GLM-5.2 scores 40.1 on the Respan Index (#48), ahead of Gemini 3 Flash Preview at 38.6 (#49). GLM-5.2 leads on 9 of the 14 benchmarks both report. Gemini 3 Flash Preview has the larger context window (1.0M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| Mystery Game Puzzles (Epoch AI) |
| 26% |
| 19% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 95.6% | 86.4% |
| SimpleQA Verified | 68.7% | 34.2% |
| SWE-bench Verified (Epoch AI) | 75.4% | 78.7% |
| Vending-Bench 2 (Andon Labs) | 3634.72 | 8313.78 |
| WeirdML (Håvard Tveit Ihle) | 61.6% | 70.1% |
| LMArena Elo | 1473 | 1476 |
| LMArena WebDev (LMArena) | 1439 | 1605 |
| tau2-bench Banking Knowledge (Sierra) | 27.3% | 37.1% |
| SimpleBench (SimpleBench) | 61.1% | 58.8% |
Higher is better. Each score links to where it was published.