AI Benchmark Model

Claude Opus 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback)

Benchmark scores, pricing, speed, and model comparisons for Claude Opus 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback).

Key scores

Intelligence56.0Index score
Speed84.1Tokens/sec
Blended Cost$8.00Per 1M tokens

Claude Opus 5.5 is an artificial intelligence model developed by Anthropic and released on September 17, 2026. The model features an intelligence index of 56 and demonstrates performance across several standardized evaluations, including an HLE score of 0.575, a SciCode score of 0.65, and an LCR score of 0.846666666666667. Regarding operational efficiency, the model provides an output speed of 84.874 tokens per second with a time to first token of 63.684 seconds. Pricing for the model is structured 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. This configuration utilizes adaptive reasoning with high effort and a default fallback setting.

Benchmark results

3 tracked benchmark rows for Claude Opus 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback).

LCR Other
84.7%
SciCode Other
65.0%
HLE Other
57.5%