AI Benchmark Model
Claude Opus 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback)
Benchmark scores, pricing, speed, and model comparisons for Claude Opus 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback).
Key scores
Claude Opus 5.5 is an AI model developed by Anthropic and released on September 17, 2026. This version features adaptive reasoning with medium effort and a default fallback configuration. In terms of performance metrics, the model achieves an output speed of 76.787 tokens per second with a time to first token of 11.136 seconds. Its intelligence index is recorded at 51.2. Benchmark results for the model include an HLE score of 0.547, a SciCode score of 0.593, and an LCR score of 0.843333333333333. Pricing for Claude Opus 5.5 is set at $4.00 per million tokens for input and $20.00 per million tokens for output, resulting in a blended rate of $8.00 per million tokens.
Benchmark results
3 tracked benchmark rows for Claude Opus 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback).
LCR Other
84.3% SciCode Other
59.3% HLE Other
54.7%