# DeepSeek-V3.1 vs GLM-4.7-Flash

> DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 38.8 on the Noometry Index. GLM-4.7-Flash costs 2.9× less per token, which makes it the better buy when DeepSeek-V3.1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-vs-glm-4-7-flash
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 6 categories and GLM-4.7-Flash in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.3 to 47.4.
- GLM-4.7-Flash is cheaper at $0.06 / $0.40 per million input/output tokens, against $0.25 / $0.95 for DeepSeek-V3.1.
- GLM-4.7-Flash accepts more context: 200K tokens versus 164K.

## Snapshot

| | DeepSeek-V3.1 | GLM-4.7-Flash |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 42.8 | 38.8 |
| Rank | 108 | 180 |
| Context | 164K | 200K |
| Input $/M | $0.25 | $0.06 |
| Output $/M | $0.95 | $0.40 |
| Weights | Open | Open |

## Coding

- DeepSeek-V3.1: 40.3 (#144)
- GLM-4.7-Flash: 40.6 (#135)

| Benchmark | DeepSeek-V3.1 | GLM-4.7-Flash |
|---|---|---|
| LMArena Coding | 1417 | 1383 |
| WeirdML | 38.4% | — |

## Reasoning

- DeepSeek-V3.1: 27.9 (#110)
- GLM-4.7-Flash: 20.9 (#229)

| Benchmark | DeepSeek-V3.1 | GLM-4.7-Flash |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1356 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| Chess Puzzles | — | 0% |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |

## Math

- DeepSeek-V3.1: 38.9 (#122)
- GLM-4.7-Flash: 36.1 (#173)

| Benchmark | DeepSeek-V3.1 | GLM-4.7-Flash |
|---|---|---|
| LMArena Math | 1420 | 1355 |
| OTIS Mock AIME 2024-2025 | — | 58.3% |

## Knowledge

- DeepSeek-V3.1: 43.7 (#90)
- GLM-4.7-Flash: 35.5 (#184)

| Benchmark | DeepSeek-V3.1 | GLM-4.7-Flash |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | 9.3% |
| LMArena Expert | 1405 | 1357 |
| GPQA Diamond | — | 60.5% |

## Multilingual

- DeepSeek-V3.1: 51.6 (#106)
- GLM-4.7-Flash: 46.5 (#158)

| Benchmark | DeepSeek-V3.1 | GLM-4.7-Flash |
|---|---|---|
| LMArena Non-English | 1400 | 1330 |
| LMArena Chinese | 1469 | 1403 |
| LMArena French | 1447 | 1332 |
| LMArena German | 1411 | 1337 |
| LMArena Korean | 1337 | 1283 |
| LMArena Russian | 1405 | 1332 |
| LMArena Spanish | 1431 | 1350 |
| LMArena Japanese | 1378 | — |

## Instruction Following

- DeepSeek-V3.1: 73.9 (#110)
- GLM-4.7-Flash: 70.1 (#167)

| Benchmark | DeepSeek-V3.1 | GLM-4.7-Flash |
|---|---|---|
| LMArena Instruction Following | 1400 | 1327 |

## Long Context

- DeepSeek-V3.1: 36.3 (#232)
- GLM-4.7-Flash: 40.9 (#148)

| Benchmark | DeepSeek-V3.1 | GLM-4.7-Flash |
|---|---|---|
| LMArena Longer Query | 1422 | 1345 |
| Fiction.LiveBench | 52.8% | — |

## Writing & Preference

- DeepSeek-V3.1: 60.3 (#98)
- GLM-4.7-Flash: 47.4 (#210)

| Benchmark | DeepSeek-V3.1 | GLM-4.7-Flash |
|---|---|---|
| LMArena Text | 1420 | 1351 |
| LMArena Creative Writing | 1401 | 1297 |
| EQ-Bench Creative Writing | 1436 | 1125 |
| LMArena Multi-Turn | 1408 | 1342 |

## FAQ

### Is DeepSeek-V3.1 better than GLM-4.7-Flash?

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 38.8 on the Noometry Index. GLM-4.7-Flash costs 2.9× less per token, which makes it the better buy when DeepSeek-V3.1's lead doesn't matter for your workload.

### Which is cheaper, DeepSeek-V3.1 or GLM-4.7-Flash?

GLM-4.7-Flash is cheaper. It lists at $0.06 per million input tokens and $0.40 per million output tokens; DeepSeek-V3.1 lists at $0.25 and $0.95.

### Is DeepSeek-V3.1 or GLM-4.7-Flash better for coding?

They score almost the same on coding (40.3 vs 40.6); test both on your own repository before choosing.

### Which has the bigger context window?

GLM-4.7-Flash does, with 200K tokens against 164K.

### How many benchmarks do DeepSeek-V3.1 and GLM-4.7-Flash share?

18 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and GLM-4.7-Flash has 21.