GPT-5.2 Pro

Released2025-12-11
Price per 1M$21.00 in · $168.00 out
Overall score59.9 (early, few results)
Context window400,000 tokens
ProviderOpenAI
WeightsProprietary

Scores

DimensionScoreRankBenchmarks
Overall: Balanced 59.9 7
Overall: Coding 59.6 5
Overall: Reasoning 59.9 7
Overall: Agentic work 59.6 5
Reasoning 59.6 5
Math 60.4 2
Value vs price+0.0

Configurations

ConfigurationBalancedBenchmarks
Unspecified setting 59.1 ±5.3 3
High 59.6 ±5.7 2
Medium 57.7 ±5.7 2
Extra High 60.3 ±5.5 5

Evidence

Reasoning 59.6 ±1.9

BenchmarkResultSourceDate
Extended NYT Connections 79.3% Lech Mazur 2026-11-10
ARC-AGI-2 54.2% Epoch AI 2026-11-11
ARC-AGI-2 (ARC Prize verified) 54.2% ARC Prize 2026-11-11
ARC-AGI-1 (ARC Prize verified) 90.5% ARC Prize 2026-11-11
ARC-AGI-1 90.5% Epoch AI 2026-11-11
Chess Puzzles 60.0% Epoch AI 2026-10-14
SimpleBench 57.4% SimpleBench 2025-12-12
SimpleBench 57.4% Epoch AI 2026-11-11

Math 60.4 ±1.2

BenchmarkResultSourceDate
FrontierMath Tiers 1-3 74.0% Epoch AI 2026-06-13
FrontierMath Tier 4 46.0% Epoch AI 2026-06-13
FrontierMath Tier 4 (2025 set) 31.3% Epoch AI 2025-12-24

Results not used in the score

BenchmarkResultSourceWhy not used
ARC-AGI-1 85.7% Epoch AI A stronger configuration result was used
ARC-AGI-1 81.2% Epoch AI A stronger configuration result was used
ARC-AGI-1 (ARC Prize verified) 85.7% ARC Prize A stronger configuration result was used
ARC-AGI-1 (ARC Prize verified) 81.2% ARC Prize A stronger configuration result was used
ARC-AGI-2 38.5% Epoch AI A stronger configuration result was used
ARC-AGI-2 (ARC Prize verified) 38.5% ARC Prize A stronger configuration result was used

Names matched to this model

gpt-5-2-pro, gpt-5-2-pro-2025-12-11, gpt-5-2-pro-2025-12-11-webapp, robin-alpha-pro-2025-11-24

Compare GPT-5.2 Pro with other models