AI Benchmark Model

Claude Opus 4.5 (Reasoning)

Benchmark scores, pricing, speed, and model comparisons for Claude Opus 4.5 (Reasoning).

Key scores

Intelligence29.1Index score
Math91.3Index score
Blended Cost$10.00Per 1M tokens

Review benchmark scores, pricing, performance data, and generated comparisons for this AI model.

Benchmark results

9 tracked benchmark rows for Claude Opus 4.5 (Reasoning).

AIME 2025 Math
91.3%
MMLU Pro Knowledge
89.5%
TAU2 Other
89.5%
LiveCodeBench Code
87.1%
GPQA Reasoning
86.6%
LCR Other
77.3%
IFBench Other
58.0%
TerminalBench Hard Other
47.0%
HLE Other
30.1%