# GLM-5.2 vs Qwen3.5-Flash

> GLM-5.2 is the stronger model overall, scoring 50.9 to 42.3 on the Noometry Index. Qwen3.5-Flash costs 12× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-5-2-vs-qwen3-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 29

## Summary

- They share 29 benchmarks with published results for both. GLM-5.2 scores higher in 8 categories and Qwen3.5-Flash in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.2 leads 55.4 to 36.3.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 59.2% for GLM-5.2 and 18.2% for Qwen3.5-Flash.
- Qwen3.5-Flash is cheaper at $0.10 / $0.40 per million input/output tokens, against $1.40 / $4.40 for GLM-5.2.
- GLM-5.2 has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-5.2 | Qwen3.5-Flash |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 50.9 | 42.3 |
| Rank | 38 | 105 |
| Context | 1M | 1M |
| Input $/M | $1.40 | $0.10 |
| Output $/M | $4.40 | $0.40 |
| Weights | Open | Proprietary |

## Coding

- GLM-5.2: 50.9 (#37)
- Qwen3.5-Flash: 33.9 (#234)

| Benchmark | GLM-5.2 | Qwen3.5-Flash |
|---|---|---|
| LMArena WebDev | 1604 | 1243 |
| LMArena Coding | 1484 | 1412 |
| ALE-Bench | 1,047 | 221.8 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| SciCode | 50.5% | — |
| WeirdML | 70.1% | — |

## Agentic & Tool Use

- GLM-5.2: 31.6 (#63)
- Qwen3.5-Flash: —

| Benchmark | GLM-5.2 | Qwen3.5-Flash |
|---|---|---|
| Vending-Bench 2 | 8,314 | 462.69 |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |

## Reasoning

- GLM-5.2: 42.1 (#46)
- Qwen3.5-Flash: 32.9 (#63)

| Benchmark | GLM-5.2 | Qwen3.5-Flash |
|---|---|---|
| Chess Puzzles | 21% | 21% |
| LMArena Hard Prompts | 1480 | 1404 |
| Mystery Game Puzzles | 19% | 20% |
| DTBench | 93.6% | 82.9% |
| LMCA | 45.8% | 29.1% |
| Epoch Capabilities Index | 151.76 | 143.98 |
| ARC-AGI-2 | 22.8% | — |
| SimpleBench | 58.8% | — |
| Kagi LLM Benchmark | 62.6% | — |
| NYT Connections (extended) | 74.3% | — |
| ARC-AGI-1 | 77% | — |
| CritPt | 20.9% | — |
| EBR-Bench | 9.5% | — |
| Surface Evolver Bench | 55.6% | — |

## Math

- GLM-5.2: 55.4 (#35)
- Qwen3.5-Flash: 36.3 (#117)

| Benchmark | GLM-5.2 | Qwen3.5-Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 59.2% | 18.2% |
| OTIS Mock AIME 2024-2025 | 86.4% | 84.4% |
| LMArena Math | 1482 | 1407 |
| FrontierMath Tier 4 | 29.3% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| ProofBench | 35% | — |
| FrontierMath (Feb 2025 set) | — | 6.2% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- GLM-5.2: 57.1 (#36)
- Qwen3.5-Flash: 43.2 (#84)

| Benchmark | GLM-5.2 | Qwen3.5-Flash |
|---|---|---|
| GPQA Diamond | 91.9% | 82.3% |
| SimpleQA Verified | 34.2% | 20.3% |
| LMArena Expert | 1484 | 1408 |
| Vectara Hallucination Rate | — | 10.5% |

## Multilingual

- GLM-5.2: 56.0 (#25)
- Qwen3.5-Flash: 50.7 (#116)

| Benchmark | GLM-5.2 | Qwen3.5-Flash |
|---|---|---|
| LMArena Non-English | 1459 | 1385 |
| LMArena Chinese | 1518 | 1446 |
| LMArena French | 1476 | 1412 |
| LMArena German | 1470 | 1389 |
| LMArena Japanese | 1451 | 1369 |
| LMArena Korean | 1445 | 1344 |
| LMArena Russian | 1467 | 1379 |
| LMArena Spanish | 1477 | 1399 |

## Instruction Following

- GLM-5.2: 77.1 (#32)
- Qwen3.5-Flash: 72.8 (#133)

| Benchmark | GLM-5.2 | Qwen3.5-Flash |
|---|---|---|
| LMArena Instruction Following | 1465 | 1374 |

## Long Context

- GLM-5.2: 45.3 (#43)
- Qwen3.5-Flash: 42.4 (#119)

| Benchmark | GLM-5.2 | Qwen3.5-Flash |
|---|---|---|
| LMArena Longer Query | 1479 | 1392 |

## Writing & Preference

- GLM-5.2: 70.7 (#20)
- Qwen3.5-Flash: 58.2 (#117)

| Benchmark | GLM-5.2 | Qwen3.5-Flash |
|---|---|---|
| LMArena Text | 1470 | 1397 |
| LMArena Creative Writing | 1465 | 1343 |
| LMArena Multi-Turn | 1468 | 1393 |
| EQ-Bench Creative Writing | 1757 | — |
| EQ-Bench 4 | 1222 | — |

## FAQ

### Is GLM-5.2 better than Qwen3.5-Flash?

GLM-5.2 is the stronger model overall, scoring 50.9 to 42.3 on the Noometry Index. Qwen3.5-Flash costs 12× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.

### Which is cheaper, GLM-5.2 or Qwen3.5-Flash?

Qwen3.5-Flash is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; GLM-5.2 lists at $1.40 and $4.40.

### Is GLM-5.2 or Qwen3.5-Flash better for coding?

GLM-5.2 scores higher on coding benchmarks: 50.9 versus 33.9 in the Noometry coding category.

### Which has the bigger context window?

Both accept 1M tokens.

### How many benchmarks do GLM-5.2 and Qwen3.5-Flash share?

29 benchmarks have published results for both models. GLM-5.2 has 50 scored results on Noometry and Qwen3.5-Flash has 32.