GPT-5.2vsGPT-5.1
Across 16 shared benchmarks, GPT-5.2 leads overall: GPT-5.2 wins 15, GPT-5.1 wins 1, with 0 ties and an average score difference of +9.54.
GPT-5.215 wins(94%)(6%)1 winGPT-5.1
Benchmark scores
Grouped by capability, sorted by largest gap within each. 16 shared benchmarks.
General Knowledge
GPT-5.2 5/5| Benchmark | GPT-5.2 | GPT-5.1 | Diff |
|---|---|---|---|
| ARC-AGI-2 | 54.2023 / 62深度思考（无工具、并行） | 17.6036 / 62 | +36.60 |
| HLE | 45.5041 / 172Deep Thinking (With Tools + Internet) | 26.5097 / 172 | +19 |
| ARC-AGI | 90.5017 / 68深度思考（无工具、并行） | 72.8028 / 68 | +17.70 |
| LiveBench | 48.9194 / 115Normal (No Tools) | 42.65106 / 115Normal (No Tools) | +6.26 |
| GPQA Diamond | 93.209 / 187深度思考（无工具、并行） | 88.1031 / 187 | +5.10 |
Coding and Software Engineer
GPT-5.2 3/3| 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 | 55.6025 / 54极高强度思考（工具） | 50.8040 / 54Thinking High (No Tools) | +4.80 |
| SWE-bench Verified | 8017 / 112极高强度思考（工具） | 76.3034 / 112 | +3.70 |
Math and Reasoning
GPT-5.2 3/3| 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 / 107极高强度思考（无工具） | 9428 / 107 | +6 |
Agent Level Benchmark
GPT-5.2 1/1| 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 |
AI Agent - Information Search
GPT-5.2 1/1| Benchmark | GPT-5.2 | GPT-5.1 | Diff |
|---|---|---|---|
| BrowseComp | 65.8031 / 53Deep Thinking (With Tools + Internet) | 50.8043 / 53Thinking High (No Tools) | +15 |
AI Agent - Tool Usage
GPT-5.2 1/1| Benchmark | GPT-5.2 | GPT-5.1 | Diff |
|---|---|---|---|
| MCP-Atlas | 67.6018 / 27极高强度思考（工具） | 50.1025 / 27Thinking High (With Tools) | +17.50 |
Commonsense Reasoning
GPT-5.1 1/1| Benchmark | GPT-5.2 | GPT-5.1 | Diff |
|---|---|---|---|
| Simple Bench | 45.8033 / 63Thinking High (No Tools) | 53.2023 / 63Thinking High (No Tools) | -7.40 |
Multimodal Understanding
GPT-5.2 1/1| Benchmark | GPT-5.2 | GPT-5.1 | Diff |
|---|---|---|---|
| MMMU | 85.901 / 29极高强度思考（无工具） | 85.402 / 29 | +0.50 |
Specs
| Field | GPT-5.2 | GPT-5.1 |
|---|---|---|
| Publisher | OpenAI | OpenAI |
| Release date | 2025-12-11 | 2025-11-12 |
| Model type | Chat model | Reasoning model |
| Architecture | Dense | Dense |
| Parameters | Not available | Not available |
| Context length | 400K | 400K |
| Max output | Not available | 128K |
API pricing
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 / 1M tokens |
| Text output | $14 / 1M tokens | $10 / 1M tokens |
| Cache read | $0.175 / 1M tokens | $0.125 / 1M tokens |
| Cache write | $1.75 / 1M tokens | $0 / 1M tokens |
Summary
- GPT-5.2leads in:General Knowledge (5/5), Coding and Software Engineer (3/3), Math and Reasoning (3/3), Agent Level Benchmark (1/1), AI Agent - Information Search (1/1), AI Agent - Tool Usage (1/1), Multimodal Understanding (1/1)
- GPT-5.1leads in:Commonsense Reasoning (1/1)
On average across the 16 shared benchmarks, GPT-5.2 scores 9.54 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.