# Gemini 3.8 Flash vs GLM-5.2

> Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 51.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-8-flash-vs-glm-5-2
- Last updated: 2026-10-10
- Shared benchmarks: 42

## Summary

- They share 42 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 9 categories and GLM-5.2 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 42.3.
- The biggest single-benchmark swing is ARC-AGI-2: 89.2% for Gemini 3.8 Flash and 22.8% for GLM-5.2.
- Gemini 3.8 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $1.40 / $4.40 for GLM-5.2.
- Gemini 3.8 Flash accepts more context: 1.05M tokens versus 1M.
- GLM-5.2 has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.8 Flash | GLM-5.2 |
|---|---|---|
| Provider | Google | Z.ai (Zhipu) |
| Noometry Index | 61.8 | 51.1 |
| Rank | 11 | 44 |
| Context | 1.05M | 1M |
| Input $/M | $0.75 | $1.40 |
| Output $/M | $3.75 | $4.40 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.8 Flash: 59.2 (#15)
- GLM-5.2: 51.3 (#41)

| Benchmark | Gemini 3.8 Flash | GLM-5.2 |
|---|---|---|
| DeepSWE | 73.8% | 43.8% |
| FrontierCode | 41.2% | 24.5% |
| LMArena WebDev | 1584 | 1603 |
| SciCode | 56.6% | 50.5% |
| WeirdML | 84.8% | 70.1% |
| LMArena Coding | 1510 | 1485 |
| ALE-Bench | 1,270 | 1,047 |
| SWE-bench Verified | — | 78.7% |
| CursorBench | 39.6% | — |
| FrontierSWE | 19.6% | — |

## Agentic & Tool Use

- Gemini 3.8 Flash: 41.8 (#21)
- GLM-5.2: 32.4 (#63)

| Benchmark | Gemini 3.8 Flash | GLM-5.2 |
|---|---|---|
| APEX-Agents | 64.3% | 45.2% |
| Vending-Bench 2 | 5,094 | 8,314 |
| Remote Labor Index | 5.8% | — |
| τ²-bench Banking | — | 37.1% |
| PostTrainBench | — | 31.7% |
| GBAEval | — | 0% |
| GDP.pdf | 23.4% | — |

## Reasoning

- Gemini 3.8 Flash: 76.9 (#5)
- GLM-5.2: 42.3 (#52)

| Benchmark | Gemini 3.8 Flash | GLM-5.2 |
|---|---|---|
| ARC-AGI-2 | 89.2% | 22.8% |
| NYT Connections (extended) | 97.4% | 74.3% |
| ARC-AGI-1 | 98.5% | 77% |
| CritPt | 18.3% | 20.9% |
| Chess Puzzles | 61% | 21% |
| LMArena Hard Prompts | 1508 | 1480 |
| Mystery Game Puzzles | 47% | 19% |
| DTBench | 95.7% | 93.6% |
| LMCA | 52.9% | 45.8% |
| Surface Evolver Bench | 76.9% | 55.6% |
| Epoch Capabilities Index | 156.71 | 151.78 |
| SimpleBench | — | 58.8% |
| Kagi LLM Benchmark | — | 62.6% |
| EBR-Bench | — | 9.5% |

## Math

- Gemini 3.8 Flash: 65.3 (#28)
- GLM-5.2: 55.7 (#43)

| Benchmark | Gemini 3.8 Flash | GLM-5.2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 68.4% | 59.2% |
| FrontierMath Tier 4 | 22% | 29.3% |
| OTIS Mock AIME 2024-2025 | 98.9% | 86.4% |
| ProofBench | 48% | 35% |
| LMArena Math | 1528 | 1482 |
| MathArena Final-Answer Competitions | — | 67.6% |

## Knowledge

- Gemini 3.8 Flash: 74.8 (#2)
- GLM-5.2: 57.1 (#40)

| Benchmark | Gemini 3.8 Flash | GLM-5.2 |
|---|---|---|
| GPQA Diamond | 95.4% | 91.9% |
| SimpleQA Verified | 69.7% | 34.2% |
| LMArena Expert | 1524 | 1486 |
| Humanity's Last Exam | 44.5% | — |

## Multimodal

- Gemini 3.8 Flash: 40.7 (#45)
- GLM-5.2: —

| Benchmark | Gemini 3.8 Flash | GLM-5.2 |
|---|---|---|
| LMArena Vision | 1314 | — |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 31.7% | — |

## Multilingual

- Gemini 3.8 Flash: 58.0 (#5)
- GLM-5.2: 55.8 (#26)

| Benchmark | Gemini 3.8 Flash | GLM-5.2 |
|---|---|---|
| LMArena Non-English | 1491 | 1459 |
| LMArena Chinese | 1554 | 1519 |
| LMArena French | 1498 | 1479 |
| LMArena German | 1493 | 1468 |
| LMArena Japanese | 1502 | 1451 |
| LMArena Korean | 1459 | 1445 |
| LMArena Russian | 1515 | 1466 |
| LMArena Spanish | 1485 | 1477 |

## Instruction Following

- Gemini 3.8 Flash: 78.0 (#13)
- GLM-5.2: 76.9 (#34)

| Benchmark | Gemini 3.8 Flash | GLM-5.2 |
|---|---|---|
| LMArena Instruction Following | 1490 | 1465 |

## Long Context

- Gemini 3.8 Flash: 46.3 (#24)
- GLM-5.2: 45.3 (#43)

| Benchmark | Gemini 3.8 Flash | GLM-5.2 |
|---|---|---|
| LMArena Longer Query | 1508 | 1479 |

## Writing & Preference

- Gemini 3.8 Flash: 72.2 (#15)
- GLM-5.2: 70.4 (#21)

| Benchmark | Gemini 3.8 Flash | GLM-5.2 |
|---|---|---|
| LMArena Text | 1499 | 1470 |
| LMArena Creative Writing | 1492 | 1462 |
| EQ-Bench Creative Writing | 1748 | 1757 |
| LMArena Multi-Turn | 1501 | 1469 |
| EQ-Bench 4 | — | 1222 |

## FAQ

### Is Gemini 3.8 Flash better than GLM-5.2?

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 51.1 on the Noometry Index.

### Which is cheaper, Gemini 3.8 Flash or GLM-5.2?

Gemini 3.8 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; GLM-5.2 lists at $1.40 and $4.40.

### Is Gemini 3.8 Flash or GLM-5.2 better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 51.3 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.8 Flash does, with 1.05M tokens against 1M.

### How many benchmarks do Gemini 3.8 Flash and GLM-5.2 share?

42 benchmarks have published results for both models. Gemini 3.8 Flash has 50 scored results on Noometry and GLM-5.2 has 51.