AI Benchmark Model
GPT-5.5 (high)
Benchmark scores, pricing, speed, and model comparisons for GPT-5.5 (high).
Key scores
GPT-5.5 (high) is an artificial intelligence model developed by OpenAI and released on April 23, 2026. In performance evaluations, the model achieved an intelligence index of 58.9 and a coding index of 58.5. Benchmark results include a GPQA score of 0.932, an HLE score of 0.43, a SciCode score of 0.559, an IFBench score of 0.716, an LCR score of 0.733, a TerminalBench Hard score of 0.598, and a TAU2 score of 0.930. Regarding operational metrics, the model provides an output speed of 61.555 tokens per second with a time to first token of 18.517 seconds. Pricing for the model is set at $5.00 per million input tokens and $30.00 per million output tokens, resulting in a blended rate of $11.25 per million tokens.
Benchmark results
7 tracked benchmark rows for GPT-5.5 (high).
GPQA Reasoning
93.2% TAU2 Other
93.0% LCR Other
73.3% IFBench Other
71.6% TerminalBench Hard Other
59.8% SciCode Other
55.9% HLE Other
43.0%
Comments (0)
to join the discussion
No comments yet
Be the first to share your thoughts!