GPT-5.2 Chat: benchmark results
Provider: OpenAI. Released 2025-12-11. Access: API.
Unified ELO 1609 ± 1, rank #392 of 1761 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LM Market Cap LMC Score | 90.5 | LMC Score (0-100) | 94.5 |
| Conceptual Reasoning Index - Argument Evaluation (LMCA) | 40.12 | Chance-Corrected Score (0-100) | 78.5 |
| BenchTable | 61.7 | Total Score (%) | 74.1 |
| SnakeBench | 25.6 | TrueSkill Rating | 68.9 |
| Conceptual Reasoning Index | 51.04 | Chance-Corrected Score (0-100) | 66.4 |
| Conceptual Reasoning Index - Decision Theory (DTBench) | 68.88 | Chance-Corrected Score (0-100) | 66.2 |
| Conceptual Reasoning Index - Consistency (ACCoRD) | 65.97 | Chance-Corrected Score (0-100) | 64.9 |
| OpenRouter GPQA Diamond | 79.8 | Accuracy (%) | 48.4 |
| OpenRouter Tau2-Bench Airline | 67.3 | Accuracy (%) | 40.8 |
Interactive version: theaggregate.ai/model?slug=gpt-5-2-chat · How It Works · Data refreshed daily, snapshot 2026-09-05.