# DeepSeek-V3.1-Terminus vs GLM-4.5

> DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 41.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-terminus-vs-glm-4-5
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 4 categories and GLM-4.5 in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in long context, where DeepSeek-V3.1-Terminus leads 43.5 to 38.2.
- DeepSeek-V3.1-Terminus is cheaper at $0.30 / $1 per million input/output tokens, against $0.60 / $2.20 for GLM-4.5.
- DeepSeek-V3.1-Terminus accepts more context: 164K tokens versus 131K.

## Snapshot

| | DeepSeek-V3.1-Terminus | GLM-4.5 |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 42.6 | 41.4 |
| Rank | 96 | 125 |
| Context | 164K | 131K |
| Input $/M | $0.30 | $0.60 |
| Output $/M | $1 | $2.20 |
| Weights | Open | Open |

## Coding

- DeepSeek-V3.1-Terminus: 41.5 (#114)
- GLM-4.5: 41.1 (#121)

| Benchmark | DeepSeek-V3.1-Terminus | GLM-4.5 |
|---|---|---|
| LMArena Coding | 1426 | 1434 |
| ALE-Bench | 745.17 | 344.82 |
| SWE-bench Verified (bash only) | — | 54.2% |
| SciCode | 40.6% | — |
| WeirdML | — | 40.6% |
| AlgoTune | — | 1.52 |

## Reasoning

- DeepSeek-V3.1-Terminus: 25.7 (#126)
- GLM-4.5: 27.7 (#99)

| Benchmark | DeepSeek-V3.1-Terminus | GLM-4.5 |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | 57.9% |
| LMArena Hard Prompts | 1427 | 1430 |
| CritPt | 1.7% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |

## Math

- DeepSeek-V3.1-Terminus: 35.7 (#138)
- GLM-4.5: 36.3 (#119)

| Benchmark | DeepSeek-V3.1-Terminus | GLM-4.5 |
|---|---|---|
| LMArena Math | 1402 | 1427 |

## Knowledge

- DeepSeek-V3.1-Terminus: —
- GLM-4.5: 35.5 (#172)

| Benchmark | DeepSeek-V3.1-Terminus | GLM-4.5 |
|---|---|---|
| Humanity's Last Exam | — | 8.3% |
| Confabulations | — | 11.3% |
| LMArena Expert | — | 1433 |

## Multilingual

- DeepSeek-V3.1-Terminus: 52.3 (#87)
- GLM-4.5: 53.0 (#74)

| Benchmark | DeepSeek-V3.1-Terminus | GLM-4.5 |
|---|---|---|
| LMArena Non-English | 1407 | 1417 |
| LMArena Russian | 1434 | 1414 |
| LMArena Chinese | — | 1465 |
| LMArena French | — | 1423 |
| LMArena German | — | 1406 |
| LMArena Japanese | — | 1416 |
| LMArena Korean | — | 1382 |
| LMArena Spanish | — | 1454 |

## Instruction Following

- DeepSeek-V3.1-Terminus: 74.4 (#96)
- GLM-4.5: 74.3 (#100)

| Benchmark | DeepSeek-V3.1-Terminus | GLM-4.5 |
|---|---|---|
| LMArena Instruction Following | 1406 | 1405 |

## Long Context

- DeepSeek-V3.1-Terminus: 43.5 (#88)
- GLM-4.5: 38.2 (#196)

| Benchmark | DeepSeek-V3.1-Terminus | GLM-4.5 |
|---|---|---|
| LMArena Longer Query | 1426 | 1413 |
| Fiction.LiveBench | — | 58.3% |

## Writing & Preference

- DeepSeek-V3.1-Terminus: 61.3 (#87)
- GLM-4.5: 57.7 (#121)

| Benchmark | DeepSeek-V3.1-Terminus | GLM-4.5 |
|---|---|---|
| LMArena Text | 1420 | 1430 |
| LMArena Creative Writing | 1404 | 1395 |
| LMArena Multi-Turn | 1411 | 1415 |
| Short-Story Creative Writing | — | 73.4% |
| EQ-Bench Creative Writing | — | 1343 |

## FAQ

### Is DeepSeek-V3.1-Terminus better than GLM-4.5?

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 41.4 on the Noometry Index.

### Which is cheaper, DeepSeek-V3.1-Terminus or GLM-4.5?

DeepSeek-V3.1-Terminus is cheaper. It lists at $0.30 per million input tokens and $1 per million output tokens; GLM-4.5 lists at $0.60 and $2.20.

### Is DeepSeek-V3.1-Terminus or GLM-4.5 better for coding?

They score almost the same on coding (41.5 vs 41.1); test both on your own repository before choosing.

### Which has the bigger context window?

DeepSeek-V3.1-Terminus does, with 164K tokens against 131K.

### How many benchmarks do DeepSeek-V3.1-Terminus and GLM-4.5 share?

12 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and GLM-4.5 has 27.