# Gemini 2.5 Flash vs GLM-5

> GLM-5 is the stronger model overall, scoring 46.1 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 1.8× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-2-5-flash-vs-glm-5
- Last updated: 2026-10-10
- Shared benchmarks: 33

## Summary

- They share 33 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 2 categories and GLM-5 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5 leads 52.3 to 36.4.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 28.7% for Gemini 2.5 Flash and 72.8% for GLM-5.
- Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $1 / $3.20 for GLM-5.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 205K.
- GLM-5 has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 2.5 Flash | GLM-5 |
|---|---|---|
| Provider | Google | Z.ai (Zhipu) |
| Noometry Index | 39.3 | 46.1 |
| Rank | 170 | 66 |
| Context | 1.05M | 205K |
| Input $/M | $0.30 | $1 |
| Output $/M | $2.50 | $3.20 |
| Weights | Proprietary | Open |

## Coding

- Gemini 2.5 Flash: 35.8 (#220)
- GLM-5: 49.0 (#52)

| Benchmark | Gemini 2.5 Flash | GLM-5 |
|---|---|---|
| SWE-bench Verified (bash only) | 28.7% | 72.8% |
| WeirdML | 41.9% | 48.2% |
| LMArena Coding | 1424 | 1461 |
| ALE-Bench | 661.88 | 765.62 |
| SWE-bench Verified | — | 72.1% |
| Aider Polyglot | 55.1% | — |
| LMArena WebDev | — | 1434 |
| SWE-bench Multilingual | — | 69.7% |

## Agentic & Tool Use

- Gemini 2.5 Flash: 30.8 (#74)
- GLM-5: 31.1 (#71)

| Benchmark | Gemini 2.5 Flash | GLM-5 |
|---|---|---|
| Terminal-Bench | 17.1% | 52.4% |
| Vending-Bench 2 | 548.84 | 4,432 |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 73.7% |
| τ²-bench Telecom | — | 86.8% |
| BALROG | 33.5% | — |

## Reasoning

- Gemini 2.5 Flash: 18.1 (#286)
- GLM-5: 27.6 (#116)

| Benchmark | Gemini 2.5 Flash | GLM-5 |
|---|---|---|
| ARC-AGI-2 | 2.5% | 4.9% |
| SimpleBench | 41.2% | 53.2% |
| Kagi LLM Benchmark | 56.8% | 75% |
| ARC-AGI-1 | 33.3% | 44.7% |
| LMArena Hard Prompts | 1422 | 1452 |
| Epoch Capabilities Index | 143.03 | 145.83 |
| ForecastBench | 60.6 | 61 |
| NYT Connections (extended) | — | 74.8% |
| CritPt | 1.1% | — |
| Chess Puzzles | — | 10% |
| EnigmaEval | 2.7% | — |
| DTBench | 76.5% | — |
| LMCA | 27.5% | — |

## Math

- Gemini 2.5 Flash: 39.9 (#98)
- GLM-5: 46.4 (#71)

| Benchmark | Gemini 2.5 Flash | GLM-5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | 80% |
| LMArena Math | 1415 | 1440 |
| FrontierMath (Feb 2025 set) | 4.8% | 16.4% |
| FrontierMath Tier 4 (v1) | 4.2% | 2.1% |
| MathArena Final-Answer Competitions | — | 65.7% |
| Omni-MATH | 38.5% | — |

## Knowledge

- Gemini 2.5 Flash: 36.4 (#168)
- GLM-5: 52.3 (#64)

| Benchmark | Gemini 2.5 Flash | GLM-5 |
|---|---|---|
| Vectara Hallucination Rate | 7.8% | 10.1% |
| LMArena Expert | 1426 | 1454 |
| GPQA Diamond | — | 87.8% |
| 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-5: —

| Benchmark | Gemini 2.5 Flash | GLM-5 |
|---|---|---|
| LMArena Vision | 1253 | — |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| SpatialViz-Bench | 36.9% | — |

## Multilingual

- Gemini 2.5 Flash: 52.3 (#88)
- GLM-5: 53.7 (#58)

| Benchmark | Gemini 2.5 Flash | GLM-5 |
|---|---|---|
| LMArena Non-English | 1409 | 1430 |
| LMArena Chinese | 1450 | 1511 |
| LMArena French | 1433 | 1455 |
| LMArena German | 1418 | 1445 |
| LMArena Japanese | 1405 | 1416 |
| LMArena Korean | 1385 | 1423 |
| LMArena Russian | 1415 | 1436 |
| LMArena Spanish | 1421 | 1454 |

## Instruction Following

- Gemini 2.5 Flash: 75.7 (#54)
- GLM-5: 75.2 (#67)

| Benchmark | Gemini 2.5 Flash | GLM-5 |
|---|---|---|
| LMArena Instruction Following | 1405 | 1428 |
| IFEval | 89.8% | — |

## Long Context

- Gemini 2.5 Flash: 47.5 (#17)
- GLM-5: 44.7 (#60)

| Benchmark | Gemini 2.5 Flash | GLM-5 |
|---|---|---|
| LMArena Longer Query | 1419 | 1446 |
| Fiction.LiveBench | 77.8% | — |
| CL-bench | — | 18.7% |

## Writing & Preference

- Gemini 2.5 Flash: 53.8 (#157)
- GLM-5: 66.0 (#38)

| Benchmark | Gemini 2.5 Flash | GLM-5 |
|---|---|---|
| LMArena Text | 1417 | 1446 |
| LMArena Creative Writing | 1400 | 1439 |
| EQ-Bench Creative Writing | 1137 | 1601 |
| LMArena Multi-Turn | 1408 | 1456 |
| Short-Story Creative Writing | 76.5% | — |
| WildBench | 81.7% | — |

## FAQ

### Is Gemini 2.5 Flash better than GLM-5?

GLM-5 is the stronger model overall, scoring 46.1 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 1.8× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.

### Which is cheaper, Gemini 2.5 Flash or GLM-5?

Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; GLM-5 lists at $1 and $3.20.

### Is Gemini 2.5 Flash or GLM-5 better for coding?

GLM-5 scores higher on coding benchmarks: 49.0 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-5 share?

33 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and GLM-5 has 45.