# GLM-4.6 vs GPT-4.1 mini

> GLM-4.6 is the stronger model overall, scoring 40.9 to 33.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-6-vs-gpt-4-1-mini
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. GLM-4.6 scores higher in 8 categories and GPT-4.1 mini in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.6 leads 36.4 to 23.1.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 55.4% for GLM-4.6 and 23.9% for GPT-4.1 mini.
- GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
- GPT-4.1 mini accepts more context: 1.05M tokens versus 205K.
- GLM-4.6 has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-4.6 | GPT-4.1 mini |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 40.9 | 33.5 |
| Rank | 132 | 232 |
| Context | 205K | 1.05M |
| Input $/M | $0.60 | $0.40 |
| Output $/M | $2.20 | $1.60 |
| Weights | Open | Proprietary |

## Coding

- GLM-4.6: 39.9 (#137)
- GPT-4.1 mini: 30.4 (#286)

| Benchmark | GLM-4.6 | GPT-4.1 mini |
|---|---|---|
| SWE-bench Verified (bash only) | 55.4% | 23.9% |
| SciCode | 38.4% | 40.4% |
| LMArena Coding | 1449 | 1367 |
| Aider Polyglot | — | 32.4% |
| LMArena WebDev | 1339 | — |
| WeirdML | — | 37.6% |
| BigCodeBench Instruct | — | 48.9% |
| CadEval | — | 16% |
| ALE-Bench | 340.82 | — |

## Agentic & Tool Use

- GLM-4.6: 32.1 (#60)
- GPT-4.1 mini: 33.0 (#52)

| Benchmark | GLM-4.6 | GPT-4.1 mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 72.4% | 50.5% |
| Terminal-Bench | 24.5% | — |

## Reasoning

- GLM-4.6: 23.1 (#168)
- GPT-4.1 mini: 10.9 (#335)

| Benchmark | GLM-4.6 | GPT-4.1 mini |
|---|---|---|
| Kagi LLM Benchmark | 47.4% | 48.6% |
| CritPt | 1.1% | 0% |
| LMArena Hard Prompts | 1440 | 1349 |
| ARC-AGI-2 | — | 0% |
| ARC-AGI-1 | — | 3.5% |
| Chess Puzzles | — | 7% |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 68.8% |
| LMCA | — | 21.1% |
| Epoch Capabilities Index | — | 135.01 |

## Math

- GLM-4.6: 36.4 (#115)
- GPT-4.1 mini: 23.1 (#264)

| Benchmark | GLM-4.6 | GPT-4.1 mini |
|---|---|---|
| LMArena Math | 1431 | 1343 |
| FrontierMath (Feb 2025 set) | 3.8% | 4.5% |
| FrontierMath (Tiers 1-3) | — | 6.7% |
| OTIS Mock AIME 2024-2025 | — | 44.7% |
| Omni-MATH | — | 49.1% |
| MATH Level 5 | — | 87.3% |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GLM-4.6: 39.6 (#118)
- GPT-4.1 mini: 34.7 (#183)

| Benchmark | GLM-4.6 | GPT-4.1 mini |
|---|---|---|
| LMArena Expert | 1432 | 1338 |
| GPQA Diamond | — | 65.8% |
| SimpleQA Verified | — | 12.7% |
| MMLU-Pro | — | 78.3% |
| Vectara Hallucination Rate | 9.5% | — |
| GPQA (HELM) | — | 61.4% |

## Multimodal

- GLM-4.6: —
- GPT-4.1 mini: 35.2 (#77)

| Benchmark | GLM-4.6 | GPT-4.1 mini |
|---|---|---|
| LMArena Vision | — | 1181 |

## Multilingual

- GLM-4.6: 53.6 (#62)
- GPT-4.1 mini: 45.9 (#161)

| Benchmark | GLM-4.6 | GPT-4.1 mini |
|---|---|---|
| LMArena Non-English | 1426 | 1318 |
| LMArena Chinese | 1500 | 1329 |
| LMArena French | 1459 | 1357 |
| LMArena German | 1447 | 1349 |
| LMArena Japanese | 1394 | 1291 |
| LMArena Korean | 1401 | 1298 |
| LMArena Russian | 1418 | 1324 |
| LMArena Spanish | 1436 | 1319 |

## Instruction Following

- GLM-4.6: 74.5 (#93)
- GPT-4.1 mini: 73.9 (#113)

| Benchmark | GLM-4.6 | GPT-4.1 mini |
|---|---|---|
| LMArena Instruction Following | 1410 | 1332 |
| IFEval | — | 90.4% |

## Long Context

- GLM-4.6: 43.4 (#91)
- GPT-4.1 mini: 31.8 (#270)

| Benchmark | GLM-4.6 | GPT-4.1 mini |
|---|---|---|
| LMArena Longer Query | 1423 | 1344 |
| Fiction.LiveBench | — | 44.4% |

## Writing & Preference

- GLM-4.6: 61.3 (#86)
- GPT-4.1 mini: 48.8 (#193)

| Benchmark | GLM-4.6 | GPT-4.1 mini |
|---|---|---|
| LMArena Text | 1440 | 1341 |
| LMArena Creative Writing | 1411 | 1300 |
| EQ-Bench Creative Writing | 1411 | 1147 |
| LMArena Multi-Turn | 1427 | 1354 |
| WildBench | — | 83.8% |

## FAQ

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

GLM-4.6 is the stronger model overall, scoring 40.9 to 33.5 on the Noometry Index.

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

GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; GLM-4.6 lists at $0.60 and $2.20.

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

GLM-4.6 scores higher on coding benchmarks: 39.9 versus 30.4 in the Noometry coding category.

### Which has the bigger context window?

GPT-4.1 mini does, with 1.05M tokens against 205K.

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

24 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and GPT-4.1 mini has 47.