# DeepSeek V4.1 Flash vs GLM-4.7

> DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 42.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v4-1-flash-vs-glm-4-7
- Last updated: 2026-10-10
- Shared benchmarks: 26

## Summary

- They share 26 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 9 categories and GLM-4.7 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 38.6.
- The biggest single-benchmark swing is ProofBench: 54% for DeepSeek V4.1 Flash and 6% for GLM-4.7.
- DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.60 / $2.20 for GLM-4.7.
- DeepSeek V4.1 Flash accepts more context: 1M tokens versus 205K.

## Snapshot

| | DeepSeek V4.1 Flash | GLM-4.7 |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 52.8 | 42.0 |
| Rank | 38 | 124 |
| 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-4.7: 44.0 (#79)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.7 |
|---|---|---|
| LMArena WebDev | 1619 | 1435 |
| SciCode | 51.9% | 45.1% |
| LMArena Coding | 1506 | 1454 |
| ALE-Bench | 1,092 | 399.48 |

## Agentic & Tool Use

- DeepSeek V4.1 Flash: 31.2 (#69)
- GLM-4.7: 26.5 (#103)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.7 |
|---|---|---|
| Terminal-Bench | — | 33.4% |
| APEX-Agents | 39.5% | — |
| GDP.pdf | 19.8% | — |
| Vending-Bench 2 | — | 2,377 |

## Reasoning

- DeepSeek V4.1 Flash: 50.2 (#36)
- GLM-4.7: 24.3 (#164)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.7 |
|---|---|---|
| CritPt | 14.3% | 1.7% |
| LMArena Hard Prompts | 1483 | 1443 |
| Epoch Capabilities Index | 154.9 | 143.51 |
| SimpleBench | — | 47.7% |
| NYT Connections (extended) | 89.6% | — |
| Chess Puzzles | — | 6% |
| Mystery Game Puzzles | 43% | — |
| DTBench | 89.9% | — |
| LMCA | 47% | — |
| Surface Evolver Bench | 46.3% | — |

## Math

- DeepSeek V4.1 Flash: 66.7 (#25)
- GLM-4.7: 38.6 (#135)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.7 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.3% | 83.3% |
| ProofBench | 54% | 6% |
| LMArena Math | 1477 | 1423 |
| FrontierMath (Tiers 1-3) | 67.4% | — |
| FrontierMath Tier 4 | 26.8% | — |
| FrontierMath (Feb 2025 set) | — | 2.4% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- DeepSeek V4.1 Flash: 57.9 (#38)
- GLM-4.7: 47.0 (#80)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.7 |
|---|---|---|
| GPQA Diamond | 89.8% | 83.3% |
| LMArena Expert | 1506 | 1424 |
| SimpleQA Verified | — | 32.2% |
| Vectara Hallucination Rate | — | 11.7% |

## Multimodal

- DeepSeek V4.1 Flash: 39.1 (#61)
- GLM-4.7: —

| Benchmark | DeepSeek V4.1 Flash | GLM-4.7 |
|---|---|---|
| LMArena Vision | 1277 | — |
| Furniture Assembly | 34.2% | — |

## Multilingual

- DeepSeek V4.1 Flash: 55.0 (#35)
- GLM-4.7: 52.8 (#79)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.7 |
|---|---|---|
| LMArena Non-English | 1448 | 1417 |
| LMArena Chinese | 1497 | 1495 |
| LMArena French | 1452 | 1432 |
| LMArena German | 1484 | 1424 |
| LMArena Japanese | 1412 | 1439 |
| LMArena Korean | 1452 | 1399 |
| LMArena Russian | 1471 | 1423 |
| LMArena Spanish | 1459 | 1434 |

## Instruction Following

- DeepSeek V4.1 Flash: 77.3 (#26)
- GLM-4.7: 74.4 (#95)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.7 |
|---|---|---|
| LMArena Instruction Following | 1474 | 1411 |

## Long Context

- DeepSeek V4.1 Flash: 45.2 (#47)
- GLM-4.7: 42.8 (#116)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.7 |
|---|---|---|
| LMArena Longer Query | 1475 | 1432 |
| CL-bench | — | 15.9% |
| CL-bench Life | — | 10.9% |

## Writing & Preference

- DeepSeek V4.1 Flash: 65.4 (#48)
- GLM-4.7: 60.9 (#93)

| Benchmark | DeepSeek V4.1 Flash | GLM-4.7 |
|---|---|---|
| LMArena Text | 1462 | 1435 |
| LMArena Creative Writing | 1435 | 1401 |
| EQ-Bench Creative Writing | 1540 | 1413 |
| LMArena Multi-Turn | 1457 | 1446 |

## FAQ

### Is DeepSeek V4.1 Flash better than GLM-4.7?

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 42.0 on the Noometry Index.

### Which is cheaper, DeepSeek V4.1 Flash or GLM-4.7?

DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GLM-4.7 lists at $0.60 and $2.20.

### Is DeepSeek V4.1 Flash or GLM-4.7 better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 44.0 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-4.7 share?

26 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and GLM-4.7 has 36.