GPT-5.2
ModelActiveby OpenAI · family “gpt”
GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly... (description from the OpenRouter listing)
in: filein: imagein: textout: textReasoningTool useStructured output
Epoch Capabilities Index
153.4 #36 of 268
90% CI 151.7 – 155.2
Released
11 Dec 2025
Context window
400K tokens
Max output
128K tokens
Input $ / 1M tokens
$1.75
Output $ / 1M tokens
$14.0
Cached input $ / 1M
$0.17
Each benchmark shown separately with its own source
Benchmark results (15)
| Benchmark | Domain | Score | vs best recorded | Setting | Run | Source |
|---|---|---|---|---|---|---|
| Mystery Game Puzzles | games | 23.0% ±4.2 | 27% | high | 6 Aug 2026 | Epoch ↗ |
| CL-bench | long-context | 18.1% | 65% | high | — | External ↗ |
| Chess Puzzles | games | 40.0% ±4.9 | 56% | high | 11 Dec 2025 | Eval log ↗ |
| SimpleQA Verified | knowledge | 34.3% ±1.5 | 45% | high | 27 Aug 2026 | Eval log ↗ |
| FrontierMath-Tier-4-2025-07-01-Privatesuperseded | math | 18.8% ±5.6 | 39% | high | 11 Dec 2025 | Epoch ↗ |
| GSO-Bench | coding | 27.5% | 58% | high | — | External ↗ |
| ARC-AGI-2 | reasoning | 43.3% | 46% | high | — | External ↗ |
| METR Time Horizons | agents | 75.3% | 88% | high | — | External ↗ |
| FrontierMath-2025-02-28-Privatesuperseded | math | 40.3% ±2.9 | 77% | high | 11 Dec 2025 | Epoch ↗ |
| VPCT | multimodal | 67.0% | 74% | high | — | External ↗ |
| OTIS Mock AIME 2024-2025 | math | 96.1% ±2.6 | 96% | high | 11 Dec 2025 | Eval log ↗ |
| SimpleBench | reasoning | 45.8% | 56% | high | — | External ↗ |
| SWE-Bench verified | coding | 73.8% ±2.0 | 88% | high | 12 Feb 2026 | Eval log ↗ |
| GPQA diamond | science | 88.2% ±1.9 | 92% | high | 11 Dec 2025 | Eval log ↗ |
| ARC-AGI | reasoning | 78.7% | 80% | high | — | External ↗ |
Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.
API list price over time
Price history
$ per 1M tokens
10 recorded prices on 7 Jan 2026 (OpenRouter listing + Internet Archive snapshots); re-read on every data refresh, most recently 8h ago. Steps show when the price changed.
Events
- BenchmarkEpoch AI evaluates GPT-5.2Epoch AI Benchmarking Hub
- Model launchMajorOpenAI releases GPT-5.2Epoch AI Benchmarking Hub