Grouped by capability, sorted by largest gap within each. 13 shared benchmarks.
| Benchmark | GPT-5.2 | GPT-5.1 | Diff |
|---|---|---|---|
| ARC-AGI-2 | 54.2019 / 58深度思考（无工具、并行） | 17.6032 / 58high | +36.60 |
| ARC-AGI | 90.5015 / 65深度思考（无工具、并行） | 72.8025 / 65high | +17.70 |
| GPQA Diamond | 93.207 / 175深度思考（无工具、并行） | 88.1025 / 175Thinking High (No Tools) | +5.10 |
| HLE | 45.5027 / 149Deep Thinking (With Tools + Internet) | 42.7038 / 149Thinking High (With Tools + Internet) | +2.80 |
| Benchmark | GPT-5.2 | GPT-5.1 | Diff |
|---|---|---|---|
| IC SWE-Lancer(Diamond) | 74.602 / 8极高强度思考（工具） | 69.703 / 8Thinking High (No Tools) | +4.90 |
| SWE-Bench Pro - Public | 55.6012 / 36极高强度思考（工具） | 50.8024 / 36Thinking High (No Tools) | +4.80 |
| SWE-bench Verified | 8012 / 103极高强度思考（工具） | 76.3025 / 103high | +3.70 |
| Benchmark | GPT-5.2 | GPT-5.1 | Diff |
|---|---|---|---|
| FrontierMath | 40.308 / 60极高强度思考（工具） | 26.7013 / 60Thinking High (With Tools) | +13.60 |
| FrontierMath - Tier 4 | 18.8016 / 80Thinking High (No Tools) | 12.5029 / 80Thinking High (With Tools) | +6.30 |
| AIME2025 | 1001 / 106极高强度思考（无工具） | 9428 / 106Thinking High (No Tools) | +6 |
| Benchmark | GPT-5.2 | GPT-5.1 | Diff |
|---|---|---|---|
| τ²-Bench - Telecom | 98.704 / 35极高强度思考（工具） | 95.6014 / 35Thinking High (With Tools) | +3.10 |
| Benchmark | GPT-5.2 | GPT-5.1 | Diff |
|---|---|---|---|
| BrowseComp | 65.8022 / 43Deep Thinking (With Tools + Internet) | 50.8034 / 43Thinking High (No Tools) | +15 |
| Benchmark | GPT-5.2 | GPT-5.1 | Diff |
|---|---|---|---|
| MMMU | 85.901 / 28极高强度思考（无工具） | 85.402 / 28Thinking High (No Tools) | +0.50 |
| Field | GPT-5.2 | GPT-5.1 |
|---|---|---|
| Publisher | OpenAI | OpenAI |
| Release date | 2025-12-11 | 2025-11-12 |
| Model type | AI model | Reasoning model |
| Architecture | Dense | Dense |
| Parameters | 0.0 | 0.0 |
| Context length | 400K | 400K |
| Max output | Not available | 131072 |
Prices use DataLearner records when available; missing fields are not inferred.
| Item | GPT-5.2 | GPT-5.1 |
|---|---|---|
| Text input | $1.75 / 1M tokens | 1.25 美元/100万 tokens |
| Text output | $14 / 1M tokens | 10 美元/100万 tokens |
| Cache read | $0.175 / 1M tokens | 0.125 美元/100万 tokens |
| Cache write | $1.75 / 1M tokens | Not public |
On average across the 13 shared benchmarks, GPT-5.2 scores 9.24 higher.
Largest single-benchmark gap: ARC-AGI-2 — GPT-5.2 54.20 vs GPT-5.1 17.60 (+36.60).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.
