# DeepSeek V4.1 Flash vs GLM-4.5

> DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 41.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v4-1-flash-vs-glm-4-5
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and GLM-4.5 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4.1 Flash leads 46.2 to 27.7.
- DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.60 / $2.20 for GLM-4.5.
- DeepSeek V4.1 Flash accepts more context: 1M tokens versus 131K.

## Snapshot

| | DeepSeek V4.1 Flash | GLM-4.5 |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 50.3 | 41.4 |
| Rank | 40 | 125 |
| Context | 1M | 131K |
| Input $/M | $0.15 | $0.60 |
| Output $/M | $0.60 | $2.20 |
| Weights | Open | Open |

## Coding

- DeepSeek V4.1 Flash: 52.8 (#29)
- GLM-4.5: 41.1 (#121)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.5 |
|---|---|---|
| LMArena Coding | 1511 | 1434 |
| ALE-Bench | 1,092 | 344.82 |
| SWE-bench Verified (bash only) | — | 54.2% |
| LMArena WebDev | 1620 | — |
| SciCode | 51.9% | — |
| WeirdML | — | 40.6% |
| AlgoTune | — | 1.52 |

## Reasoning

- DeepSeek V4.1 Flash: 46.2 (#39)
- GLM-4.5: 27.7 (#99)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.5 |
|---|---|---|
| LMArena Hard Prompts | 1485 | 1430 |
| Kagi LLM Benchmark | — | 57.9% |
| NYT Connections (extended) | 89.6% | — |
| CritPt | 14.3% | — |
| DTBench | 89.9% | — |
| LMCA | 47% | — |
| Surface Evolver Bench | 46.3% | — |
| Epoch Capabilities Index | 155.01 | — |

## Math

- DeepSeek V4.1 Flash: 48.4 (#52)
- GLM-4.5: 36.3 (#119)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.5 |
|---|---|---|
| LMArena Math | 1493 | 1427 |
| ProofBench | 54% | — |

## Knowledge

- DeepSeek V4.1 Flash: 41.6 (#97)
- GLM-4.5: 35.5 (#172)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.5 |
|---|---|---|
| LMArena Expert | 1505 | 1433 |
| Humanity's Last Exam | — | 8.3% |
| Confabulations | — | 11.3% |

## Multilingual

- DeepSeek V4.1 Flash: 55.5 (#29)
- GLM-4.5: 53.0 (#74)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.5 |
|---|---|---|
| LMArena Non-English | 1452 | 1417 |
| LMArena Chinese | 1506 | 1465 |
| LMArena French | 1448 | 1423 |
| LMArena Russian | 1473 | 1414 |
| LMArena Spanish | 1499 | 1454 |
| LMArena German | — | 1406 |
| LMArena Japanese | — | 1416 |
| LMArena Korean | — | 1382 |

## Instruction Following

- DeepSeek V4.1 Flash: 77.6 (#24)
- GLM-4.5: 74.3 (#100)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.5 |
|---|---|---|
| LMArena Instruction Following | 1475 | 1405 |

## Long Context

- DeepSeek V4.1 Flash: 45.2 (#46)
- GLM-4.5: 38.2 (#196)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.5 |
|---|---|---|
| LMArena Longer Query | 1476 | 1413 |
| Fiction.LiveBench | — | 58.3% |

## Writing & Preference

- DeepSeek V4.1 Flash: 65.8 (#43)
- GLM-4.5: 57.7 (#121)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.5 |
|---|---|---|
| LMArena Text | 1465 | 1430 |
| LMArena Creative Writing | 1436 | 1395 |
| EQ-Bench Creative Writing | 1540 | 1343 |
| LMArena Multi-Turn | 1460 | 1415 |
| Short-Story Creative Writing | — | 73.4% |

## FAQ

### Is DeepSeek V4.1 Flash better than GLM-4.5?

DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 41.4 on the Noometry Index.

### Which is cheaper, DeepSeek V4.1 Flash or GLM-4.5?

DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GLM-4.5 lists at $0.60 and $2.20.

### Is DeepSeek V4.1 Flash or GLM-4.5 better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.8 versus 41.1 in the Noometry coding category.

### Which has the bigger context window?

DeepSeek V4.1 Flash does, with 1M tokens against 131K.

### How many benchmarks do DeepSeek V4.1 Flash and GLM-4.5 share?

16 benchmarks have published results for both models. DeepSeek V4.1 Flash has 25 scored results on Noometry and GLM-4.5 has 27.