# DeepSeek LLM 67B vs GLM-5.2

> GLM-5.2 is the stronger model overall, scoring 50.9 to 24.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-glm-5-2
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and GLM-5.2 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.2 leads 57.1 to 7.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 86.4% for GLM-5.2.

## Snapshot

| | DeepSeek LLM 67B | GLM-5.2 |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 24.8 | 50.9 |
| Rank | 341 | 38 |
| Context | — | 1M |
| Input $/M | — | $1.40 |
| Output $/M | — | $4.40 |
| Weights | Open | Open |

## Coding

- DeepSeek LLM 67B: 31.3 (#273)
- GLM-5.2: 50.9 (#37)

| Benchmark | DeepSeek LLM 67B | GLM-5.2 |
|---|---|---|
| LMArena Coding | 1096 | 1484 |
| SWE-bench Verified | — | 78.7% |
| DeepSWE | — | 43.8% |
| FrontierCode | — | 24.5% |
| LMArena WebDev | — | 1604 |
| SciCode | — | 50.5% |
| WeirdML | — | 70.1% |
| ALE-Bench | — | 1,047 |

## Agentic & Tool Use

- DeepSeek LLM 67B: —
- GLM-5.2: 31.6 (#63)

| Benchmark | DeepSeek LLM 67B | GLM-5.2 |
|---|---|---|
| τ²-bench Banking | — | 37.1% |
| PostTrainBench | — | 31.7% |
| GBAEval | — | 0% |
| Vending-Bench 2 | — | 8,314 |

## Reasoning

- DeepSeek LLM 67B: 15.9 (#300)
- GLM-5.2: 42.1 (#46)

| Benchmark | DeepSeek LLM 67B | GLM-5.2 |
|---|---|---|
| Chess Puzzles | 0% | 21% |
| LMArena Hard Prompts | 1070 | 1480 |
| Epoch Capabilities Index | 110.54 | 151.76 |
| ARC-AGI-2 | — | 22.8% |
| SimpleBench | — | 58.8% |
| Kagi LLM Benchmark | — | 62.6% |
| NYT Connections (extended) | — | 74.3% |
| ARC-AGI-1 | — | 77% |
| CritPt | — | 20.9% |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 19% |
| DTBench | — | 93.6% |
| LMCA | — | 45.8% |
| Surface Evolver Bench | — | 55.6% |

## Math

- DeepSeek LLM 67B: 8.1 (#318)
- GLM-5.2: 55.4 (#35)

| Benchmark | DeepSeek LLM 67B | GLM-5.2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 86.4% |
| LMArena Math | 1108 | 1482 |
| FrontierMath (Tiers 1-3) | — | 59.2% |
| FrontierMath Tier 4 | — | 29.3% |
| MathArena Final-Answer Competitions | — | 67.6% |
| ProofBench | — | 35% |
| MATH Level 5 | 6.4% | — |

## Knowledge

- DeepSeek LLM 67B: 7.1 (#308)
- GLM-5.2: 57.1 (#36)

| Benchmark | DeepSeek LLM 67B | GLM-5.2 |
|---|---|---|
| GPQA Diamond | 24.6% | 91.9% |
| SimpleQA Verified | — | 34.2% |
| LMArena Expert | — | 1484 |

## Multilingual

- DeepSeek LLM 67B: 29.5 (#262)
- GLM-5.2: 56.0 (#25)

| Benchmark | DeepSeek LLM 67B | GLM-5.2 |
|---|---|---|
| LMArena Non-English | 1073 | 1459 |
| LMArena Chinese | 1132 | 1518 |
| LMArena French | — | 1476 |
| LMArena German | — | 1470 |
| LMArena Japanese | — | 1451 |
| LMArena Korean | — | 1445 |
| LMArena Russian | — | 1467 |
| LMArena Spanish | — | 1477 |

## Instruction Following

- DeepSeek LLM 67B: 55.7 (#272)
- GLM-5.2: 77.1 (#32)

| Benchmark | DeepSeek LLM 67B | GLM-5.2 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1465 |

## Long Context

- DeepSeek LLM 67B: 33.1 (#260)
- GLM-5.2: 45.3 (#43)

| Benchmark | DeepSeek LLM 67B | GLM-5.2 |
|---|---|---|
| LMArena Longer Query | 1092 | 1479 |

## Writing & Preference

- DeepSeek LLM 67B: 31.8 (#277)
- GLM-5.2: 70.7 (#20)

| Benchmark | DeepSeek LLM 67B | GLM-5.2 |
|---|---|---|
| LMArena Text | 1105 | 1470 |
| LMArena Creative Writing | 1067 | 1465 |
| LMArena Multi-Turn | 1082 | 1468 |
| EQ-Bench Creative Writing | — | 1757 |
| EQ-Bench 4 | — | 1222 |

## FAQ

### Is DeepSeek LLM 67B better than GLM-5.2?

GLM-5.2 is the stronger model overall, scoring 50.9 to 24.8 on the Noometry Index.

### Is DeepSeek LLM 67B or GLM-5.2 better for coding?

GLM-5.2 scores higher on coding benchmarks: 50.9 versus 31.3 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and GLM-5.2 share?

14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and GLM-5.2 has 50.