# GLM-4.5V vs GPT-6 Luna

> GPT-6 Luna is the stronger model overall, scoring 53.3 to 39.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-5v-vs-gpt-6-luna
- Last updated: 2026-10-12
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. GLM-4.5V scores higher in 0 categories and GPT-6 Luna in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Luna leads 76.1 to 37.4.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.60 / $1.80 for GLM-4.5V.
- GPT-6 Luna accepts more context: 1.05M tokens versus 64K.
- GLM-4.5V has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-4.5V | GPT-6 Luna |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 39.8 | 53.3 |
| Rank | 158 | 36 |
| Context | 64K | 1.05M |
| Input $/M | $0.60 | $0.10 |
| Output $/M | $1.80 | $0.50 |
| Weights | Open | Proprietary |

## Coding

- GLM-4.5V: 39.5 (#155)
- GPT-6 Luna: 55.5 (#25)

| Benchmark | GLM-4.5V | GPT-6 Luna |
|---|---|---|
| LMArena Coding | 1347 | 1439 |
| DeepSWE | — | 66.6% |
| FrontierCode | — | 42.4% |
| LMArena WebDev | — | 1581 |
| SciCode | — | 54.6% |
| ALE-Bench | — | 1,577 |

## Agentic & Tool Use

- GLM-4.5V: —
- GPT-6 Luna: 33.3 (#54)

| Benchmark | GLM-4.5V | GPT-6 Luna |
|---|---|---|
| APEX-Agents | — | 44.3% |
| GDP.pdf | — | 23% |

## Reasoning

- GLM-4.5V: 27.4 (#119)
- GPT-6 Luna: 48.2 (#41)

| Benchmark | GLM-4.5V | GPT-6 Luna |
|---|---|---|
| LMArena Hard Prompts | 1334 | 1411 |
| ARC-AGI-2 | — | 59.3% |
| Kagi LLM Benchmark | 59.8% | — |
| NYT Connections (extended) | — | 68.7% |
| ARC-AGI-1 | — | 86.7% |
| CritPt | — | 19.4% |
| Chess Puzzles | — | 31% |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 90.1% |
| LMCA | — | 44.5% |
| Epoch Capabilities Index | — | 156.28 |

## Math

- GLM-4.5V: 37.4 (#159)
- GPT-6 Luna: 76.1 (#15)

| Benchmark | GLM-4.5V | GPT-6 Luna |
|---|---|---|
| LMArena Math | 1354 | 1416 |
| FrontierMath (Tiers 1-3) | — | 78.9% |
| FrontierMath Tier 4 | — | 56.1% |
| OTIS Mock AIME 2024-2025 | — | 98.9% |
| ProofBench | — | 64% |

## Knowledge

- GLM-4.5V: 37.5 (#156)
- GPT-6 Luna: 57.0 (#41)

| Benchmark | GLM-4.5V | GPT-6 Luna |
|---|---|---|
| LMArena Expert | 1353 | 1444 |
| GPQA Diamond | — | 90.5% |
| SimpleQA Verified | — | 41.4% |

## Multimodal

- GLM-4.5V: 34.3 (#92)
- GPT-6 Luna: 42.4 (#30)

| Benchmark | GLM-4.5V | GPT-6 Luna |
|---|---|---|
| LMArena Vision | 1154 | 1217 |
| Blueprint-Bench 2 | — | 31.2% |
| Furniture Assembly | — | 44.2% |

## Multilingual

- GLM-4.5V: 44.6 (#177)
- GPT-6 Luna: 50.5 (#117)

| Benchmark | GLM-4.5V | GPT-6 Luna |
|---|---|---|
| LMArena Non-English | 1303 | 1386 |
| LMArena Chinese | 1337 | 1433 |
| LMArena Russian | 1298 | 1394 |
| LMArena Spanish | 1336 | 1393 |
| LMArena French | — | 1420 |
| LMArena German | — | 1369 |
| LMArena Japanese | — | 1369 |
| LMArena Korean | — | 1360 |

## Instruction Following

- GLM-4.5V: 69.2 (#175)
- GPT-6 Luna: 74.3 (#99)

| Benchmark | GLM-4.5V | GPT-6 Luna |
|---|---|---|
| LMArena Instruction Following | 1311 | 1409 |

## Long Context

- GLM-4.5V: 39.6 (#171)
- GPT-6 Luna: 43.0 (#111)

| Benchmark | GLM-4.5V | GPT-6 Luna |
|---|---|---|
| LMArena Longer Query | 1304 | 1409 |

## Writing & Preference

- GLM-4.5V: 52.5 (#170)
- GPT-6 Luna: 58.3 (#119)

| Benchmark | GLM-4.5V | GPT-6 Luna |
|---|---|---|
| LMArena Text | 1333 | 1391 |
| LMArena Creative Writing | 1295 | 1363 |
| LMArena Multi-Turn | 1332 | 1396 |

## FAQ

### Is GLM-4.5V better than GPT-6 Luna?

GPT-6 Luna is the stronger model overall, scoring 53.3 to 39.8 on the Noometry Index.

### Which is cheaper, GLM-4.5V or GPT-6 Luna?

GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; GLM-4.5V lists at $0.60 and $1.80.

### Is GLM-4.5V or GPT-6 Luna better for coding?

GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 39.5 in the Noometry coding category.

### Which has the bigger context window?

GPT-6 Luna does, with 1.05M tokens against 64K.

### How many benchmarks do GLM-4.5V and GPT-6 Luna share?

14 benchmarks have published results for both models. GLM-4.5V has 15 scored results on Noometry and GPT-6 Luna has 42.