# GLM-5.1 vs gpt-oss-20b

> GLM-5.1 is the stronger model overall, scoring 47.6 to 32.1 on the Noometry Index. gpt-oss-20b costs 60× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-5-1-vs-gpt-oss-20b
- Last updated: 2026-10-10
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. GLM-5.1 scores higher in 9 categories and gpt-oss-20b in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5.1 leads 67.2 to 35.8.
- The biggest single-benchmark swing is GPQA Diamond: 89.9% for GLM-5.1 and 60.8% for gpt-oss-20b.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- GLM-5.1 accepts more context: 200K tokens versus 131K.

## Snapshot

| | GLM-5.1 | gpt-oss-20b |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 47.6 | 32.1 |
| Rank | 51 | 249 |
| Context | 200K | 131K |
| Input $/M | $1.40 | $0.018 |
| Output $/M | $4.40 | $0.09 |
| Weights | Open | Open |

## Coding

- GLM-5.1: 48.5 (#52)
- gpt-oss-20b: 37.1 (#185)

| Benchmark | GLM-5.1 | gpt-oss-20b |
|---|---|---|
| SciCode | 43.8% | 34.4% |
| WeirdML | 57.1% | 40.9% |
| LMArena Coding | 1486 | 1307 |
| ALE-Bench | 887.1 | 566.05 |
| SWE-bench Verified | 74.2% | — |
| LMArena WebDev | 1509 | — |

## Agentic & Tool Use

- GLM-5.1: 24.8 (#106)
- gpt-oss-20b: 9.2 (#146)

| Benchmark | GLM-5.1 | gpt-oss-20b |
|---|---|---|
| Terminal-Bench | — | 3.4% |
| APEX-Agents | 40.9% | — |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |

## Reasoning

- GLM-5.1: 38.2 (#57)
- gpt-oss-20b: 18.8 (#251)

| Benchmark | GLM-5.1 | gpt-oss-20b |
|---|---|---|
| CritPt | 4.6% | 1.4% |
| Chess Puzzles | 19% | 4% |
| LMArena Hard Prompts | 1472 | 1274 |
| Epoch Capabilities Index | 149.86 | 137.81 |
| SimpleBench | 55.1% | — |
| Kagi LLM Benchmark | — | 53.2% |
| NYT Connections (extended) | 77.7% | — |
| Thematic Generalization | 69.8% | — |
| DTBench | — | 68% |
| LMCA | — | 14.5% |

## Math

- GLM-5.1: 49.0 (#48)
- gpt-oss-20b: 37.6 (#93)

| Benchmark | GLM-5.1 | gpt-oss-20b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.3% | 65.3% |
| LMArena Math | 1472 | 1317 |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| ProofBench | 22.2% | — |
| Omni-MATH | — | 56.5% |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |

## Knowledge

- GLM-5.1: 55.0 (#45)
- gpt-oss-20b: 34.6 (#186)

| Benchmark | GLM-5.1 | gpt-oss-20b |
|---|---|---|
| GPQA Diamond | 89.9% | 60.8% |
| LMArena Expert | 1477 | 1258 |
| SimpleQA Verified | 34% | — |
| MMLU-Pro | — | 74% |
| GPQA (HELM) | — | 59.4% |

## Multilingual

- GLM-5.1: 55.2 (#34)
- gpt-oss-20b: 42.4 (#192)

| Benchmark | GLM-5.1 | gpt-oss-20b |
|---|---|---|
| LMArena Non-English | 1448 | 1269 |
| LMArena Chinese | 1516 | 1311 |
| LMArena German | 1466 | 1249 |
| LMArena Japanese | 1436 | 1245 |
| LMArena Korean | 1423 | 1239 |
| LMArena Russian | 1453 | 1279 |
| LMArena Spanish | 1467 | 1267 |
| LMArena French | 1478 | — |

## Instruction Following

- GLM-5.1: 76.5 (#41)
- gpt-oss-20b: 62.0 (#235)

| Benchmark | GLM-5.1 | gpt-oss-20b |
|---|---|---|
| LMArena Instruction Following | 1451 | 1236 |
| IFEval | — | 73.2% |

## Long Context

- GLM-5.1: 44.9 (#51)
- gpt-oss-20b: 37.9 (#203)

| Benchmark | GLM-5.1 | gpt-oss-20b |
|---|---|---|
| LMArena Longer Query | 1467 | 1251 |

## Writing & Preference

- GLM-5.1: 67.2 (#29)
- gpt-oss-20b: 35.8 (#260)

| Benchmark | GLM-5.1 | gpt-oss-20b |
|---|---|---|
| LMArena Text | 1462 | 1288 |
| LMArena Creative Writing | 1454 | 1201 |
| EQ-Bench Creative Writing | 1592 | 666 |
| LMArena Multi-Turn | 1473 | 1268 |
| WildBench | — | 73.7% |

## FAQ

### Is GLM-5.1 better than gpt-oss-20b?

GLM-5.1 is the stronger model overall, scoring 47.6 to 32.1 on the Noometry Index. gpt-oss-20b costs 60× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.

### Which is cheaper, GLM-5.1 or gpt-oss-20b?

gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.

### Is GLM-5.1 or gpt-oss-20b better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.5 versus 37.1 in the Noometry coding category.

### Which has the bigger context window?

GLM-5.1 does, with 200K tokens against 131K.

### How many benchmarks do GLM-5.1 and gpt-oss-20b share?

25 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and gpt-oss-20b has 34.