GPT-5.2 Instant
GPT-5.2 Instant.
11
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
OpenAI Dec 2025
GPT-5.2 Instant
Closed weights Flagship
No Epoch Capabilities Index score yet
- KORA 52.8% #17 /42
- DTBench 68.9% #84 /178
- BullshitBench V2 27% #75 /122
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LMArena (Elo) | 1,476 | #31 of 333 | Official leaderboard | |
| SuperGPQA | 56.4% | #17 of 58 | Official leaderboard | |
| BullshitBench V2 | 27% | #75 of 122 | Official leaderboard | |
| BullshitBench | 14.6% | #87 of 107 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| DTBench | 68.9% | #84 of 178 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SnakeBench | 26 | #70 of 183 | Official leaderboard | |
| LLM Chess | 142 | #57 of 124 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Vision Arena | 1,278 | #25 of 136 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| KORA | 52.8% | #17 of 42 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Conceptual Reasoning Index | 51.0 | #64 of 149 | Official leaderboard | |
| ACCoRD | 66.0 | #66 of 150 | Official leaderboard |