# GLM-4.6V vs GPT-4.1

> GLM-4.6V is the stronger model overall, scoring 41.3 to 35.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-6v-vs-gpt-4-1
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. GLM-4.6V scores higher in 5 categories and GPT-4.1 in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-4.6V leads 27.6 to 11.7.
- GLM-4.6V is cheaper at $0.30 / $0.90 per million input/output tokens, against $2 / $8 for GPT-4.1.
- GPT-4.1 accepts more context: 1.05M tokens versus 128K.
- GLM-4.6V has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-4.6V | GPT-4.1 |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 41.3 | 35.9 |
| Rank | 137 | 219 |
| Context | 128K | 1.05M |
| Input $/M | $0.30 | $2 |
| Output $/M | $0.90 | $8 |
| Weights | Open | Proprietary |

## Coding

- GLM-4.6V: 40.9 (#128)
- GPT-4.1: 34.4 (#238)

| Benchmark | GLM-4.6V | GPT-4.1 |
|---|---|---|
| LMArena Coding | 1390 | 1391 |
| SWE-bench Verified | — | 48.5% |
| SWE-bench Verified (bash only) | — | 39.6% |
| Aider Polyglot | — | 52.4% |
| WeirdML | — | 39% |
| CadEval | — | 42% |
| ALE-Bench | — | 558.1 |

## Agentic & Tool Use

- GLM-4.6V: —
- GPT-4.1: 34.7 (#43)

| Benchmark | GLM-4.6V | GPT-4.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 54% |

## Reasoning

- GLM-4.6V: 27.6 (#115)
- GPT-4.1: 11.7 (#339)

| Benchmark | GLM-4.6V | GPT-4.1 |
|---|---|---|
| LMArena Hard Prompts | 1368 | 1384 |
| ARC-AGI-2 | — | 0.4% |
| SimpleBench | — | 27% |
| Kagi LLM Benchmark | — | 52.3% |
| ARC-AGI-1 | — | 5.5% |
| Chess Puzzles | — | 6% |
| EnigmaEval | — | 2.2% |
| DTBench | — | 68.3% |
| LMCA | — | 25.6% |
| Epoch Capabilities Index | — | 136.78 |
| ForecastBench | — | 61.5 |

## Math

- GLM-4.6V: —
- GPT-4.1: 22.3 (#280)

| Benchmark | GLM-4.6V | GPT-4.1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 6% |
| OTIS Mock AIME 2024-2025 | — | 38.3% |
| Omni-MATH | — | 47.1% |
| LMArena Math | — | 1370 |
| MATH Level 5 | — | 83% |
| FrontierMath (Feb 2025 set) | — | 5.5% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- GLM-4.6V: 38.0 (#149)
- GPT-4.1: 37.1 (#160)

| Benchmark | GLM-4.6V | GPT-4.1 |
|---|---|---|
| LMArena Expert | 1371 | 1364 |
| GPQA Diamond | — | 66.9% |
| Humanity's Last Exam | — | 5.4% |
| SimpleQA Verified | — | 31.1% |
| MMLU-Pro | — | 81.1% |
| Vectara Hallucination Rate | — | 5.6% |
| GPQA (HELM) | — | 65.9% |

## Multimodal

- GLM-4.6V: 34.8 (#90)
- GPT-4.1: 38.2 (#67)

| Benchmark | GLM-4.6V | GPT-4.1 |
|---|---|---|
| LMArena Vision | 1164 | 1211 |
| GeoBench | — | 72% |

## Multilingual

- GLM-4.6V: 48.6 (#141)
- GPT-4.1: 49.4 (#133)

| Benchmark | GLM-4.6V | GPT-4.1 |
|---|---|---|
| LMArena Non-English | 1359 | 1370 |
| LMArena Chinese | 1425 | 1382 |
| LMArena Russian | 1340 | 1377 |
| LMArena French | — | 1382 |
| LMArena German | — | 1381 |
| LMArena Japanese | — | 1319 |
| LMArena Korean | — | 1339 |
| LMArena Spanish | — | 1376 |

## Instruction Following

- GLM-4.6V: 71.4 (#151)
- GPT-4.1: 71.3 (#153)

| Benchmark | GLM-4.6V | GPT-4.1 |
|---|---|---|
| LMArena Instruction Following | 1352 | 1367 |
| IFEval | — | 83.8% |

## Long Context

- GLM-4.6V: 41.3 (#143)
- GPT-4.1: 40.0 (#163)

| Benchmark | GLM-4.6V | GPT-4.1 |
|---|---|---|
| LMArena Longer Query | 1358 | 1385 |
| Fiction.LiveBench | — | 63.9% |

## Writing & Preference

- GLM-4.6V: 56.6 (#137)
- GPT-4.1: 57.6 (#125)

| Benchmark | GLM-4.6V | GPT-4.1 |
|---|---|---|
| LMArena Text | 1377 | 1383 |
| LMArena Creative Writing | 1347 | 1363 |
| LMArena Multi-Turn | 1360 | 1398 |
| EQ-Bench Creative Writing | — | 1420 |
| WildBench | — | 85.4% |

## FAQ

### Is GLM-4.6V better than GPT-4.1?

GLM-4.6V is the stronger model overall, scoring 41.3 to 35.9 on the Noometry Index.

### Which is cheaper, GLM-4.6V or GPT-4.1?

GLM-4.6V is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; GPT-4.1 lists at $2 and $8.

### Is GLM-4.6V or GPT-4.1 better for coding?

GLM-4.6V scores higher on coding benchmarks: 40.9 versus 34.4 in the Noometry coding category.

### Which has the bigger context window?

GPT-4.1 does, with 1.05M tokens against 128K.

### How many benchmarks do GLM-4.6V and GPT-4.1 share?

12 benchmarks have published results for both models. GLM-4.6V has 12 scored results on Noometry and GPT-4.1 has 52.