Cost | On the Pareto Frontier? |
|---|---|---|---|---|
|
Scienceagentbench
|
SAB Self-Debug | 23.53% | $3.41 | No |
|
Swebench Verified Mini
|
HAL Generalist Agent | 44.00% | $65.31 | Yes |