Model comparison
GLM-5.2 vs Qwen3.6 Max Preview
GLM-5.2 and Qwen3.6 Max Preview score almost the same on the Noometry Index (51.1 vs 51.5), so choose on price, context window or the category you care about most.
Last verified . 27 shared benchmarks.
Alibaba (Qwen)Summary
- They share 27 benchmarks with published results for both. GLM-5.2 scores higher in 7 categories and Qwen3.6 Max Preview in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5.2 leads 70.4 to 63.8.
- The biggest single-benchmark swing is SimpleQA Verified: 34.2% for GLM-5.2 and 52% for Qwen3.6 Max Preview.
- GLM-5.2 is cheaper at $1.40 / $4.40 per million input/output tokens, against $1.30 / $7.80 for Qwen3.6 Max Preview.
- GLM-5.2 accepts more context: 1M tokens versus 262K.
- GLM-5.2 has downloadable open weights; the other is API-only.
Side by side
| GLM-5.2 | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 51.1 | 51.5 |
| Released | 2026-06-13 | 2026-04-20 |
| Weights | Open | Proprietary |
| Context window | 1M | 262K |
| Max output | 131K | 66K |
| Input $ / M tokens | $1.40 | $1.30 |
| Output $ / M tokens | $4.40 | $7.80 |
| Results tracked | 51 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.2 leads
GLM-5.2: 51.3 (#41), Qwen3.6 Max Preview: 48.7 (#54)
| Benchmark | GLM-5.2 | Qwen3.6 Max Preview |
|---|---|---|
| SWE-bench Verified | 78.7% | 76.7% |
| LMArena WebDev | 1603 | 1482 |
| LMArena Coding | 1485 | 1471 |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| SciCode | 50.5% | — |
| WeirdML | 70.1% | — |
| ALE-Bench | 1,047 | — |
Agentic & Tool Use Not comparable
GLM-5.2: 32.4 (#63), Qwen3.6 Max Preview: —
| Benchmark | GLM-5.2 | Qwen3.6 Max Preview |
|---|---|---|
| Vending-Bench 2 | 8,314 | 4,254 |
| APEX-Agents | 45.2% | — |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |
Reasoning Too close to call
GLM-5.2: 42.3 (#52), Qwen3.6 Max Preview: 41.7 (#53)
| Benchmark | GLM-5.2 | Qwen3.6 Max Preview |
|---|---|---|
| SimpleBench | 58.8% | 63% |
| NYT Connections (extended) | 74.3% | 74.1% |
| Chess Puzzles | 21% | 20% |
| LMArena Hard Prompts | 1480 | 1457 |
| Mystery Game Puzzles | 19% | 19% |
| DTBench | 93.6% | 87.2% |
| LMCA | 45.8% | 42.5% |
| Epoch Capabilities Index | 151.78 | 149.24 |
| ARC-AGI-2 | 22.8% | — |
| Kagi LLM Benchmark | 62.6% | — |
| ARC-AGI-1 | 77% | — |
| CritPt | 20.9% | — |
| EBR-Bench | 9.5% | — |
| Surface Evolver Bench | 55.6% | — |
Math GLM-5.2 leads
GLM-5.2: 55.7 (#43), Qwen3.6 Max Preview: 54.1 (#46)
| Benchmark | GLM-5.2 | Qwen3.6 Max Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.4% | 91.1% |
| LMArena Math | 1482 | 1465 |
| FrontierMath (Tiers 1-3) | 59.2% | — |
| FrontierMath Tier 4 | 29.3% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| ProofBench | 35% | — |
| FrontierMath (Feb 2025 set) | — | 23.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Too close to call
GLM-5.2: 57.1 (#40), Qwen3.6 Max Preview: 57.6 (#39)
| Benchmark | GLM-5.2 | Qwen3.6 Max Preview |
|---|---|---|
| GPQA Diamond | 91.9% | 87.4% |
| SimpleQA Verified | 34.2% | 52% |
| LMArena Expert | 1486 | 1478 |
Multilingual GLM-5.2 leads
GLM-5.2: 55.8 (#26), Qwen3.6 Max Preview: 54.2 (#48)
| Benchmark | GLM-5.2 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1459 | 1437 |
| LMArena Chinese | 1519 | 1487 |
| LMArena French | 1479 | 1449 |
| LMArena Russian | 1466 | 1445 |
| LMArena Spanish | 1477 | 1454 |
| LMArena German | 1468 | — |
| LMArena Japanese | 1451 | — |
| LMArena Korean | 1445 | — |
Instruction Following GLM-5.2 leads
GLM-5.2: 76.9 (#34), Qwen3.6 Max Preview: 75.7 (#55)
| Benchmark | GLM-5.2 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1465 | 1438 |
Long Context Too close to call
GLM-5.2: 45.3 (#43), Qwen3.6 Max Preview: 44.6 (#61)
| Benchmark | GLM-5.2 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1479 | 1457 |
Writing & Preference GLM-5.2 leads
GLM-5.2: 70.4 (#21), Qwen3.6 Max Preview: 63.8 (#60)
| Benchmark | GLM-5.2 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1470 | 1447 |
| LMArena Creative Writing | 1462 | 1435 |
| LMArena Multi-Turn | 1469 | 1456 |
| EQ-Bench Creative Writing | 1757 | — |
| EQ-Bench 4 | 1222 | — |
Frequently asked questions
Is GLM-5.2 better than Qwen3.6 Max Preview?
GLM-5.2 and Qwen3.6 Max Preview score almost the same on the Noometry Index (51.1 vs 51.5), so choose on price, context window or the category you care about most.
Which is cheaper, GLM-5.2 or Qwen3.6 Max Preview?
GLM-5.2 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; Qwen3.6 Max Preview lists at $1.30 and $7.80.
Is GLM-5.2 or Qwen3.6 Max Preview better for coding?
GLM-5.2 scores higher on coding benchmarks: 51.3 versus 48.7 in the Noometry coding category.
Which has the bigger context window?
GLM-5.2 does, with 1M tokens against 262K.
How many benchmarks do GLM-5.2 and Qwen3.6 Max Preview share?
27 benchmarks have published results for both models. GLM-5.2 has 51 scored results on Noometry and Qwen3.6 Max Preview has 29.