# Gemini 3.8 Flash vs GLM-4.6

> Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 41.4 on the Noometry Index. GLM-4.6 costs 1.5× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-3-8-flash-vs-glm-4-6
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 9 categories and GLM-4.6 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 23.7.
- The biggest single-benchmark swing is SciCode: 56.6% for Gemini 3.8 Flash and 38.4% for GLM-4.6.
- GLM-4.6 is cheaper at $0.60 / $2.20 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.8 Flash.
- Gemini 3.8 Flash accepts more context: 1.05M tokens versus 205K.
- GLM-4.6 has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.8 Flash | GLM-4.6 |
|---|---|---|
| Provider | Google | Z.ai (Zhipu) |
| Noometry Index | 61.8 | 41.4 |
| Rank | 11 | 135 |
| Context | 1.05M | 205K |
| Input $/M | $0.75 | $0.60 |
| Output $/M | $3.75 | $2.20 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.8 Flash: 59.2 (#15)
- GLM-4.6: 40.1 (#148)

| Benchmark | Gemini 3.8 Flash | GLM-4.6 |
|---|---|---|
| LMArena WebDev | 1584 | 1340 |
| SciCode | 56.6% | 38.4% |
| LMArena Coding | 1510 | 1449 |
| ALE-Bench | 1,270 | 340.82 |
| DeepSWE | 73.8% | — |
| FrontierCode | 41.2% | — |
| SWE-bench Verified (bash only) | — | 55.4% |
| CursorBench | 39.6% | — |
| FrontierSWE | 19.6% | — |
| WeirdML | 84.8% | — |

## Agentic & Tool Use

- Gemini 3.8 Flash: 41.8 (#21)
- GLM-4.6: 32.3 (#66)

| Benchmark | Gemini 3.8 Flash | GLM-4.6 |
|---|---|---|
| Terminal-Bench | — | 24.5% |
| APEX-Agents | 64.3% | — |
| Berkeley Function Calling Leaderboard | — | 72.4% |
| Remote Labor Index | 5.8% | — |
| GDP.pdf | 23.4% | — |
| Vending-Bench 2 | 5,094 | — |

## Reasoning

- Gemini 3.8 Flash: 76.9 (#5)
- GLM-4.6: 23.7 (#172)

| Benchmark | Gemini 3.8 Flash | GLM-4.6 |
|---|---|---|
| CritPt | 18.3% | 1.1% |
| LMArena Hard Prompts | 1508 | 1440 |
| ARC-AGI-2 | 89.2% | — |
| Kagi LLM Benchmark | — | 47.4% |
| NYT Connections (extended) | 97.4% | — |
| ARC-AGI-1 | 98.5% | — |
| Chess Puzzles | 61% | — |
| Mystery Game Puzzles | 47% | — |
| DTBench | 95.7% | — |
| LMCA | 52.9% | — |
| Surface Evolver Bench | 76.9% | — |
| Epoch Capabilities Index | 156.71 | — |

## Math

- Gemini 3.8 Flash: 65.3 (#28)
- GLM-4.6: 39.1 (#111)

| Benchmark | Gemini 3.8 Flash | GLM-4.6 |
|---|---|---|
| LMArena Math | 1528 | 1432 |
| FrontierMath (Tiers 1-3) | 68.4% | — |
| FrontierMath Tier 4 | 22% | — |
| OTIS Mock AIME 2024-2025 | 98.9% | — |
| ProofBench | 48% | — |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- Gemini 3.8 Flash: 74.8 (#2)
- GLM-4.6: 40.2 (#124)

| Benchmark | Gemini 3.8 Flash | GLM-4.6 |
|---|---|---|
| LMArena Expert | 1524 | 1431 |
| GPQA Diamond | 95.4% | — |
| Humanity's Last Exam | 44.5% | — |
| SimpleQA Verified | 69.7% | — |
| Vectara Hallucination Rate | — | 9.5% |

## Multimodal

- Gemini 3.8 Flash: 40.7 (#45)
- GLM-4.6: —

| Benchmark | Gemini 3.8 Flash | GLM-4.6 |
|---|---|---|
| LMArena Vision | 1314 | — |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 31.7% | — |

## Multilingual

- Gemini 3.8 Flash: 58.0 (#5)
- GLM-4.6: 53.5 (#66)

| Benchmark | Gemini 3.8 Flash | GLM-4.6 |
|---|---|---|
| LMArena Non-English | 1491 | 1426 |
| LMArena Chinese | 1554 | 1499 |
| LMArena French | 1498 | 1459 |
| LMArena German | 1493 | 1447 |
| LMArena Japanese | 1502 | 1393 |
| LMArena Korean | 1459 | 1400 |
| LMArena Russian | 1515 | 1419 |
| LMArena Spanish | 1485 | 1436 |

## Instruction Following

- Gemini 3.8 Flash: 78.0 (#13)
- GLM-4.6: 74.3 (#98)

| Benchmark | Gemini 3.8 Flash | GLM-4.6 |
|---|---|---|
| LMArena Instruction Following | 1490 | 1410 |

## Long Context

- Gemini 3.8 Flash: 46.3 (#24)
- GLM-4.6: 43.4 (#94)

| Benchmark | Gemini 3.8 Flash | GLM-4.6 |
|---|---|---|
| LMArena Longer Query | 1508 | 1422 |

## Writing & Preference

- Gemini 3.8 Flash: 72.2 (#15)
- GLM-4.6: 61.1 (#90)

| Benchmark | Gemini 3.8 Flash | GLM-4.6 |
|---|---|---|
| LMArena Text | 1499 | 1440 |
| LMArena Creative Writing | 1492 | 1411 |
| EQ-Bench Creative Writing | 1748 | 1411 |
| LMArena Multi-Turn | 1501 | 1427 |

## FAQ

### Is Gemini 3.8 Flash better than GLM-4.6?

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 41.4 on the Noometry Index. GLM-4.6 costs 1.5× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.

### Which is cheaper, Gemini 3.8 Flash or GLM-4.6?

GLM-4.6 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Gemini 3.8 Flash lists at $0.75 and $3.75.

### Is Gemini 3.8 Flash or GLM-4.6 better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 40.1 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.8 Flash does, with 1.05M tokens against 205K.

### How many benchmarks do Gemini 3.8 Flash and GLM-4.6 share?

22 benchmarks have published results for both models. Gemini 3.8 Flash has 50 scored results on Noometry and GLM-4.6 has 29.