Gemini 3 Pro vs GLM-5.2
Gemini 3 Pro 
GLM-5.2 Verdict
- GLM-5.2 (max) leads on quality: 63.9 vs 61.1.
- Gemini 3 Pro is stronger in human preference, knowledge, multimodal.
- GLM-5.2 (max) is stronger in agents & tools, coding, instruction following, maths, reasoning, composite, long context.
- GLM-5.2 (max) is 2.1× cheaper ($2.15 vs $4.50 per 1M blended).
| Metric | Gemini 3 Pro | GLM-5.2 (max) |
|---|---|---|
| BenchLeader Index | 61.1 | 63.9 |
| Agents & tools score | 61.4 | 63.8 |
| Coding score | 58.8 | 63.8 |
| Human preference score | 68.8 | 67.2 |
| Instruction following score | 61.9 | 71.6 |
| Knowledge score | 56.5 | 55.5 |
| Maths score | 54.8 | 59.0 |
| Multimodal score | 66.0 | – |
| Reasoning score | 67.1 | 72.9 |
| Composite score | – | 72.1 |
| Long context score | – | 65.6 |
| Blended price $/M | $4.50 | $2.15 |
| Output speed | – | 71 tok/s |
| Time to first answer | – | 31.6 s |
| Context window | 1.0M | 1M |
| GPQA Diamond | 92.6% | 91.9% |
| FrontierMath Tiers 1–3 | – | 59.2% |
| FrontierMath Tier 4 | – | 29.3% |
| OTIS Mock AIME | 91.4% | 86.4% |
| SWE-bench Verified (Epoch) | 72.9% | 78.7% |
| SimpleQA Verified | – | 34.2% |
| Humanity's Last Exam | 37.5% | – |
| Terminal-Bench | 69.4% | – |
| SimpleBench | 76.4% | – |
| GDPval | 40.3% | – |
| SciCode | – | 50.5% |
| Remote Labor Index | 1.3% | – |
| WeirdML | 69.9% | 70.1% |
| APEX-Agents | 31.5% | – |
| ProofBench | 20.0% | 35.0% |
| GSO-Bench | 18.6% | – |
| Epoch Capabilities Index | 153 | – |
| LMArena Text | 1486 | 1472 |
| LMArena Hard Prompts | 1504 | 1493 |
| LMArena Coding | 1518 | 1510 |
| LMArena WebDev | 1439 | 1592 |
| LMArena Vision | 1304 | – |
| LMArena Agent | – | 4.4 |
| AA Intelligence Index | – | 34.0 |
| IFBench | – | 73.3% |
| AA-LCR | – | 78.3% |
| AA-Omniscience | – | 4.4 |
| Terminal-Bench Hard | – | 50.8% |
| GPQA Diamond (AA) | – | 89.5% |
| Humanity's Last Exam (AA) | – | 41.1% |
| SciCode (AA) | – | 51.2% |
| τ²-Bench Telecom (AA) | – | 99.1% |
| LiveCodeBench | 86.4% | – |
| MMLU-Pro | 90.1% | – |
| Terminal-Bench 2.1 (Vals) | – | 67.8% |
| SWE-bench (Vals) | – | 82.8% |
| AIME 2026 | 91.7% | – |
| HMMT February 2026 | 86.4% | – |
| MathArena Apex | 23.4% | – |
| SWE-Bench Pro | 43.3% | – |
| MCP Atlas | 70.3% | – |
| MultiChallenge | 65.7% | – |
| PRBench Finance | 39.2% | – |
| PRBench Legal | 40.6% | – |
| VISTA | 51.5% | – |
| MultiNRC | 59.0% | – |
| TutorBench | 53.7% | – |
| MMMU-Pro (official) | 81.0% | – |
| Kagi LLM Benchmark | 80.1% | – |
| IFEval (HELM) | 87.6% | – |
| Omni-MATH (HELM) | 55.6% | – |
| WildBench (HELM) | 85.9% | – |
| MMLU-Pro (HELM) | 90.3% | – |
| GPQA Diamond (HELM) | 80.3% | – |
| HELM Capabilities mean | 79.9% | – |
| SWE-bench Verified (bash only) | 74.2% | – |
| SWE-bench Verified (any scaffold) | 77.4% | – |
| ARC-AGI-1 | 75.0% | – |
| ARC-AGI-2 | 54.0% | – |
| BFCL Overall | 72.5% | – |
| CritPt | – | 20.9% |
| GDPval (AA) | – | 45.3% |
| τ²-Bench Banking (AA) | – | 34.6% |
| ITBench SRE (AA) | – | 42.7% |
| APEX-Agents (AA) | – | 33.7% |
| Code Migration | – | 37.9% |
| Harvey's Legal Agent Benchmark | – | 7.1% |
| Legal Research Bench | – | 31.3% |
| Poker Agent | 1078.9% | – |
| ProgramBench | – | 0.5% |
| SkillsBench | – | 45.1% |
| SREBench | – | 0.0% |
| Vibe Code Bench v1.1 | – | 64.0% |
| FORTRESS | 41.7% | – |
| MASK | 42.6% | – |
| PropensityBench | 52.9% | – |
| SciPredict | 25.3% | – |
| SWE-Bench Pro (private) | 17.9% | – |
| VTB | 26.9% | – |
| LMArena Maths | 1477 | 1480 |
| LMArena Creative Writing | 1483 | 1451 |
| LMArena Instruction Following | 1473 | 1466 |
| LMArena Multi-turn | 1495 | 1469 |
| LMArena Longer Queries | 1491 | 1483 |
| LMArena Document | 1451 | – |
| Chess Puzzles | 31.0% | 21.0% |
| EBR-bench | – | 9.5% |
| BALROG | 58.1% | – |
| GeoBench | 84.0% | – |
| VPCT | 91.0% | – |
| PostTrainBench | – | 31.7% |
| CL-bench | 15.8% | – |
| METR Time Horizons | 71.0% | – |
| DeepSWE | – | 43.8% |
| LMCA | – | 45.8% |
| DTBench | – | 93.6% |
| ForecastBench | 61.2% | – |
| CursorBench | – | 55.0% |
| ALE-Bench | 1176.8 | 1010.2 |
| AlgoTune | 1.8 | – |
| Vending-Bench 2 | 5478.2 | – |
Data as of 2026-09-19. Best configuration of each model; every score links to its source on the model pages.
Gemini 3 Pro vs GLM-5.2: questions
- Is Gemini 3 Pro better than GLM-5.2?
- GLM-5.2 (max) leads on quality: 63.9 vs 61.1. The BenchLeader Index combines every independent quality benchmark; GLM-5.2 (max) is ahead overall as of 2026-09-19, but check the category scores for your use.
- Is Gemini 3 Pro better than GLM-5.2 for coding?
- GLM-5.2 scores higher in coding (64 vs 59 on the category index, where 50 is average).
- Is Gemini 3 Pro better than GLM-5.2 for agentic tasks?
- GLM-5.2 scores higher in agentic tasks (64 vs 61 on the category index, where 50 is average).
- Which is cheaper, Gemini 3 Pro or GLM-5.2?
- GLM-5.2 is cheaper: $2.15 against $4.50 per million tokens, blended at three input tokens per output token.
- Which has the larger context window?
- Gemini 3 Pro accepts more context: 1.0M against 1M tokens.