# GLM-4.5 vs gpt-oss-20b

> GLM-4.5 is the stronger model overall, scoring 41.4 to 32.1 on the Noometry Index. gpt-oss-20b costs 28× less per token, which makes it the better buy when GLM-4.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-4-5-vs-gpt-oss-20b
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. GLM-4.5 scores higher in 7 categories and gpt-oss-20b in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.5 leads 57.7 to 35.8.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.60 / $2.20 for GLM-4.5.

## Snapshot

| | GLM-4.5 | gpt-oss-20b |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 41.4 | 32.1 |
| Rank | 125 | 249 |
| Context | 131K | 131K |
| Input $/M | $0.60 | $0.018 |
| Output $/M | $2.20 | $0.09 |
| Weights | Open | Open |

## Coding

- GLM-4.5: 41.1 (#121)
- gpt-oss-20b: 37.1 (#185)

| Benchmark | GLM-4.5 | gpt-oss-20b |
|---|---|---|
| WeirdML | 40.6% | 40.9% |
| LMArena Coding | 1434 | 1307 |
| ALE-Bench | 344.82 | 566.05 |
| SWE-bench Verified (bash only) | 54.2% | — |
| SciCode | — | 34.4% |
| AlgoTune | 1.52 | — |

## Agentic & Tool Use

- GLM-4.5: —
- gpt-oss-20b: 9.2 (#146)

| Benchmark | GLM-4.5 | gpt-oss-20b |
|---|---|---|
| Terminal-Bench | — | 3.4% |

## Reasoning

- GLM-4.5: 27.7 (#99)
- gpt-oss-20b: 18.8 (#251)

| Benchmark | GLM-4.5 | gpt-oss-20b |
|---|---|---|
| Kagi LLM Benchmark | 57.9% | 53.2% |
| LMArena Hard Prompts | 1430 | 1274 |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 4% |
| DTBench | — | 68% |
| LMCA | — | 14.5% |
| Epoch Capabilities Index | — | 137.81 |

## Math

- GLM-4.5: 36.3 (#119)
- gpt-oss-20b: 37.6 (#93)

| Benchmark | GLM-4.5 | gpt-oss-20b |
|---|---|---|
| LMArena Math | 1427 | 1317 |
| OTIS Mock AIME 2024-2025 | — | 65.3% |
| Omni-MATH | — | 56.5% |

## Knowledge

- GLM-4.5: 35.5 (#172)
- gpt-oss-20b: 34.6 (#186)

| Benchmark | GLM-4.5 | gpt-oss-20b |
|---|---|---|
| LMArena Expert | 1433 | 1258 |
| GPQA Diamond | — | 60.8% |
| Humanity's Last Exam | 8.3% | — |
| MMLU-Pro | — | 74% |
| Confabulations | 11.3% | — |
| GPQA (HELM) | — | 59.4% |

## Multilingual

- GLM-4.5: 53.0 (#74)
- gpt-oss-20b: 42.4 (#192)

| Benchmark | GLM-4.5 | gpt-oss-20b |
|---|---|---|
| LMArena Non-English | 1417 | 1269 |
| LMArena Chinese | 1465 | 1311 |
| LMArena German | 1406 | 1249 |
| LMArena Japanese | 1416 | 1245 |
| LMArena Korean | 1382 | 1239 |
| LMArena Russian | 1414 | 1279 |
| LMArena Spanish | 1454 | 1267 |
| LMArena French | 1423 | — |

## Instruction Following

- GLM-4.5: 74.3 (#100)
- gpt-oss-20b: 62.0 (#235)

| Benchmark | GLM-4.5 | gpt-oss-20b |
|---|---|---|
| LMArena Instruction Following | 1405 | 1236 |
| IFEval | — | 73.2% |

## Long Context

- GLM-4.5: 38.2 (#196)
- gpt-oss-20b: 37.9 (#203)

| Benchmark | GLM-4.5 | gpt-oss-20b |
|---|---|---|
| LMArena Longer Query | 1413 | 1251 |
| Fiction.LiveBench | 58.3% | — |

## Writing & Preference

- GLM-4.5: 57.7 (#121)
- gpt-oss-20b: 35.8 (#260)

| Benchmark | GLM-4.5 | gpt-oss-20b |
|---|---|---|
| LMArena Text | 1430 | 1288 |
| LMArena Creative Writing | 1395 | 1201 |
| EQ-Bench Creative Writing | 1343 | 666 |
| LMArena Multi-Turn | 1415 | 1268 |
| Short-Story Creative Writing | 73.4% | — |
| WildBench | — | 73.7% |

## FAQ

### Is GLM-4.5 better than gpt-oss-20b?

GLM-4.5 is the stronger model overall, scoring 41.4 to 32.1 on the Noometry Index. gpt-oss-20b costs 28× less per token, which makes it the better buy when GLM-4.5's lead doesn't matter for your workload.

### Which is cheaper, GLM-4.5 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-4.5 lists at $0.60 and $2.20.

### Is GLM-4.5 or gpt-oss-20b better for coding?

GLM-4.5 scores higher on coding benchmarks: 41.1 versus 37.1 in the Noometry coding category.

### Which has the bigger context window?

Both accept 131K tokens.

### How many benchmarks do GLM-4.5 and gpt-oss-20b share?

20 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and gpt-oss-20b has 34.