# DeepSeek LLM 67B vs GLM-5

> GLM-5 is the stronger model overall, scoring 45.9 to 24.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-glm-5
- 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 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5 leads 52.2 to 7.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 80% for GLM-5.

## Snapshot

| | DeepSeek LLM 67B | GLM-5 |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 24.8 | 45.9 |
| Rank | 341 | 59 |
| Context | — | 205K |
| Input $/M | — | $1 |
| Output $/M | — | $3.20 |
| Weights | Open | Open |

## Coding

- DeepSeek LLM 67B: 31.3 (#273)
- GLM-5: 49.0 (#47)

| Benchmark | DeepSeek LLM 67B | GLM-5 |
|---|---|---|
| LMArena Coding | 1096 | 1461 |
| SWE-bench Verified | — | 72.1% |
| SWE-bench Verified (bash only) | — | 72.8% |
| LMArena WebDev | — | 1434 |
| SWE-bench Multilingual | — | 69.7% |
| WeirdML | — | 48.2% |
| ALE-Bench | — | 765.62 |

## Agentic & Tool Use

- DeepSeek LLM 67B: —
- GLM-5: 30.9 (#65)

| Benchmark | DeepSeek LLM 67B | GLM-5 |
|---|---|---|
| Terminal-Bench | — | 52.4% |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 73.7% |
| τ²-bench Telecom | — | 86.8% |
| Vending-Bench 2 | — | 4,432 |

## Reasoning

- DeepSeek LLM 67B: 15.9 (#300)
- GLM-5: 27.6 (#100)

| Benchmark | DeepSeek LLM 67B | GLM-5 |
|---|---|---|
| Chess Puzzles | 0% | 10% |
| LMArena Hard Prompts | 1070 | 1451 |
| Epoch Capabilities Index | 110.54 | 145.84 |
| ARC-AGI-2 | — | 4.9% |
| SimpleBench | — | 53.2% |
| Kagi LLM Benchmark | — | 75% |
| NYT Connections (extended) | — | 74.8% |
| ARC-AGI-1 | — | 44.7% |
| ForecastBench | — | 61 |

## Math

- DeepSeek LLM 67B: 8.1 (#318)
- GLM-5: 44.8 (#66)

| Benchmark | DeepSeek LLM 67B | GLM-5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 80% |
| LMArena Math | 1108 | 1440 |
| MathArena Final-Answer Competitions | — | 65.7% |
| MATH Level 5 | 6.4% | — |
| FrontierMath (Feb 2025 set) | — | 16.4% |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- DeepSeek LLM 67B: 7.1 (#308)
- GLM-5: 52.2 (#59)

| Benchmark | DeepSeek LLM 67B | GLM-5 |
|---|---|---|
| GPQA Diamond | 24.6% | 87.8% |
| Vectara Hallucination Rate | — | 10.1% |
| LMArena Expert | — | 1454 |

## Multilingual

- DeepSeek LLM 67B: 29.5 (#262)
- GLM-5: 53.9 (#57)

| Benchmark | DeepSeek LLM 67B | GLM-5 |
|---|---|---|
| LMArena Non-English | 1073 | 1430 |
| LMArena Chinese | 1132 | 1511 |
| LMArena French | — | 1455 |
| LMArena German | — | 1445 |
| LMArena Japanese | — | 1416 |
| LMArena Korean | — | 1421 |
| LMArena Russian | — | 1436 |
| LMArena Spanish | — | 1452 |

## Instruction Following

- DeepSeek LLM 67B: 55.7 (#272)
- GLM-5: 75.4 (#64)

| Benchmark | DeepSeek LLM 67B | GLM-5 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1427 |

## Long Context

- DeepSeek LLM 67B: 33.1 (#260)
- GLM-5: 44.6 (#58)

| Benchmark | DeepSeek LLM 67B | GLM-5 |
|---|---|---|
| LMArena Longer Query | 1092 | 1446 |
| CL-bench | — | 18.7% |

## Writing & Preference

- DeepSeek LLM 67B: 31.8 (#277)
- GLM-5: 66.2 (#38)

| Benchmark | DeepSeek LLM 67B | GLM-5 |
|---|---|---|
| LMArena Text | 1105 | 1446 |
| LMArena Creative Writing | 1067 | 1438 |
| LMArena Multi-Turn | 1082 | 1456 |
| EQ-Bench Creative Writing | — | 1601 |

## FAQ

### Is DeepSeek LLM 67B better than GLM-5?

GLM-5 is the stronger model overall, scoring 45.9 to 24.8 on the Noometry Index.

### Is DeepSeek LLM 67B or GLM-5 better for coding?

GLM-5 scores higher on coding benchmarks: 49.0 versus 31.3 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and GLM-5 share?

14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and GLM-5 has 45.