Comparing 2 models
Gemini 3.5 Flash vs GLM 5.2
Benchmarks through
Verdict
Gemini 3.5 Flash and GLM 5.2 are not yet ranked on the same task, so compare the specifications below. GLM 5.2 costs 214.3x less per input token. Only GLM 5.2 has open weights for self-hosting.
- Choose GLM 5.2 for you need to self-host.
Built from the published task rankings below; ranks come from each task's own weighted benchmarks, so a win on one task says nothing about another.
Measured head to head
Benchmarks both models were run on
| Evaluation | Gemini 3.5 Flash | GLM 5.2 | Source |
|---|---|---|---|
| Design Arena Coding | 1256 Elo | 1276 Elo | source · 2026-11-15 |
| Design Arena Full-stack Agent | 1170 Elo | 1215 Elo | source · 2026-11-15 |
| Design Arena UI | 1265 Elo | 1286 Elo | source · 2026-11-15 |
| Design Arena Web-app Agent | 1177 Elo | 1200 Elo | source · 2026-11-15 |
| Design Arena Website | 1260 Elo | 1277 Elo | source · 2026-11-15 |
| FrontierMath Tiers 1-3 (Epoch AI) | 62.8% ± 2.9 | 59.2% ± 3 | source · 2026-06-10 |
| GPQA Diamond (Epoch AI) | 88.9% ± 2.2 | 91.9% ± 1.6 | source · 2026-08-06 |
| GPQA Diamond (Epoch AI) | 86.4% ± 2.4 | 91.9% ± 1.6 | source · 2026-07-15 |
| GPQA Diamond (Epoch AI) | 92.8% ± 1.6 | 91.9% ± 1.6 | source · 2026-05-22 |
| LiveBench Agentic Coding | 49.0% | 51.8% | source · 2026-10-18 |
| LiveBench Coding | 78.2% | 79.7% | source · 2026-10-18 |
| LiveBench Data Analysis | 64.9% | 73.7% | source · 2026-10-18 |
| LiveBench Instruction Following | 75.6% | 62.3% | source · 2026-10-18 |
| LiveBench Language | 84.6% | 76.2% | source · 2026-10-18 |
| LiveBench Math | 88.2% | 89.8% | source · 2026-10-18 |
| LiveBench Reasoning | 82% | 78.6% | source · 2026-10-18 |
| LMArena Creative Writing | 1469 Elo | 1459 Elo | source · 2026-11-11 |
| LMArena Instruction Following | 1467 Elo | 1467 Elo | source · 2026-11-11 |
| LMArena Long Query | 1484 Elo | 1479 Elo | source · 2026-11-11 |
| LMArena Math | 1504 Elo | 1483 Elo | source · 2026-11-11 |
| LMArena Text | 1478 Elo | 1475 Elo | source · 2026-11-11 |
| LMArena Text Factuality | 1478 Elo | 1462 Elo | source · 2026-11-11 |
| LMArena WebDev | 1500 Elo | 1608 Elo | source · 2026-11-11 |
| OTIS Mock AIME (Epoch AI) | 88.9% ± 4.7 | 86.4% ± 4.2 | source · 2026-08-06 |
| OTIS Mock AIME (Epoch AI) | 80% ± 6 | 86.4% ± 4.2 | source · 2026-07-15 |
| OTIS Mock AIME (Epoch AI) | 95.6% ± 2.7 | 86.4% ± 4.2 | source · 2026-05-25 |
| SimpleQA Verified (Epoch AI) | 66.2% ± 1.5 | 34.2% ± 1.5 | source · 2026-08-27 |
Values are as published by each evaluator, in its own units; rows from different evaluators are not on a common scale.
task evidence
How they place when the question changes
Lower ranks are better. “Best” marks the strongest option in this shortlist for that task.