GPT-5.2 scores 43.5 on the Respan Index (#36), ahead of DeepSeek V4 Flash at 43.3 (#37). GPT-5.2 leads on 11 of the 18 benchmarks both report. DeepSeek V4 Flash has the larger context window (1M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| 46.8% |
| 50.3% |
| LiveBench Coding (LiveBench) | 75% | 76.1% |
| LiveBench Data Analysis (LiveBench) | 79.3% | 78.2% |
| LiveBench Instruction Following (LiveBench) | 65.5% | 61.8% |
| LiveBench Language (LiveBench) | 79.2% | 79.8% |
| LiveBench Mathematics (LiveBench) | 86.8% | 93.2% |
| LiveBench Reasoning (LiveBench) | 86.6% | 83.2% |
| Mystery Game Puzzles (Epoch AI) | 34% | 23% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 94.4% | 96.1% |
| SimpleQA Verified | 33.6% | 37.1% |
| WeirdML (Håvard Tveit Ihle) | 63% | 72.2% |
| LMArena Elo | 1436 | 1412 |
| LMArena WebDev (LMArena) | 1581 | 1416 |
| SimpleBench (SimpleBench) | 61.1% | 45.8% |
Higher is better. Each score links to where it was published.