GPT-5.2 Low
| Released | 2025-12-11 |
|---|---|
| Price per 1M | $1.75 in · $14.00 out |
| Overall score | 49.9 · rank 268 |
| Context window | 400,000 tokens |
| Provider | OpenAI |
| Weights | Proprietary |
| Configuration | Low |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 49.9 | 268 | 11 |
| Overall: Coding | 48.2 | 285 | 7 |
| Overall: Reasoning | 52.3 | 228 | 10 |
| Overall: Agentic work | 47.4 | 304 | 7 |
| Agents | 46.1 | 229 | 1 |
| Reasoning | 52.6 | 228 | 6 |
| Math | 53.0 | 146 | 3 |
| Knowledge | 50.7 | 123 | 1 |
| Value vs price | −4.8 | 312 |
Evidence
Agents 46.1 ±6.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| DeepResearch Bench | 41.1% | Epoch AI | 2026-11-11 |
Reasoning 52.6 ±1.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Extended NYT Connections | 54.2% | Lech Mazur | 2026-11-10 |
| ARC-AGI-2 | 9.7% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 9.7% | ARC Prize | 2026-11-11 |
| GPQA Diamond | 82.7% | Epoch AI | 2025-12-11 |
| ARC-AGI-1 (ARC Prize verified) | 55.7% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 55.7% | Epoch AI | 2026-11-11 |
| Chess Puzzles | 26.0% | Epoch AI | 2026-10-13 |
| Mystery Game Puzzles | 10.0% | Epoch AI | 2026-08-27 |
Math 53.0 ±2.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 (2025 set) | 26.6% | Epoch AI | 2025-12-11 |
| FrontierMath Tier 4 (2025 set) | 6.3% | Epoch AI | 2025-12-11 |
| OTIS Mock AIME 2024-2025 | 78.9% | Epoch AI | 2025-12-11 |
Knowledge 50.7 ±3.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 32.8% | Epoch AI | 2026-08-27 |
Names matched to this model
gpt-5-2-low