# Gemini 2.5 Flash vs GLM-4.6

> GLM-4.6 is the stronger model overall, scoring 41.4 to 39.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-2-5-flash-vs-glm-4-6
- Last updated: 2026-10-11
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 3 categories and GLM-4.6 in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.6 leads 61.1 to 53.8.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 28.7% for Gemini 2.5 Flash and 55.4% for GLM-4.6.
- Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 205K.
- GLM-4.6 has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 2.5 Flash | GLM-4.6 |
|---|---|---|
| Provider | Google | Z.ai (Zhipu) |
| Noometry Index | 39.3 | 41.4 |
| Rank | 170 | 135 |
| Context | 1.05M | 205K |
| Input $/M | $0.30 | $0.60 |
| Output $/M | $2.50 | $2.20 |
| Weights | Proprietary | Open |

## Coding

- Gemini 2.5 Flash: 35.8 (#220)
- GLM-4.6: 40.1 (#148)

| Benchmark | Gemini 2.5 Flash | GLM-4.6 |
|---|---|---|
| SWE-bench Verified (bash only) | 28.7% | 55.4% |
| LMArena Coding | 1424 | 1449 |
| ALE-Bench | 661.88 | 340.82 |
| Aider Polyglot | 55.1% | — |
| LMArena WebDev | — | 1340 |
| SciCode | — | 38.4% |
| WeirdML | 41.9% | — |

## Agentic & Tool Use

- Gemini 2.5 Flash: 30.8 (#74)
- GLM-4.6: 32.3 (#66)

| Benchmark | Gemini 2.5 Flash | GLM-4.6 |
|---|---|---|
| Terminal-Bench | 17.1% | 24.5% |
| Berkeley Function Calling Leaderboard | 56.2% | 72.4% |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
| Vending-Bench 2 | 548.84 | — |

## Reasoning

- Gemini 2.5 Flash: 18.1 (#286)
- GLM-4.6: 23.7 (#172)

| Benchmark | Gemini 2.5 Flash | GLM-4.6 |
|---|---|---|
| Kagi LLM Benchmark | 56.8% | 47.4% |
| CritPt | 1.1% | 1.1% |
| LMArena Hard Prompts | 1422 | 1440 |
| ARC-AGI-2 | 2.5% | — |
| SimpleBench | 41.2% | — |
| ARC-AGI-1 | 33.3% | — |
| EnigmaEval | 2.7% | — |
| DTBench | 76.5% | — |
| LMCA | 27.5% | — |
| Epoch Capabilities Index | 143.03 | — |
| ForecastBench | 60.6 | — |

## Math

- Gemini 2.5 Flash: 39.9 (#98)
- GLM-4.6: 39.1 (#111)

| Benchmark | Gemini 2.5 Flash | GLM-4.6 |
|---|---|---|
| LMArena Math | 1415 | 1432 |
| FrontierMath (Feb 2025 set) | 4.8% | 3.8% |
| FrontierMath Tier 4 (v1) | 4.2% | 2.1% |
| OTIS Mock AIME 2024-2025 | 73.1% | — |
| Omni-MATH | 38.5% | — |

## Knowledge

- Gemini 2.5 Flash: 36.4 (#168)
- GLM-4.6: 40.2 (#124)

| Benchmark | Gemini 2.5 Flash | GLM-4.6 |
|---|---|---|
| Vectara Hallucination Rate | 7.8% | 9.5% |
| LMArena Expert | 1426 | 1431 |
| Humanity's Last Exam | 12.1% | — |
| MMLU-Pro | 63.9% | — |
| Confabulations | 16.8% | — |
| GPQA (HELM) | 39% | — |

## Multimodal

- Gemini 2.5 Flash: 41.8 (#32)
- GLM-4.6: —

| Benchmark | Gemini 2.5 Flash | GLM-4.6 |
|---|---|---|
| LMArena Vision | 1253 | — |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| SpatialViz-Bench | 36.9% | — |

## Multilingual

- Gemini 2.5 Flash: 52.3 (#88)
- GLM-4.6: 53.5 (#66)

| Benchmark | Gemini 2.5 Flash | GLM-4.6 |
|---|---|---|
| LMArena Non-English | 1409 | 1426 |
| LMArena Chinese | 1450 | 1499 |
| LMArena French | 1433 | 1459 |
| LMArena German | 1418 | 1447 |
| LMArena Japanese | 1405 | 1393 |
| LMArena Korean | 1385 | 1400 |
| LMArena Russian | 1415 | 1419 |
| LMArena Spanish | 1421 | 1436 |

## Instruction Following

- Gemini 2.5 Flash: 75.7 (#54)
- GLM-4.6: 74.3 (#98)

| Benchmark | Gemini 2.5 Flash | GLM-4.6 |
|---|---|---|
| LMArena Instruction Following | 1405 | 1410 |
| IFEval | 89.8% | — |

## Long Context

- Gemini 2.5 Flash: 47.5 (#17)
- GLM-4.6: 43.4 (#94)

| Benchmark | Gemini 2.5 Flash | GLM-4.6 |
|---|---|---|
| LMArena Longer Query | 1419 | 1422 |
| Fiction.LiveBench | 77.8% | — |

## Writing & Preference

- Gemini 2.5 Flash: 53.8 (#157)
- GLM-4.6: 61.1 (#90)

| Benchmark | Gemini 2.5 Flash | GLM-4.6 |
|---|---|---|
| LMArena Text | 1417 | 1440 |
| LMArena Creative Writing | 1400 | 1411 |
| EQ-Bench Creative Writing | 1137 | 1411 |
| LMArena Multi-Turn | 1408 | 1427 |
| Short-Story Creative Writing | 76.5% | — |
| WildBench | 81.7% | — |

## FAQ

### Is Gemini 2.5 Flash better than GLM-4.6?

GLM-4.6 is the stronger model overall, scoring 41.4 to 39.3 on the Noometry Index.

### Which is cheaper, Gemini 2.5 Flash or GLM-4.6?

Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; GLM-4.6 lists at $0.60 and $2.20.

### Is Gemini 2.5 Flash or GLM-4.6 better for coding?

GLM-4.6 scores higher on coding benchmarks: 40.1 versus 35.8 in the Noometry coding category.

### Which has the bigger context window?

Gemini 2.5 Flash does, with 1.05M tokens against 205K.

### How many benchmarks do Gemini 2.5 Flash and GLM-4.6 share?

27 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and GLM-4.6 has 29.