# DeepSeek V4.1 Flash vs GLM-4.6

> DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 41.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v4-1-flash-vs-glm-4-6
- Last updated: 2026-10-12
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and GLM-4.6 in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 39.1.
- The biggest single-benchmark swing is SciCode: 51.9% for DeepSeek V4.1 Flash and 38.4% for GLM-4.6.
- DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
- DeepSeek V4.1 Flash accepts more context: 1M tokens versus 205K.

## Snapshot

| | DeepSeek V4.1 Flash | GLM-4.6 |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 52.8 | 41.4 |
| Rank | 38 | 135 |
| Context | 1M | 205K |
| Input $/M | $0.15 | $0.60 |
| Output $/M | $0.60 | $2.20 |
| Weights | Open | Open |

## Coding

- DeepSeek V4.1 Flash: 52.9 (#32)
- GLM-4.6: 40.1 (#148)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.6 |
|---|---|---|
| LMArena WebDev | 1619 | 1340 |
| SciCode | 51.9% | 38.4% |
| LMArena Coding | 1506 | 1449 |
| ALE-Bench | 1,092 | 340.82 |
| SWE-bench Verified (bash only) | — | 55.4% |

## Agentic & Tool Use

- DeepSeek V4.1 Flash: 31.2 (#69)
- GLM-4.6: 32.3 (#66)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.6 |
|---|---|---|
| Terminal-Bench | — | 24.5% |
| APEX-Agents | 39.5% | — |
| Berkeley Function Calling Leaderboard | — | 72.4% |
| GDP.pdf | 19.8% | — |

## Reasoning

- DeepSeek V4.1 Flash: 50.2 (#36)
- GLM-4.6: 23.7 (#172)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.6 |
|---|---|---|
| CritPt | 14.3% | 1.1% |
| LMArena Hard Prompts | 1483 | 1440 |
| Kagi LLM Benchmark | — | 47.4% |
| NYT Connections (extended) | 89.6% | — |
| Mystery Game Puzzles | 43% | — |
| DTBench | 89.9% | — |
| LMCA | 47% | — |
| Surface Evolver Bench | 46.3% | — |
| Epoch Capabilities Index | 154.9 | — |

## Math

- DeepSeek V4.1 Flash: 66.7 (#25)
- GLM-4.6: 39.1 (#111)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.6 |
|---|---|---|
| LMArena Math | 1477 | 1432 |
| FrontierMath (Tiers 1-3) | 67.4% | — |
| FrontierMath Tier 4 | 26.8% | — |
| OTIS Mock AIME 2024-2025 | 98.3% | — |
| ProofBench | 54% | — |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- DeepSeek V4.1 Flash: 57.9 (#38)
- GLM-4.6: 40.2 (#124)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.6 |
|---|---|---|
| LMArena Expert | 1506 | 1431 |
| GPQA Diamond | 89.8% | — |
| Vectara Hallucination Rate | — | 9.5% |

## Multimodal

- DeepSeek V4.1 Flash: 39.1 (#61)
- GLM-4.6: —

| Benchmark | DeepSeek V4.1 Flash | GLM-4.6 |
|---|---|---|
| LMArena Vision | 1277 | — |
| Furniture Assembly | 34.2% | — |

## Multilingual

- DeepSeek V4.1 Flash: 55.0 (#35)
- GLM-4.6: 53.5 (#66)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.6 |
|---|---|---|
| LMArena Non-English | 1448 | 1426 |
| LMArena Chinese | 1497 | 1499 |
| LMArena French | 1452 | 1459 |
| LMArena German | 1484 | 1447 |
| LMArena Japanese | 1412 | 1393 |
| LMArena Korean | 1452 | 1400 |
| LMArena Russian | 1471 | 1419 |
| LMArena Spanish | 1459 | 1436 |

## Instruction Following

- DeepSeek V4.1 Flash: 77.3 (#26)
- GLM-4.6: 74.3 (#98)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.6 |
|---|---|---|
| LMArena Instruction Following | 1474 | 1410 |

## Long Context

- DeepSeek V4.1 Flash: 45.2 (#47)
- GLM-4.6: 43.4 (#94)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.6 |
|---|---|---|
| LMArena Longer Query | 1475 | 1422 |

## Writing & Preference

- DeepSeek V4.1 Flash: 65.4 (#48)
- GLM-4.6: 61.1 (#90)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.6 |
|---|---|---|
| LMArena Text | 1462 | 1440 |
| LMArena Creative Writing | 1435 | 1411 |
| EQ-Bench Creative Writing | 1540 | 1411 |
| LMArena Multi-Turn | 1457 | 1427 |

## FAQ

### Is DeepSeek V4.1 Flash better than GLM-4.6?

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 41.4 on the Noometry Index.

### Which is cheaper, DeepSeek V4.1 Flash or GLM-4.6?

DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GLM-4.6 lists at $0.60 and $2.20.

### Is DeepSeek V4.1 Flash or GLM-4.6 better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 40.1 in the Noometry coding category.

### Which has the bigger context window?

DeepSeek V4.1 Flash does, with 1M tokens against 205K.

### How many benchmarks do DeepSeek V4.1 Flash and GLM-4.6 share?

22 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and GLM-4.6 has 29.