AI Benchmark Model

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

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

Key scores

Intelligence42.3Index score
Speed72.0Tokens/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. This model features adaptive reasoning capabilities with low effort and default fallback configurations. In terms of performance metrics, the model achieves an output speed of 70.483 tokens per second with a time to first token of 2.822 seconds. The intelligence index for this model is 42.3. Benchmark results include an HLE score of 0.483, a SciCode score of 0.586, and an LCR score of 0.806666666666667. Pricing for the model is set at $4.00 per million tokens for input and $20.00 per million tokens for output, resulting in a blended cost of $8.00 per million tokens.

Benchmark results

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

LCR Other
80.7%
SciCode Other
58.6%
HLE Other
48.3%