Model comparison
GLM-5 vs Qwen3.6 Plus
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 46.1 on the Noometry Index.
Last verified . 29 shared benchmarks.
Alibaba (Qwen)Summary
- They share 29 benchmarks with published results for both. GLM-5 scores higher in 4 categories and Qwen3.6 Plus in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in coding, where GLM-5 leads 49.0 to 40.8.
- The biggest single-benchmark swing is NYT Connections (extended): 74.8% for GLM-5 and 60.3% for Qwen3.6 Plus.
- Qwen3.6 Plus is cheaper at $0.50 / $3 per million input/output tokens, against $1 / $3.20 for GLM-5.
- Qwen3.6 Plus accepts more context: 1M tokens versus 205K.
- GLM-5 has downloadable open weights; the other is API-only.
Side by side
| GLM-5 | Qwen3.6 Plus | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 46.1 | 47.5 |
| Released | 2026-02-11 | 2026-03-31 |
| Weights | Open | Proprietary |
| Context window | 205K | 1M |
| Max output | 131K | 66K |
| Input $ / M tokens | $1 | $0.50 |
| Output $ / M tokens | $3.20 | $3 |
| Results tracked | 45 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#52), Qwen3.6 Plus: 40.8 (#130)
| Benchmark | GLM-5 | Qwen3.6 Plus |
|---|---|---|
| SWE-bench Verified | 72.1% | 57.9% |
| LMArena WebDev | 1434 | 1461 |
| LMArena Coding | 1461 | 1467 |
| ALE-Bench | 765.62 | 670.15 |
| SWE-bench Verified (bash only) | 72.8% | — |
| SWE-bench Multilingual | 69.7% | — |
| SciCode | — | 40.7% |
| WeirdML | 48.2% | — |
Agentic & Tool Use Not comparable
GLM-5: 31.1 (#71), Qwen3.6 Plus: —
| Benchmark | GLM-5 | Qwen3.6 Plus |
|---|---|---|
| Vending-Bench 2 | 4,432 | 5,115 |
| Terminal-Bench | 52.4% | — |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |
Reasoning Qwen3.6 Plus leads
GLM-5: 27.6 (#116), Qwen3.6 Plus: 29.3 (#93)
| Benchmark | GLM-5 | Qwen3.6 Plus |
|---|---|---|
| NYT Connections (extended) | 74.8% | 60.3% |
| Chess Puzzles | 10% | 17% |
| LMArena Hard Prompts | 1452 | 1449 |
| Epoch Capabilities Index | 145.83 | 147.65 |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 53.2% | — |
| Kagi LLM Benchmark | 75% | — |
| ARC-AGI-1 | 44.7% | — |
| CritPt | — | 2.9% |
| Thematic Generalization | — | 59.5% |
| Mystery Game Puzzles | — | 12% |
| DTBench | — | 81.9% |
| LMCA | — | 33.1% |
| ForecastBench | 61 | — |
Math Qwen3.6 Plus leads
GLM-5: 46.4 (#71), Qwen3.6 Plus: 51.8 (#54)
| Benchmark | GLM-5 | Qwen3.6 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 93.3% |
| LMArena Math | 1440 | 1450 |
| FrontierMath (Feb 2025 set) | 16.4% | 26.2% |
| FrontierMath Tier 4 (v1) | 2.1% | 8.3% |
| FrontierMath (Tiers 1-3) | — | 38.2% |
| MathArena Final-Answer Competitions | 65.7% | — |
Knowledge Qwen3.6 Plus leads
GLM-5: 52.3 (#64), Qwen3.6 Plus: 56.1 (#45)
| Benchmark | GLM-5 | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 87.8% | 88.4% |
| LMArena Expert | 1454 | 1454 |
| SimpleQA Verified | — | 44.1% |
| Vectara Hallucination Rate | 10.1% | — |
Multilingual Too close to call
GLM-5: 53.7 (#58), Qwen3.6 Plus: 53.3 (#70)
| Benchmark | GLM-5 | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1430 | 1424 |
| LMArena Chinese | 1511 | 1477 |
| LMArena French | 1455 | 1455 |
| LMArena German | 1445 | 1452 |
| LMArena Japanese | 1416 | 1389 |
| LMArena Korean | 1423 | 1379 |
| LMArena Russian | 1436 | 1434 |
| LMArena Spanish | 1454 | 1432 |
Instruction Following Too close to call
GLM-5: 75.2 (#67), Qwen3.6 Plus: 75.0 (#74)
| Benchmark | GLM-5 | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1428 | 1425 |
Long Context Too close to call
GLM-5: 44.7 (#60), Qwen3.6 Plus: 45.2 (#49)
| Benchmark | GLM-5 | Qwen3.6 Plus |
|---|---|---|
| CL-bench | 18.7% | 20.3% |
| LMArena Longer Query | 1446 | 1439 |
Writing & Preference GLM-5 leads
GLM-5: 66.0 (#38), Qwen3.6 Plus: 62.2 (#82)
| Benchmark | GLM-5 | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1446 | 1437 |
| LMArena Creative Writing | 1439 | 1404 |
| LMArena Multi-Turn | 1456 | 1438 |
| EQ-Bench Creative Writing | 1601 | — |
Frequently asked questions
Is GLM-5 better than Qwen3.6 Plus?
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 46.1 on the Noometry Index.
Which is cheaper, GLM-5 or Qwen3.6 Plus?
Qwen3.6 Plus is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; GLM-5 lists at $1 and $3.20.
Is GLM-5 or Qwen3.6 Plus better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Plus does, with 1M tokens against 205K.
How many benchmarks do GLM-5 and Qwen3.6 Plus share?
29 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and Qwen3.6 Plus has 37.