GPT-5.5vsGPT-5.1
Across 10 shared benchmarks, GPT-5.5 leads overall: GPT-5.5 wins 10, GPT-5.1 wins 0, with 0 ties and an average score difference of +24.76.
GPT-5.510 wins(100%)(0%)0 winsGPT-5.1
Benchmark scores
Grouped by capability, sorted by largest gap within each. 10 shared benchmarks.
General Knowledge
GPT-5.5 4/4| Benchmark | GPT-5.5 | GPT-5.1 | Diff |
|---|---|---|---|
| ARC-AGI-2 | 851 / 59Thinking High (No Tools) | 17.6033 / 59 | +67.40 |
| HLE | 52.2013 / 157Thinking High (With Tools) | 26.5083 / 157 | +25.70 |
| ARC-AGI | 953 / 65极高强度思考（无工具） | 72.8025 / 65 | +22.20 |
| GPQA Diamond | 93.606 / 178Thinking High (No Tools) | 88.1028 / 178 | +5.50 |
Math and Reasoning
GPT-5.5 2/2| Benchmark | GPT-5.5 | GPT-5.1 | Diff |
|---|---|---|---|
| FrontierMath | 51.702 / 60Thinking High (With Tools) | 26.7013 / 60Thinking High (With Tools) | +25 |
| FrontierMath - Tier 4 | 35.407 / 80Thinking High (With Tools) | 12.5029 / 80Thinking High (With Tools) | +22.90 |
Agent Level Benchmark
GPT-5.5 1/1| Benchmark | GPT-5.5 | GPT-5.1 | Diff |
|---|---|---|---|
| τ²-Bench - Telecom | 985 / 35Thinking High (With Tools) | 95.6014 / 35Thinking High (With Tools) | +2.40 |
AI Agent - Information Search
GPT-5.5 1/1| Benchmark | GPT-5.5 | GPT-5.1 | Diff |
|---|---|---|---|
| BrowseComp | 84.405 / 45Thinking High (With Tools + Internet) | 50.8036 / 45Thinking High (No Tools) | +33.60 |
AI Agent - Tool Usage
GPT-5.5 1/1| Benchmark | GPT-5.5 | GPT-5.1 | Diff |
|---|---|---|---|
| Terminal Bench 2.0 | 82.701 / 46Thinking High (With Tools) | 47.6037 / 46Thinking High (With Tools) | +35.10 |
Coding and Software Engineer
GPT-5.5 1/1| Benchmark | GPT-5.5 | GPT-5.1 | Diff |
|---|---|---|---|
| SWE-Bench Pro - Public | 58.607 / 43Thinking High (With Tools) | 50.8030 / 43Thinking High (No Tools) | +7.80 |
Specs
| Field | GPT-5.5 | GPT-5.1 |
|---|---|---|
| Publisher | OpenAI | OpenAI |
| Release date | 2026-04-23 | 2025-11-12 |
| Model type | Reasoning model | Reasoning model |
| Architecture | Dense | Dense |
| Parameters | Not available | Not available |
| Context length | 1000K | 400K |
| Max output | 128K | 128K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | GPT-5.5 | GPT-5.1 |
|---|---|---|
| Text input | $0.5 / 1M tokens | Not public |
| Text output | $30 / 1M tokens | Not public |
| Cache read | $0.5 / 1M tokens | Not public |
| Cache write | $6.25 / 1M tokens | Not public |
One or both models have incomplete public pricing.
Summary
- GPT-5.5leads in:General Knowledge (4/4), Math and Reasoning (2/2), Agent Level Benchmark (1/1), AI Agent - Information Search (1/1), AI Agent - Tool Usage (1/1), Coding and Software Engineer (1/1)
On average across the 10 shared benchmarks, GPT-5.5 scores 24.76 higher.
Largest single-benchmark gap: ARC-AGI-2 — GPT-5.5 85 vs GPT-5.1 17.60 (+67.40).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.