# DeepSeek LLM 67B vs GLM-4.5-Air

> GLM-4.5-Air is the stronger model overall, scoring 38.9 to 24.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-glm-4-5-air
- Last updated: 2026-10-12
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and GLM-4.5-Air in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.5-Air leads 35.0 to 7.0.

## Snapshot

| | DeepSeek LLM 67B | GLM-4.5-Air |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 24.9 | 38.9 |
| Rank | 347 | 177 |
| Context | — | 131K |
| Input $/M | — | $0.20 |
| Output $/M | — | $1.10 |
| Weights | Open | Open |

## Coding

- DeepSeek LLM 67B: 31.9 (#278)
- GLM-4.5-Air: 33.3 (#259)

| Benchmark | DeepSeek LLM 67B | GLM-4.5-Air |
|---|---|---|
| LMArena Coding | 1096 | 1397 |
| GSO | — | 2.9% |

## Reasoning

- DeepSeek LLM 67B: 16.5 (#304)
- GLM-4.5-Air: 24.1 (#166)

| Benchmark | DeepSeek LLM 67B | GLM-4.5-Air |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1379 |
| Kagi LLM Benchmark | — | 43% |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.5 | — |
| ForecastBench | — | 59.2 |

## Math

- DeepSeek LLM 67B: 8.7 (#324)
- GLM-4.5-Air: 36.2 (#170)

| Benchmark | DeepSeek LLM 67B | GLM-4.5-Air |
|---|---|---|
| LMArena Math | 1108 | 1396 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| Omni-MATH | — | 39.1% |
| MATH Level 5 | 6.4% | — |

## Knowledge

- DeepSeek LLM 67B: 7.0 (#313)
- GLM-4.5-Air: 35.0 (#191)

| Benchmark | DeepSeek LLM 67B | GLM-4.5-Air |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| Humanity's Last Exam | — | 8.1% |
| MMLU-Pro | — | 76.2% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 59.4% |
| LMArena Expert | — | 1370 |

## Multilingual

- DeepSeek LLM 67B: 29.4 (#267)
- GLM-4.5-Air: 49.1 (#135)

| Benchmark | DeepSeek LLM 67B | GLM-4.5-Air |
|---|---|---|
| LMArena Non-English | 1073 | 1366 |
| LMArena Chinese | 1132 | 1426 |
| LMArena French | — | 1399 |
| LMArena German | — | 1377 |
| LMArena Japanese | — | 1348 |
| LMArena Korean | — | 1308 |
| LMArena Russian | — | 1373 |
| LMArena Spanish | — | 1386 |

## Instruction Following

- DeepSeek LLM 67B: 55.4 (#277)
- GLM-4.5-Air: 69.6 (#171)

| Benchmark | DeepSeek LLM 67B | GLM-4.5-Air |
|---|---|---|
| LMArena Instruction Following | 1079 | 1354 |
| IFEval | — | 81.2% |

## Long Context

- DeepSeek LLM 67B: 33.1 (#265)
- GLM-4.5-Air: 41.6 (#135)

| Benchmark | DeepSeek LLM 67B | GLM-4.5-Air |
|---|---|---|
| LMArena Longer Query | 1092 | 1366 |

## Writing & Preference

- DeepSeek LLM 67B: 31.6 (#282)
- GLM-4.5-Air: 55.9 (#139)

| Benchmark | DeepSeek LLM 67B | GLM-4.5-Air |
|---|---|---|
| LMArena Text | 1105 | 1384 |
| LMArena Creative Writing | 1067 | 1343 |
| LMArena Multi-Turn | 1082 | 1371 |
| WildBench | — | 78.9% |

## FAQ

### Is DeepSeek LLM 67B better than GLM-4.5-Air?

GLM-4.5-Air is the stronger model overall, scoring 38.9 to 24.9 on the Noometry Index.

### Is DeepSeek LLM 67B or GLM-4.5-Air better for coding?

GLM-4.5-Air scores higher on coding benchmarks: 33.3 versus 31.9 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and GLM-4.5-Air share?

10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and GLM-4.5-Air has 27.