GPT 5.2 Pro
OpenAI
Highlights
Top benchmark results for openai/gpt-5-2-pro-2025-12-11.
Benchmark table
| Benchmark | Category | Top Score | Info | Self Reported | Source |
|---|---|---|---|---|---|
| AIME 2025 | math | 1 | No Tools | Yes | Source |
| ARC-AGI-1 | - | 0.91 | Extra High Reasoning Effort | Yes | - |
| ARC-AGI-2 | - | 0.86 | Medium Reasoning Effort | Yes | - |
| GPQA Diamond | general-knowledge | 0.93 | No Tools | Yes | Source |
| HMMT 2025 | - | 1 | Feb 2025, No Tools | Yes | Source |
| Humanity's Last Exam | - | 0.50 | With Search + Python | Yes | Source |
Benchmark comparisons
Use the selector to switch benchmarks and see how this model stacks up against its closest competitors.
GPQA Diamond
Compare this model with the leading peers for the selected benchmark.
Benchmark
0.93
Rank #2/116
116 models
Showing 11 models around the selected model (out of 116 total).