Claude Opus 4.5 High (November 2025)

Performance overview across all HAL benchmarks

1
Benchmarks
2
Agents
0
Pareto Optimal Benchmarks

Token Pricing

$5
Input Tokens
per 1M tokens
$25
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?
Corebench Hard
CORE-Agent 42.22% $152.66 No
Corebench Hard
HAL Generalist Agent 31.11% $112.38 No