GPT-5.2vsGPT-5
Across 13 shared benchmarks, GPT-5.2 leads overall: GPT-5.2 wins 13, GPT-5 wins 0, with 0 ties and an average score difference of +11.65.
GPT-5.213 wins(100%)(0%)0 winsGPT-5
Benchmark scores
Grouped by capability, sorted by largest gap within each. 13 shared benchmarks.
General Knowledge
GPT-5.2 4/4| Benchmark | GPT-5.2 | GPT-5 | Diff |
|---|---|---|---|
| ARC-AGI-2 | 54.2020 / 59深度思考（无工具、并行） | 9.9037 / 59 | +44.30 |
| ARC-AGI | 90.5015 / 65深度思考（无工具、并行） | 65.7030 / 65 | +24.80 |
| HLE | 45.5032 / 157Deep Thinking (With Tools + Internet) | 35.2060 / 157 | +10.30 |
| GPQA Diamond | 93.208 / 178深度思考（无工具、并行） | 87.3037 / 178 | +5.90 |
Math and Reasoning
GPT-5.2 3/3| Benchmark | GPT-5.2 | GPT-5 | Diff |
|---|---|---|---|
| FrontierMath | 40.308 / 60极高强度思考（工具） | 24.8015 / 60 | +15.50 |
| FrontierMath - Tier 4 | 18.8016 / 80Thinking High (No Tools) | 12.5029 / 80Thinking High (No Tools) | +6.30 |
| AIME2025 | 1001 / 106极高强度思考（无工具） | 99.609 / 106 | +0.40 |
Agent Level Benchmark
GPT-5.2 2/2| Benchmark | GPT-5.2 | GPT-5 | Diff |
|---|---|---|---|
| τ²-Bench - Telecom | 98.704 / 35极高强度思考（工具） | 95.8013 / 35 | +2.90 |
| τ²-Bench | 8212 / 40极高强度思考（工具） | 8015 / 40 | +2 |
Coding and Software Engineer
GPT-5.2 2/2| Benchmark | GPT-5.2 | GPT-5 | Diff |
|---|---|---|---|
| SWE-Bench Pro - Public | 55.6017 / 43极高强度思考（工具） | 36.3041 / 43 | +19.30 |
| SWE-bench Verified | 8016 / 108极高强度思考（工具） | 72.8046 / 108 | +7.20 |
AI Agent - Information Search
GPT-5.2 1/1| Benchmark | GPT-5.2 | GPT-5 | Diff |
|---|---|---|---|
| BrowseComp | 65.8024 / 45Deep Thinking (With Tools + Internet) | 54.9032 / 45 | +10.90 |
Multimodal Understanding
GPT-5.2 1/1| Benchmark | GPT-5.2 | GPT-5 | Diff |
|---|---|---|---|
| MMMU | 85.901 / 28极高强度思考（无工具） | 84.205 / 28 | +1.70 |
Specs
| Field | GPT-5.2 | GPT-5 |
|---|---|---|
| Publisher | OpenAI | OpenAI |
| Release date | 2025-12-11 | 2025-08-07 |
| Model type | Chat model | Foundation 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 |
|---|---|---|
| Text input | $1.75 / 1M tokens | Not public |
| Text output | $14 / 1M tokens | Not public |
| Cache read | $0.175 / 1M tokens | Not public |
| Cache write | $1.75 / 1M tokens | Not public |
One or both models have incomplete public pricing.
Summary
- GPT-5.2leads in:General Knowledge (4/4), Math and Reasoning (3/3), Agent Level Benchmark (2/2), Coding and Software Engineer (2/2), AI Agent - Information Search (1/1), Multimodal Understanding (1/1)
On average across the 13 shared benchmarks, GPT-5.2 scores 11.65 higher.
Largest single-benchmark gap: ARC-AGI-2 — GPT-5.2 54.20 vs GPT-5 9.90 (+44.30).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.