# GLM-5.3 vs GPT-5.1

> GLM-5.3 is the stronger model overall, scoring 54.6 to 48.8 on the Noometry Index.

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

## Summary

- They share 31 benchmarks with published results for both. GLM-5.3 scores higher in 7 categories and GPT-5.1 in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where GLM-5.3 leads 59.0 to 46.9.
- The biggest single-benchmark swing is SciCode: 59% for GLM-5.3 and 43.3% for GPT-5.1.
- GLM-5.3 is cheaper at $1.40 / $4.40 per million input/output tokens, against $1.25 / $10 for GPT-5.1.
- GLM-5.3 accepts more context: 1M tokens versus 400K.
- GLM-5.3 has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-5.3 | GPT-5.1 |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 54.6 | 48.8 |
| Rank | 25 | 47 |
| Context | 1M | 400K |
| Input $/M | $1.40 | $1.25 |
| Output $/M | $4.40 | $10 |
| Weights | Open | Proprietary |

## Coding

- GLM-5.3: 59.0 (#12)
- GPT-5.1: 46.9 (#59)

| Benchmark | GLM-5.3 | GPT-5.1 |
|---|---|---|
| LMArena WebDev | 1623 | 1395 |
| SciCode | 59% | 43.3% |
| WeirdML | 75.4% | 60.8% |
| LMArena Coding | 1499 | 1454 |
| ALE-Bench | 1,317 | 1,192 |
| SWE-bench Verified | — | 68% |
| DeepSWE | 69% | — |
| FrontierCode | 40.1% | — |
| SWE-bench Verified (bash only) | — | 66% |
| FrontierSWE | 30.2% | — |
| GSO | — | 13.7% |
| LiveBench Coding | — | 72.5% |

## Agentic & Tool Use

- GLM-5.3: 36.3 (#34)
- GPT-5.1: 32.5 (#55)

| Benchmark | GLM-5.3 | GPT-5.1 |
|---|---|---|
| Vending-Bench 2 | 8,164 | 1,473 |
| Terminal-Bench | — | 47.6% |
| APEX-Agents | 56.6% | — |
| DeepResearch Bench | — | 42.8% |
| LMArena Search | — | 1199 |

## Reasoning

- GLM-5.3: 45.2 (#42)
- GPT-5.1: 39.9 (#50)

| Benchmark | GLM-5.3 | GPT-5.1 |
|---|---|---|
| CritPt | 19.1% | 4.9% |
| Chess Puzzles | 21% | 32% |
| LMArena Hard Prompts | 1491 | 1457 |
| Mystery Game Puzzles | 33% | 19% |
| DTBench | 87.7% | 90.1% |
| LMCA | 55.5% | 43.9% |
| Epoch Capabilities Index | 155.56 | 149.66 |
| ARC-AGI-2 | — | 17.6% |
| SimpleBench | — | 53.2% |
| NYT Connections (extended) | 74.2% | — |
| ARC-AGI-1 | — | 72.8% |
| EnigmaEval | — | 11.2% |
| LiveBench Reasoning | — | 95.8% |
| LiveBench Data Analysis | — | 72.1% |
| Bench to the Future 3 | 0.15 | — |
| ForecastBench | — | 58.1 |
| LiveBench | — | 78.8% |

## Math

- GLM-5.3: 62.1 (#27)
- GPT-5.1: 50.3 (#45)

| Benchmark | GLM-5.3 | GPT-5.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 91.1% | 88.6% |
| LMArena Math | 1493 | 1446 |
| FrontierMath (Tiers 1-3) | 68.8% | — |
| FrontierMath Tier 4 | 29.3% | — |
| ProofBench | 49% | — |
| Omni-MATH | — | 46.4% |
| LiveBench Math | — | 94.5% |
| FrontierMath (Feb 2025 set) | — | 31% |
| FrontierMath Tier 4 (v1) | — | 12.5% |

## Knowledge

- GLM-5.3: 58.3 (#34)
- GPT-5.1: 50.5 (#65)

| Benchmark | GLM-5.3 | GPT-5.1 |
|---|---|---|
| GPQA Diamond | 90.9% | 87.6% |
| SimpleQA Verified | 41% | 48% |
| LMArena Expert | 1512 | 1470 |
| Humanity's Last Exam | — | 23.7% |
| MMLU-Pro | — | 57.9% |
| Vectara Hallucination Rate | — | 10.9% |
| GPQA (HELM) | — | 44.2% |

## Multimodal

- GLM-5.3: —
- GPT-5.1: 44.0 (#17)

| Benchmark | GLM-5.3 | GPT-5.1 |
|---|---|---|
| LMArena Vision | — | 1250 |
| VPCT | — | 58.7% |
| LMArena Document | — | 1403 |

## Multilingual

- GLM-5.3: 55.9 (#27)
- GPT-5.1: 54.0 (#51)

| Benchmark | GLM-5.3 | GPT-5.1 |
|---|---|---|
| LMArena Non-English | 1457 | 1431 |
| LMArena Chinese | 1523 | 1495 |
| LMArena French | 1499 | 1451 |
| LMArena German | 1505 | 1439 |
| LMArena Japanese | 1438 | 1453 |
| LMArena Korean | 1478 | 1401 |
| LMArena Russian | 1460 | 1435 |
| LMArena Spanish | 1444 | 1430 |

## Instruction Following

- GLM-5.3: 77.8 (#15)
- GPT-5.1: 84.0 (#1)

| Benchmark | GLM-5.3 | GPT-5.1 |
|---|---|---|
| LMArena Instruction Following | 1481 | 1442 |
| LiveBench Instruction Following | — | 93.3% |
| IFEval | — | 93.5% |

## Long Context

- GLM-5.3: 45.5 (#32)
- GPT-5.1: 47.6 (#14)

| Benchmark | GLM-5.3 | GPT-5.1 |
|---|---|---|
| LMArena Longer Query | 1485 | 1448 |
| CL-bench | — | 23.7% |
| CL-bench Life | — | 17.3% |

## Writing & Preference

- GLM-5.3: 75.9 (#6)
- GPT-5.1: 64.7 (#53)

| Benchmark | GLM-5.3 | GPT-5.1 |
|---|---|---|
| LMArena Text | 1473 | 1443 |
| LMArena Creative Writing | 1459 | 1427 |
| LMArena Multi-Turn | 1473 | 1449 |
| EQ-Bench Creative Writing | 2075 | — |
| WildBench | — | 86.3% |
| LiveBench Language | — | 80.2% |

## FAQ

### Is GLM-5.3 better than GPT-5.1?

GLM-5.3 is the stronger model overall, scoring 54.6 to 48.8 on the Noometry Index.

### Which is cheaper, GLM-5.3 or GPT-5.1?

GLM-5.3 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; GPT-5.1 lists at $1.25 and $10.

### Is GLM-5.3 or GPT-5.1 better for coding?

GLM-5.3 scores higher on coding benchmarks: 59.0 versus 46.9 in the Noometry coding category.

### Which has the bigger context window?

GLM-5.3 does, with 1M tokens against 400K.

### How many benchmarks do GLM-5.3 and GPT-5.1 share?

31 benchmarks have published results for both models. GLM-5.3 has 41 scored results on Noometry and GPT-5.1 has 63.