Leaderboard / Model
GPT-5.5 Pro
OpenAI · Closed weights · Released Apr 23, 2026 · $30 in · $180 out per 1M tokens
n/aOverall · not enough data
Score by job
Coding
Not enough data · 0 of 5 benchmarks
Agents
Not enough data · 0 of 4 benchmarks
Reasoning
80 · rank 7 · 3 of 4 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| GPQA Diamond | 93.9% | gpt-5.5-pro-pre-release_xhigh | 0.95 |
| ARC-AGI-2 | 84.6% | gpt-5.5-pro_high | 0.95 |
| SimpleBench | 76.9% | gpt-5.5-pro_unknown | 1.15 |
Math
85 · rank 5 · 3 of 5 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| FrontierMath Tiers 1–3 | 87.7% | gpt-5.5-pro_xhigh | 1.36 |
| FrontierMath Tier 4 | 78.0% | gpt-5.5-pro_xhigh | 1.55 |
| OTIS Mock AIME | 100.0% | gpt-5.5-pro-pre-release_xhigh | 1.09 |
Writing
Not enough data · 0 of 2 benchmarks
Design
Not enough data · 0 of 1 benchmarks