GPT-5.5 (high)
Analysis Summary
GPT-5.5 (high) is the top reasoning tier within OpenAI's GPT-5.5 family, with an intelligence index of 58.9 and a coding index of 58.5 that place it second globally in both dimensions. Its agentic index of 76.4 and tau2 of 0.930 confirm exceptional reliability in multi-step autonomous workflows. GPQA (0.932), HLE (0.430), and terminalbench (0.598) are all near the top of the benchmarked field.
For businesses, this tier is the right choice for the most demanding coding, reasoning, and agentic tasks where the standard GPT-5.5 variant is unavailable or where compute-tier control is needed. Instruction following (ifbench 0.716) and long-context reasoning (lcr 0.733) are both strong, supporting structured content and document analysis at scale.
At $5 input and $30 output, it shares pricing with other GPT-5.5 tiers. The marginal gap below the standard GPT-5.5 flagship is small, and teams should treat this as a near-equivalent option for production deployment where the full GPT-5.5 endpoint is not accessible.
Assessed June 6, 2026
Editorial notes
GPT-5.5 (high) from OpenAI posts an intelligence index of 58.9 and coding index of 58.5, both near the absolute top of the field, with a 76.4 agentic index confirming world-class autonomous task performance.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How GPT-5.5 (high) compares
GPT-5.5 (high) ranks #4 of 378 AI models we track for overall intelligence, #3 of 315 for coding, #3 of 289 for agentic tasks. At $5.00 per million input tokens it is cheaper than 7% of comparable models.
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does GPT-5.5 (high) stack up?
Compare side-by-side with other professional models.
Model Information
| Provider | OpenAI |
| Release Date | April 23, 2026 |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $5.00 | $0.005000 |
| Output | $30.00 | $0.030000 |
Leaderboard Categories
Frequently asked questions about GPT-5.5 (high)
How much does GPT-5.5 (high) cost?
GPT-5.5 (high) costs $5.00 per million input tokens and $30.00 per million output tokens.
Is GPT-5.5 (high) good for coding?
On our coding benchmark index, GPT-5.5 (high) ranks #3 of 315 models, placing it in the top quartile of the field for code generation and debugging.
Who created GPT-5.5 (high)?
GPT-5.5 (high) is developed by OpenAI and was released on April 23, 2026.
