# GLM-4.7 vs gpt-oss-120b

> GLM-4.7 is the stronger model overall, scoring 41.7 to 36.0 on the Noometry Index. gpt-oss-120b costs 14× less per token, which makes it the better buy when GLM-4.7's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-4-7-vs-gpt-oss-120b
- Last updated: 2026-10-10
- Shared benchmarks: 29

## Summary

- They share 29 benchmarks with published results for both. GLM-4.7 scores higher in 8 categories and gpt-oss-120b in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.7 leads 61.1 to 46.7.
- The biggest single-benchmark swing is SimpleBench: 47.7% for GLM-4.7 and 22.1% for gpt-oss-120b.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.60 / $2.20 for GLM-4.7.
- GLM-4.7 accepts more context: 205K tokens versus 131K.

## Snapshot

| | GLM-4.7 | gpt-oss-120b |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 41.7 | 36.0 |
| Rank | 117 | 210 |
| Context | 205K | 131K |
| Input $/M | $0.60 | $0.037 |
| Output $/M | $2.20 | $0.17 |
| Weights | Open | Open |

## Coding

- GLM-4.7: 43.6 (#74)
- gpt-oss-120b: 33.2 (#251)

| Benchmark | GLM-4.7 | gpt-oss-120b |
|---|---|---|
| SciCode | 45.1% | 36% |
| LMArena Coding | 1454 | 1380 |
| ALE-Bench | 399.48 | 575.62 |
| SWE-bench Verified (bash only) | — | 26% |
| Aider Polyglot | — | 41.8% |
| LMArena WebDev | 1435 | — |
| WeirdML | — | 48.2% |
| AlgoTune | — | 1.41 |

## Agentic & Tool Use

- GLM-4.7: 26.4 (#96)
- gpt-oss-120b: 12.1 (#145)

| Benchmark | GLM-4.7 | gpt-oss-120b |
|---|---|---|
| Terminal-Bench | 33.4% | 18.7% |
| Vending-Bench 2 | 2,377 | -21.53 |
| APEX-Agents | — | 4.4% |
| METR Time Horizons | — | 56.6% |

## Reasoning

- GLM-4.7: 23.7 (#161)
- gpt-oss-120b: 19.5 (#236)

| Benchmark | GLM-4.7 | gpt-oss-120b |
|---|---|---|
| SimpleBench | 47.7% | 22.1% |
| CritPt | 1.7% | 1.1% |
| Chess Puzzles | 6% | 20% |
| LMArena Hard Prompts | 1443 | 1364 |
| Epoch Capabilities Index | 143.53 | 139.94 |
| Kagi LLM Benchmark | — | 58.6% |
| Mystery Game Puzzles | — | 2% |
| DTBench | — | 76.3% |
| LMCA | — | 22.1% |
| Surface Evolver Bench | — | 25% |

## Math

- GLM-4.7: 37.7 (#92)
- gpt-oss-120b: 50.6 (#43)

| Benchmark | GLM-4.7 | gpt-oss-120b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.3% | 88.9% |
| LMArena Math | 1423 | 1388 |
| ProofBench | 6% | — |
| Omni-MATH | — | 68.8% |
| FrontierMath (Feb 2025 set) | 2.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- GLM-4.7: 47.0 (#74)
- gpt-oss-120b: 42.3 (#89)

| Benchmark | GLM-4.7 | gpt-oss-120b |
|---|---|---|
| GPQA Diamond | 83.3% | 75.8% |
| Vectara Hallucination Rate | 11.7% | 14.2% |
| LMArena Expert | 1424 | 1356 |
| SimpleQA Verified | 32.2% | — |
| MMLU-Pro | — | 79.5% |
| Confabulations | — | 15.7% |
| GPQA (HELM) | — | 68.4% |

## Multilingual

- GLM-4.7: 53.0 (#75)
- gpt-oss-120b: 48.2 (#142)

| Benchmark | GLM-4.7 | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1417 | 1350 |
| LMArena Chinese | 1495 | 1384 |
| LMArena French | 1432 | 1370 |
| LMArena German | 1426 | 1355 |
| LMArena Japanese | 1439 | 1332 |
| LMArena Korean | 1401 | 1283 |
| LMArena Russian | 1423 | 1343 |
| LMArena Spanish | 1433 | 1388 |

## Instruction Following

- GLM-4.7: 74.6 (#90)
- gpt-oss-120b: 69.5 (#168)

| Benchmark | GLM-4.7 | gpt-oss-120b |
|---|---|---|
| LMArena Instruction Following | 1411 | 1318 |
| IFEval | — | 83.6% |

## Long Context

- GLM-4.7: 42.8 (#111)
- gpt-oss-120b: 31.4 (#273)

| Benchmark | GLM-4.7 | gpt-oss-120b |
|---|---|---|
| LMArena Longer Query | 1432 | 1319 |
| Fiction.LiveBench | — | 44.4% |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |

## Writing & Preference

- GLM-4.7: 61.1 (#89)
- gpt-oss-120b: 46.7 (#213)

| Benchmark | GLM-4.7 | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1436 | 1366 |
| LMArena Creative Writing | 1401 | 1274 |
| EQ-Bench Creative Writing | 1413 | 961 |
| LMArena Multi-Turn | 1446 | 1340 |
| Short-Story Creative Writing | — | 77.1% |
| WildBench | — | 84.5% |

## FAQ

### Is GLM-4.7 better than gpt-oss-120b?

GLM-4.7 is the stronger model overall, scoring 41.7 to 36.0 on the Noometry Index. gpt-oss-120b costs 14× less per token, which makes it the better buy when GLM-4.7's lead doesn't matter for your workload.

### Which is cheaper, GLM-4.7 or gpt-oss-120b?

gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; GLM-4.7 lists at $0.60 and $2.20.

### Is GLM-4.7 or gpt-oss-120b better for coding?

GLM-4.7 scores higher on coding benchmarks: 43.6 versus 33.2 in the Noometry coding category.

### Which has the bigger context window?

GLM-4.7 does, with 205K tokens against 131K.

### How many benchmarks do GLM-4.7 and gpt-oss-120b share?

29 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and gpt-oss-120b has 48.