# Gemini 3.7 Flash vs GLM-5.1

> Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 47.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-7-flash-vs-glm-5-1
- Last updated: 2026-10-10
- Shared benchmarks: 31

## Summary

- They share 31 benchmarks with published results for both. Gemini 3.7 Flash scores higher in 9 categories and GLM-5.1 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.7 Flash leads 70.1 to 38.2.
- The biggest single-benchmark swing is ProofBench: 58% for Gemini 3.7 Flash and 22.2% for GLM-5.1.
- Gemini 3.7 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- Gemini 3.7 Flash accepts more context: 1.05M tokens versus 200K.
- GLM-5.1 has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.7 Flash | GLM-5.1 |
|---|---|---|
| Provider | Google | Z.ai (Zhipu) |
| Noometry Index | 59.8 | 47.6 |
| Rank | 11 | 51 |
| Context | 1.05M | 200K |
| Input $/M | $0.75 | $1.40 |
| Output $/M | $3.75 | $4.40 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.7 Flash: 55.7 (#19)
- GLM-5.1: 48.5 (#52)

| Benchmark | Gemini 3.7 Flash | GLM-5.1 |
|---|---|---|
| LMArena WebDev | 1593 | 1509 |
| SciCode | 59.8% | 43.8% |
| LMArena Coding | 1499 | 1486 |
| ALE-Bench | 904.3 | 887.1 |
| SWE-bench Verified | — | 74.2% |
| DeepSWE | 65.5% | — |
| FrontierCode | 43.6% | — |
| FrontierSWE | 20.3% | — |
| WeirdML | — | 57.1% |

## Agentic & Tool Use

- Gemini 3.7 Flash: 42.2 (#18)
- GLM-5.1: 24.8 (#106)

| Benchmark | Gemini 3.7 Flash | GLM-5.1 |
|---|---|---|
| APEX-Agents | 67.8% | 40.9% |
| Remote Labor Index | 5% | — |
| ExploitBench | — | 18.1% |
| GBAEval | — | 0% |
| GDP.pdf | 23.8% | — |
| Vending-Bench 2 | — | 5,634 |

## Reasoning

- Gemini 3.7 Flash: 70.1 (#12)
- GLM-5.1: 38.2 (#57)

| Benchmark | Gemini 3.7 Flash | GLM-5.1 |
|---|---|---|
| NYT Connections (extended) | 94% | 77.7% |
| CritPt | 14.3% | 4.6% |
| Chess Puzzles | 47% | 19% |
| LMArena Hard Prompts | 1497 | 1472 |
| Epoch Capabilities Index | 157.72 | 149.86 |
| ARC-AGI-2 | 84.6% | — |
| SimpleBench | — | 55.1% |
| ARC-AGI-1 | 95.5% | — |
| Thematic Generalization | — | 69.8% |
| Mystery Game Puzzles | 37% | — |
| DTBench | 96.8% | — |
| LMCA | 50.4% | — |

## Math

- Gemini 3.7 Flash: 69.5 (#18)
- GLM-5.1: 49.0 (#48)

| Benchmark | Gemini 3.7 Flash | GLM-5.1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 71.6% | 36.8% |
| OTIS Mock AIME 2024-2025 | 97.2% | 93.3% |
| ProofBench | 58% | 22.2% |
| LMArena Math | 1511 | 1472 |
| FrontierMath Tier 4 | 36.6% | — |
| MathArena Final-Answer Competitions | — | 67.1% |
| FrontierMath (Feb 2025 set) | — | 33.4% |
| FrontierMath Tier 4 (v1) | — | 12.5% |

## Knowledge

- Gemini 3.7 Flash: 69.8 (#4)
- GLM-5.1: 55.0 (#45)

| Benchmark | Gemini 3.7 Flash | GLM-5.1 |
|---|---|---|
| GPQA Diamond | 94.8% | 89.9% |
| SimpleQA Verified | 69.2% | 34% |
| LMArena Expert | 1508 | 1477 |

## Multimodal

- Gemini 3.7 Flash: 36.9 (#69)
- GLM-5.1: —

| Benchmark | Gemini 3.7 Flash | GLM-5.1 |
|---|---|---|
| LMArena Vision | 1314 | — |
| Furniture Assembly | 26.7% | — |

## Multilingual

- Gemini 3.7 Flash: 57.8 (#7)
- GLM-5.1: 55.2 (#34)

| Benchmark | Gemini 3.7 Flash | GLM-5.1 |
|---|---|---|
| LMArena Non-English | 1485 | 1448 |
| LMArena Chinese | 1553 | 1516 |
| LMArena French | 1512 | 1478 |
| LMArena German | 1485 | 1466 |
| LMArena Japanese | 1506 | 1436 |
| LMArena Korean | 1486 | 1423 |
| LMArena Russian | 1519 | 1453 |
| LMArena Spanish | 1507 | 1467 |

## Instruction Following

- Gemini 3.7 Flash: 78.0 (#12)
- GLM-5.1: 76.5 (#41)

| Benchmark | Gemini 3.7 Flash | GLM-5.1 |
|---|---|---|
| LMArena Instruction Following | 1486 | 1451 |

## Long Context

- Gemini 3.7 Flash: 45.8 (#28)
- GLM-5.1: 44.9 (#51)

| Benchmark | Gemini 3.7 Flash | GLM-5.1 |
|---|---|---|
| LMArena Longer Query | 1493 | 1467 |

## Writing & Preference

- Gemini 3.7 Flash: 71.4 (#19)
- GLM-5.1: 67.2 (#29)

| Benchmark | Gemini 3.7 Flash | GLM-5.1 |
|---|---|---|
| LMArena Text | 1487 | 1462 |
| LMArena Creative Writing | 1490 | 1454 |
| EQ-Bench Creative Writing | 1723 | 1592 |
| LMArena Multi-Turn | 1495 | 1473 |

## FAQ

### Is Gemini 3.7 Flash better than GLM-5.1?

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 47.6 on the Noometry Index.

### Which is cheaper, Gemini 3.7 Flash or GLM-5.1?

Gemini 3.7 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.

### Is Gemini 3.7 Flash or GLM-5.1 better for coding?

Gemini 3.7 Flash scores higher on coding benchmarks: 55.7 versus 48.5 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.7 Flash does, with 1.05M tokens against 200K.

### How many benchmarks do Gemini 3.7 Flash and GLM-5.1 share?

31 benchmarks have published results for both models. Gemini 3.7 Flash has 44 scored results on Noometry and GLM-5.1 has 41.