# DeepSeek V4.1 Flash vs GLM-5.2

> DeepSeek V4.1 Flash and GLM-5.2 score almost the same on the Noometry Index (50.3 vs 50.9), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/deepseek-v4-1-flash-vs-glm-5-2
- Last updated: 2026-10-10
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 3 categories and GLM-5.2 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.2 leads 57.1 to 41.6.
- The biggest single-benchmark swing is ProofBench: 54% for DeepSeek V4.1 Flash and 35% for GLM-5.2.
- DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.40 / $4.40 for GLM-5.2.

## Snapshot

| | DeepSeek V4.1 Flash | GLM-5.2 |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 50.3 | 50.9 |
| Rank | 40 | 38 |
| Context | 1M | 1M |
| Input $/M | $0.15 | $1.40 |
| Output $/M | $0.60 | $4.40 |
| Weights | Open | Open |

## Coding

- DeepSeek V4.1 Flash: 52.8 (#29)
- GLM-5.2: 50.9 (#37)

| Benchmark | DeepSeek V4.1 Flash | GLM-5.2 |
|---|---|---|
| LMArena WebDev | 1620 | 1604 |
| SciCode | 51.9% | 50.5% |
| LMArena Coding | 1511 | 1484 |
| ALE-Bench | 1,092 | 1,047 |
| SWE-bench Verified | — | 78.7% |
| DeepSWE | — | 43.8% |
| FrontierCode | — | 24.5% |
| WeirdML | — | 70.1% |

## Agentic & Tool Use

- DeepSeek V4.1 Flash: —
- GLM-5.2: 31.6 (#63)

| Benchmark | DeepSeek V4.1 Flash | GLM-5.2 |
|---|---|---|
| τ²-bench Banking | — | 37.1% |
| PostTrainBench | — | 31.7% |
| GBAEval | — | 0% |
| Vending-Bench 2 | — | 8,314 |

## Reasoning

- DeepSeek V4.1 Flash: 46.2 (#39)
- GLM-5.2: 42.1 (#46)

| Benchmark | DeepSeek V4.1 Flash | GLM-5.2 |
|---|---|---|
| NYT Connections (extended) | 89.6% | 74.3% |
| CritPt | 14.3% | 20.9% |
| LMArena Hard Prompts | 1485 | 1480 |
| DTBench | 89.9% | 93.6% |
| LMCA | 47% | 45.8% |
| Surface Evolver Bench | 46.3% | 55.6% |
| Epoch Capabilities Index | 155.01 | 151.76 |
| ARC-AGI-2 | — | 22.8% |
| SimpleBench | — | 58.8% |
| Kagi LLM Benchmark | — | 62.6% |
| ARC-AGI-1 | — | 77% |
| Chess Puzzles | — | 21% |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 19% |

## Math

- DeepSeek V4.1 Flash: 48.4 (#52)
- GLM-5.2: 55.4 (#35)

| Benchmark | DeepSeek V4.1 Flash | GLM-5.2 |
|---|---|---|
| ProofBench | 54% | 35% |
| LMArena Math | 1493 | 1482 |
| FrontierMath (Tiers 1-3) | — | 59.2% |
| FrontierMath Tier 4 | — | 29.3% |
| MathArena Final-Answer Competitions | — | 67.6% |
| OTIS Mock AIME 2024-2025 | — | 86.4% |

## Knowledge

- DeepSeek V4.1 Flash: 41.6 (#97)
- GLM-5.2: 57.1 (#36)

| Benchmark | DeepSeek V4.1 Flash | GLM-5.2 |
|---|---|---|
| LMArena Expert | 1505 | 1484 |
| GPQA Diamond | — | 91.9% |
| SimpleQA Verified | — | 34.2% |

## Multilingual

- DeepSeek V4.1 Flash: 55.5 (#29)
- GLM-5.2: 56.0 (#25)

| Benchmark | DeepSeek V4.1 Flash | GLM-5.2 |
|---|---|---|
| LMArena Non-English | 1452 | 1459 |
| LMArena Chinese | 1506 | 1518 |
| LMArena French | 1448 | 1476 |
| LMArena Russian | 1473 | 1467 |
| LMArena Spanish | 1499 | 1477 |
| LMArena German | — | 1470 |
| LMArena Japanese | — | 1451 |
| LMArena Korean | — | 1445 |

## Instruction Following

- DeepSeek V4.1 Flash: 77.6 (#24)
- GLM-5.2: 77.1 (#32)

| Benchmark | DeepSeek V4.1 Flash | GLM-5.2 |
|---|---|---|
| LMArena Instruction Following | 1475 | 1465 |

## Long Context

- DeepSeek V4.1 Flash: 45.2 (#46)
- GLM-5.2: 45.3 (#43)

| Benchmark | DeepSeek V4.1 Flash | GLM-5.2 |
|---|---|---|
| LMArena Longer Query | 1476 | 1479 |

## Writing & Preference

- DeepSeek V4.1 Flash: 65.8 (#43)
- GLM-5.2: 70.7 (#20)

| Benchmark | DeepSeek V4.1 Flash | GLM-5.2 |
|---|---|---|
| LMArena Text | 1465 | 1470 |
| LMArena Creative Writing | 1436 | 1465 |
| EQ-Bench Creative Writing | 1540 | 1757 |
| LMArena Multi-Turn | 1460 | 1468 |
| EQ-Bench 4 | — | 1222 |

## FAQ

### Is DeepSeek V4.1 Flash better than GLM-5.2?

DeepSeek V4.1 Flash and GLM-5.2 score almost the same on the Noometry Index (50.3 vs 50.9), so choose on price, context window or the category you care about most.

### Which is cheaper, DeepSeek V4.1 Flash or GLM-5.2?

DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GLM-5.2 lists at $1.40 and $4.40.

### Is DeepSeek V4.1 Flash or GLM-5.2 better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.8 versus 50.9 in the Noometry coding category.

### Which has the bigger context window?

Both accept 1M tokens.

### How many benchmarks do DeepSeek V4.1 Flash and GLM-5.2 share?

25 benchmarks have published results for both models. DeepSeek V4.1 Flash has 25 scored results on Noometry and GLM-5.2 has 50.