# GLM-5.1 vs o3

> GLM-5.1 and o3 score almost the same on the Noometry Index (47.6 vs 47.4), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/glm-5-1-vs-o3
- Last updated: 2026-10-10
- Shared benchmarks: 31

## Summary

- They share 31 benchmarks with published results for both. GLM-5.1 scores higher in 7 categories and o3 in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where o3 leads 34.3 to 24.8.
- The biggest single-benchmark swing is Chess Puzzles: 19% for GLM-5.1 and 38% for o3.
- GLM-5.1 is cheaper at $1.40 / $4.40 per million input/output tokens, against $2 / $8 for o3.
- GLM-5.1 has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-5.1 | o3 |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 47.6 | 47.4 |
| Rank | 51 | 53 |
| Context | 200K | 200K |
| Input $/M | $1.40 | $2 |
| Output $/M | $4.40 | $8 |
| Weights | Open | Proprietary |

## Coding

- GLM-5.1: 48.5 (#52)
- o3: 47.3 (#57)

| Benchmark | GLM-5.1 | o3 |
|---|---|---|
| SWE-bench Verified | 74.2% | 62.3% |
| WeirdML | 57.1% | 52.4% |
| LMArena Coding | 1486 | 1408 |
| ALE-Bench | 887.1 | 933.55 |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| LMArena WebDev | 1509 | — |
| SciCode | 43.8% | — |
| GSO | — | 8.8% |
| CadEval | — | 74% |

## Agentic & Tool Use

- GLM-5.1: 24.8 (#106)
- o3: 34.3 (#42)

| Benchmark | GLM-5.1 | o3 |
|---|---|---|
| APEX-Agents | 40.9% | — |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 30.8% |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |
| Vending-Bench 2 | 5,634 | — |

## Reasoning

- GLM-5.1: 38.2 (#57)
- o3: 32.1 (#66)

| Benchmark | GLM-5.1 | o3 |
|---|---|---|
| SimpleBench | 55.1% | 53.1% |
| CritPt | 4.6% | 1.4% |
| Chess Puzzles | 19% | 38% |
| LMArena Hard Prompts | 1472 | 1402 |
| Epoch Capabilities Index | 149.86 | 146.88 |
| ARC-AGI-2 | — | 6.5% |
| Kagi LLM Benchmark | — | 67.6% |
| NYT Connections (extended) | 77.7% | — |
| ARC-AGI-1 | — | 60.8% |
| EnigmaEval | — | 13.1% |
| Thematic Generalization | 69.8% | — |
| Mystery Game Puzzles | — | 29% |
| DTBench | — | 84.8% |
| LMCA | — | 39.7% |
| ForecastBench | — | 62.5 |

## Math

- GLM-5.1: 49.0 (#48)
- o3: 48.9 (#49)

| Benchmark | GLM-5.1 | o3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 36.8% | 33.3% |
| OTIS Mock AIME 2024-2025 | 93.3% | 84.4% |
| LMArena Math | 1472 | 1426 |
| FrontierMath (Feb 2025 set) | 33.4% | 18.7% |
| FrontierMath Tier 4 (v1) | 12.5% | 2.1% |
| MathArena Final-Answer Competitions | 67.1% | — |
| ProofBench | 22.2% | — |
| Omni-MATH | — | 71.4% |
| MATH Level 5 | — | 97.8% |

## Knowledge

- GLM-5.1: 55.0 (#45)
- o3: 54.5 (#47)

| Benchmark | GLM-5.1 | o3 |
|---|---|---|
| GPQA Diamond | 89.9% | 81.8% |
| SimpleQA Verified | 34% | 49.4% |
| LMArena Expert | 1477 | 1403 |
| Humanity's Last Exam | — | 20.3% |
| MMLU-Pro | — | 85.9% |
| Confabulations | — | 14.4% |
| GPQA (HELM) | — | 75.3% |

## Multimodal

- GLM-5.1: —
- o3: 40.7 (#35)

| Benchmark | GLM-5.1 | o3 |
|---|---|---|
| LMArena Vision | — | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |

## Multilingual

- GLM-5.1: 55.2 (#34)
- o3: 51.9 (#99)

| Benchmark | GLM-5.1 | o3 |
|---|---|---|
| LMArena Non-English | 1448 | 1402 |
| LMArena Chinese | 1516 | 1438 |
| LMArena French | 1478 | 1430 |
| LMArena German | 1466 | 1420 |
| LMArena Japanese | 1436 | 1404 |
| LMArena Korean | 1423 | 1371 |
| LMArena Russian | 1453 | 1407 |
| LMArena Spanish | 1467 | 1395 |

## Instruction Following

- GLM-5.1: 76.5 (#41)
- o3: 73.0 (#122)

| Benchmark | GLM-5.1 | o3 |
|---|---|---|
| LMArena Instruction Following | 1451 | 1368 |
| IFEval | — | 86.9% |

## Long Context

- GLM-5.1: 44.9 (#51)
- o3: 53.2 (#6)

| Benchmark | GLM-5.1 | o3 |
|---|---|---|
| LMArena Longer Query | 1467 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |

## Writing & Preference

- GLM-5.1: 67.2 (#29)
- o3: 63.7 (#62)

| Benchmark | GLM-5.1 | o3 |
|---|---|---|
| LMArena Text | 1462 | 1410 |
| LMArena Creative Writing | 1454 | 1359 |
| EQ-Bench Creative Writing | 1592 | 1676 |
| LMArena Multi-Turn | 1473 | 1405 |
| Short-Story Creative Writing | — | 83.9% |
| WildBench | — | 86.1% |

## FAQ

### Is GLM-5.1 better than o3?

GLM-5.1 and o3 score almost the same on the Noometry Index (47.6 vs 47.4), so choose on price, context window or the category you care about most.

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

GLM-5.1 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; o3 lists at $2 and $8.

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

GLM-5.1 scores higher on coding benchmarks: 48.5 versus 47.3 in the Noometry coding category.

### Which has the bigger context window?

Both accept 200K tokens.

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

31 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and o3 has 63.