# GLM-5.1 vs o3-pro

> GLM-5.1 is the stronger model overall, scoring 47.6 to 42.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-5-1-vs-o3-pro
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. GLM-5.1 scores higher in 3 categories and o3-pro in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.1 to 44.9.
- GLM-5.1 is cheaper at $1.40 / $4.40 per million input/output tokens, against $20 / $80 for o3-pro.
- GLM-5.1 has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-5.1 | o3-pro |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 47.6 | 42.7 |
| Rank | 51 | 94 |
| Context | 200K | 200K |
| Input $/M | $1.40 | $20 |
| Output $/M | $4.40 | $80 |
| Weights | Open | Proprietary |

## Coding

- GLM-5.1: 48.5 (#52)
- o3-pro: 55.1 (#22)

| Benchmark | GLM-5.1 | o3-pro |
|---|---|---|
| WeirdML | 57.1% | 58.2% |
| SWE-bench Verified | 74.2% | — |
| Aider Polyglot | — | 84.9% |
| LMArena WebDev | 1509 | — |
| SciCode | 43.8% | — |
| LMArena Coding | 1486 | — |
| ALE-Bench | 887.1 | — |

## Agentic & Tool Use

- GLM-5.1: 24.8 (#106)
- o3-pro: —

| Benchmark | GLM-5.1 | o3-pro |
|---|---|---|
| APEX-Agents | 40.9% | — |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |

## Reasoning

- GLM-5.1: 38.2 (#57)
- o3-pro: 24.1 (#152)

| Benchmark | GLM-5.1 | o3-pro |
|---|---|---|
| Epoch Capabilities Index | 149.86 | 147.43 |
| ARC-AGI-2 | — | 4.9% |
| SimpleBench | 55.1% | — |
| Kagi LLM Benchmark | — | 72.1% |
| NYT Connections (extended) | 77.7% | — |
| ARC-AGI-1 | — | 59.3% |
| CritPt | 4.6% | — |
| Chess Puzzles | 19% | — |
| Thematic Generalization | 69.8% | — |
| LMArena Hard Prompts | 1472 | — |
| DTBench | — | 86.9% |
| LMCA | — | 38.5% |

## Math

- GLM-5.1: 49.0 (#48)
- o3-pro: —

| Benchmark | GLM-5.1 | o3-pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| OTIS Mock AIME 2024-2025 | 93.3% | — |
| ProofBench | 22.2% | — |
| LMArena Math | 1472 | — |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |

## Knowledge

- GLM-5.1: 55.0 (#45)
- o3-pro: 29.0 (#234)

| Benchmark | GLM-5.1 | o3-pro |
|---|---|---|
| GPQA Diamond | 89.9% | — |
| SimpleQA Verified | 34% | — |
| Confabulations | — | 14.2% |
| Vectara Hallucination Rate | — | 23.3% |
| LMArena Expert | 1477 | — |

## Multilingual

- GLM-5.1: 55.2 (#34)
- o3-pro: —

| Benchmark | GLM-5.1 | o3-pro |
|---|---|---|
| LMArena Non-English | 1448 | — |
| LMArena Chinese | 1516 | — |
| LMArena French | 1478 | — |
| LMArena German | 1466 | — |
| LMArena Japanese | 1436 | — |
| LMArena Korean | 1423 | — |
| LMArena Russian | 1453 | — |
| LMArena Spanish | 1467 | — |

## Instruction Following

- GLM-5.1: 76.5 (#41)
- o3-pro: —

| Benchmark | GLM-5.1 | o3-pro |
|---|---|---|
| LMArena Instruction Following | 1451 | — |

## Long Context

- GLM-5.1: 44.9 (#51)
- o3-pro: 72.1 (#1)

| Benchmark | GLM-5.1 | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| LMArena Longer Query | 1467 | — |

## Writing & Preference

- GLM-5.1: 67.2 (#29)
- o3-pro: 57.1 (#128)

| Benchmark | GLM-5.1 | o3-pro |
|---|---|---|
| LMArena Text | 1462 | — |
| LMArena Creative Writing | 1454 | — |
| Short-Story Creative Writing | — | 84.4% |
| EQ-Bench Creative Writing | 1592 | — |
| LMArena Multi-Turn | 1473 | — |

## FAQ

### Is GLM-5.1 better than o3-pro?

GLM-5.1 is the stronger model overall, scoring 47.6 to 42.7 on the Noometry Index.

### Which is cheaper, GLM-5.1 or o3-pro?

GLM-5.1 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; o3-pro lists at $20 and $80.

### Is GLM-5.1 or o3-pro better for coding?

o3-pro scores higher on coding benchmarks: 55.1 versus 48.5 in the Noometry coding category.

### Which has the bigger context window?

Both accept 200K tokens.

### How many benchmarks do GLM-5.1 and o3-pro share?

2 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and o3-pro has 12.