# Gemini 2.5 Pro vs GLM-5.2

> GLM-5.2 is the stronger model overall, scoring 51.1 to 45.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-2-5-pro-vs-glm-5-2
- Last updated: 2026-10-10
- Shared benchmarks: 38

## Summary

- They share 38 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 1 category and GLM-5.2 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.2 leads 55.7 to 32.5.
- The biggest single-benchmark swing is ARC-AGI-1: 41% for Gemini 2.5 Pro and 77% for GLM-5.2.
- GLM-5.2 is cheaper at $1.40 / $4.40 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.
- Gemini 2.5 Pro accepts more context: 1.05M tokens versus 1M.
- GLM-5.2 has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 2.5 Pro | GLM-5.2 |
|---|---|---|
| Provider | Google | Z.ai (Zhipu) |
| Noometry Index | 45.0 | 51.1 |
| Rank | 75 | 44 |
| Context | 1.05M | 1M |
| Input $/M | $1.25 | $1.40 |
| Output $/M | $10 | $4.40 |
| Weights | Proprietary | Open |

## Coding

- Gemini 2.5 Pro: 42.4 (#101)
- GLM-5.2: 51.3 (#41)

| Benchmark | Gemini 2.5 Pro | GLM-5.2 |
|---|---|---|
| SWE-bench Verified | 57.6% | 78.7% |
| LMArena WebDev | 1227 | 1603 |
| SciCode | 42.8% | 50.5% |
| WeirdML | 54% | 70.1% |
| LMArena Coding | 1452 | 1485 |
| ALE-Bench | 785.52 | 1,047 |
| DeepSWE | — | 43.8% |
| FrontierCode | — | 24.5% |
| SWE-bench Verified (bash only) | 53.6% | — |
| Aider Polyglot | 83.1% | — |
| GSO | 3.9% | — |
| LiveBench Coding | 85.9% | — |
| CadEval | 64% | — |
| AlgoTune | 1.51 | — |

## Agentic & Tool Use

- Gemini 2.5 Pro: 29.2 (#88)
- GLM-5.2: 32.4 (#63)

| Benchmark | Gemini 2.5 Pro | GLM-5.2 |
|---|---|---|
| τ²-bench Banking | 13.7% | 37.1% |
| Vending-Bench 2 | 573.64 | 8,314 |
| Terminal-Bench | 32.6% | — |
| APEX-Agents | — | 45.2% |
| GDPval | 23.3% | — |
| Remote Labor Index | 0.8% | — |
| TheAgentCompany | 30.3% | — |
| DeepResearch Bench | 42.8% | — |
| PostTrainBench | — | 31.7% |
| BALROG | 43.3% | — |
| GBAEval | — | 0% |
| LMArena Search | 1142 | — |
| METR Time Horizons | 55.4% | — |

## Reasoning

- Gemini 2.5 Pro: 28.8 (#99)
- GLM-5.2: 42.3 (#52)

| Benchmark | Gemini 2.5 Pro | GLM-5.2 |
|---|---|---|
| ARC-AGI-2 | 4.9% | 22.8% |
| SimpleBench | 62.4% | 58.8% |
| Kagi LLM Benchmark | 70.3% | 62.6% |
| ARC-AGI-1 | 41% | 77% |
| CritPt | 2% | 20.9% |
| Chess Puzzles | 20% | 21% |
| LMArena Hard Prompts | 1455 | 1480 |
| DTBench | 82.4% | 93.6% |
| LMCA | 34.8% | 45.8% |
| Epoch Capabilities Index | 145.32 | 151.78 |
| NYT Connections (extended) | — | 74.3% |
| EnigmaEval | 5.6% | — |
| EBR-Bench | — | 9.5% |
| LiveBench Reasoning | 89.8% | — |
| Mystery Game Puzzles | — | 19% |
| LiveBench Data Analysis | 79.9% | — |
| Surface Evolver Bench | — | 55.6% |
| ForecastBench | 61.3 | — |
| LiveBench | 82.3% | — |

## Math

- Gemini 2.5 Pro: 32.5 (#213)
- GLM-5.2: 55.7 (#43)

| Benchmark | Gemini 2.5 Pro | GLM-5.2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 24.6% | 59.2% |
| FrontierMath Tier 4 | 0% | 29.3% |
| OTIS Mock AIME 2024-2025 | 84.7% | 86.4% |
| LMArena Math | 1450 | 1482 |
| MathArena Final-Answer Competitions | — | 67.6% |
| ProofBench | — | 35% |
| Omni-MATH | 41.6% | — |
| LiveBench Math | 90.2% | — |
| MATH Level 5 | 95.9% | — |
| FrontierMath (Feb 2025 set) | 14.1% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Gemini 2.5 Pro: 56.0 (#46)
- GLM-5.2: 57.1 (#40)

| Benchmark | Gemini 2.5 Pro | GLM-5.2 |
|---|---|---|
| GPQA Diamond | 85.3% | 91.9% |
| LMArena Expert | 1452 | 1486 |
| Humanity's Last Exam | 21.6% | — |
| SimpleQA Verified | — | 34.2% |
| MMLU-Pro | 86.3% | — |
| Confabulations | 10.6% | — |
| Vectara Hallucination Rate | 7% | — |
| GPQA (HELM) | 74.9% | — |

## Multimodal

- Gemini 2.5 Pro: 45.2 (#18)
- GLM-5.2: —

| Benchmark | Gemini 2.5 Pro | GLM-5.2 |
|---|---|---|
| LMArena Vision | 1263 | — |
| GeoBench | 86% | — |
| VPCT | 48% | — |
| LMArena Document | 1421 | — |
| SpatialViz-Bench | 44.7% | — |

## Multilingual

- Gemini 2.5 Pro: 55.3 (#31)
- GLM-5.2: 55.8 (#26)

| Benchmark | Gemini 2.5 Pro | GLM-5.2 |
|---|---|---|
| LMArena Non-English | 1451 | 1459 |
| LMArena Chinese | 1507 | 1519 |
| LMArena French | 1472 | 1479 |
| LMArena German | 1487 | 1468 |
| LMArena Japanese | 1461 | 1451 |
| LMArena Korean | 1434 | 1445 |
| LMArena Russian | 1461 | 1466 |
| LMArena Spanish | 1473 | 1477 |

## Instruction Following

- Gemini 2.5 Pro: 75.0 (#75)
- GLM-5.2: 76.9 (#34)

| Benchmark | Gemini 2.5 Pro | GLM-5.2 |
|---|---|---|
| LMArena Instruction Following | 1437 | 1465 |
| LiveBench Instruction Following | 80.6% | — |
| IFEval | 84% | — |

## Long Context

- Gemini 2.5 Pro: 59.8 (#5)
- GLM-5.2: 45.3 (#43)

| Benchmark | Gemini 2.5 Pro | GLM-5.2 |
|---|---|---|
| LMArena Longer Query | 1449 | 1479 |
| Fiction.LiveBench | 91.7% | — |

## Writing & Preference

- Gemini 2.5 Pro: 63.7 (#62)
- GLM-5.2: 70.4 (#21)

| Benchmark | Gemini 2.5 Pro | GLM-5.2 |
|---|---|---|
| LMArena Text | 1458 | 1470 |
| LMArena Creative Writing | 1454 | 1462 |
| EQ-Bench Creative Writing | 1421 | 1757 |
| LMArena Multi-Turn | 1453 | 1469 |
| Short-Story Creative Writing | 83.8% | — |
| WildBench | 85.7% | — |
| EQ-Bench 4 | — | 1222 |
| LiveBench Language | 67.8% | — |

## FAQ

### Is Gemini 2.5 Pro better than GLM-5.2?

GLM-5.2 is the stronger model overall, scoring 51.1 to 45.0 on the Noometry Index.

### Which is cheaper, Gemini 2.5 Pro or GLM-5.2?

GLM-5.2 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.

### Is Gemini 2.5 Pro or GLM-5.2 better for coding?

GLM-5.2 scores higher on coding benchmarks: 51.3 versus 42.4 in the Noometry coding category.

### Which has the bigger context window?

Gemini 2.5 Pro does, with 1.05M tokens against 1M.

### How many benchmarks do Gemini 2.5 Pro and GLM-5.2 share?

38 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and GLM-5.2 has 51.