OpenAI·released 2025-12-111 source
GPT-5.2 Pro benchmark scores: 5 benchmarks tracked. 40% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 5 benchmarks·best result 90.5 on ARC-AGI (unverified)·2 of 5 independently reproduced·$21/$168 per M tokens
Consensus: LiteLLM · Cross-check: models.dev, OpenRouter · See every model’s pricing →
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| ARC-AGI | 90.5accuracy (%) | unverified· optimizedT1 | 2025-12-11https://arcprize.org/leaderboard |
| FrontierMath-Tiers-1-3-v2-Private | 74accuracy (%) | reproducedT1 | 2025-12-11Epoch AI |
| ARC-AGI-2 | 54.16accuracy (%) | unverifiedT2 | 2025-12-11 |
| SimpleBench | 48.88accuracy (%) | unverifiedT1 | 2025-12-11SimpleBench Leaderboard |
| FrontierMath-Tier-4-v2-Private | 46accuracy (%) | reproducedT1 | 2025-12-11Epoch AI |
Claims drawn from cited facts, not live model generation.
This model was developed by OpenAI. It was released in 2025.
2 cited facts
This model is scored on 5 tracked benchmarks and currently holds no top score on any of them. Since the record is independently reproduced, these scores can be treated as verified rather than as unconfirmed vendor claims.
3 cited facts
Trailing the state of the art by an average of 26.53 points, this model is well behind the leaders on its benchmarks. It holds the top score on none of the benchmarks, indicating no category leadership.
2 cited facts
5 facts cross-checked across data sources: 2 corroborated, 1 single-source, 2 disputed.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks, litellm_prices, modelsdev_models, openrouter_models
GPT-5.2 Pro is an AI model developed by OpenAI, released 2025-12-11. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
GPT-5.2 Pro has recorded scores on 5 benchmarks, each shown with its evidence status.
GPT-5.2 Pro has recorded scores on 5 benchmarks — SimpleBench, ARC-AGI, ARC-AGI-2, FrontierMath-Tiers-1-3-v2-Private, FrontierMath-Tier-4-v2-Private. The full table above shows each score with its evidence status.
2 of 5 recorded scores (40%) are independently reproduced rather than self-reported by the lab.
GPT-5.2 Pro has 5 tracked claims: 2 independently reproduced, 3 unverified.
Listed API pricing: $21 per million input tokens, $168 per million output tokens (prices disputed across sources). See the pricing block for the full breakdown.