AI Benchmark Model
GPT-5.5 (medium)
Benchmark scores, pricing, speed, and model comparisons for GPT-5.5 (medium).
Key scores
GPT-5.5 (medium) is an artificial intelligence model developed by OpenAI and released on April 23, 2026. On the platform intelligence index, the model scores 56.7, while its coding index is 56.2. Performance metrics indicate an output speed of 64.654 tokens per second with a time to first token of 3.958 seconds. Pricing for the model is set at $5.00 per million tokens for input and $30.00 per million tokens for output, resulting in a blended rate of $11.25 per million tokens. Benchmark results include 0.926 for GPQA, 0.406 for HLE, 0.535 for SciCode, 0.7095 for IFBench, 0.7233 for LCR, 0.5758 for TerminalBench Hard, and 0.9181 for TAU2.
Benchmark results
7 tracked benchmark rows for GPT-5.5 (medium).
GPQA Reasoning
92.6% TAU2 Other
91.8% LCR Other
72.3% IFBench Other
71.0% TerminalBench Hard Other
57.6% SciCode Other
53.5% HLE Other
40.6%
Comments (0)
to join the discussion
No comments yet
Be the first to share your thoughts!