Model comparison
GLM-4.6 vs Qwen3.7 Plus
Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 40.9 on the Noometry Index.
Last verified . 19 shared benchmarks.
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. GLM-4.6 scores higher in 2 categories and Qwen3.7 Plus in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.7 Plus leads 38.4 to 23.1.
- The biggest single-benchmark swing is CritPt: 1.1% for GLM-4.6 and 9.1% for Qwen3.7 Plus.
- Qwen3.7 Plus is cheaper at $0.40 / $1.60 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
- Qwen3.7 Plus accepts more context: 1M tokens versus 205K.
- GLM-4.6 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.6 | Qwen3.7 Plus | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 40.9 | 45.0 |
| Released | 2025-09-30 | 2026-06-02 |
| Weights | Open | Proprietary |
| Context window | 205K | 1M |
| Max output | 131K | 131K |
| Input $ / M tokens | $0.60 | $0.40 |
| Output $ / M tokens | $2.20 | $1.60 |
| Results tracked | 29 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6 leads
GLM-4.6: 39.9 (#137), Qwen3.7 Plus: 36.1 (#200)
| Benchmark | GLM-4.6 | Qwen3.7 Plus |
|---|---|---|
| SciCode | 38.4% | 45.5% |
| LMArena Coding | 1449 | 1473 |
| FrontierCode | — | 10.2% |
| SWE-bench Verified (bash only) | 55.4% | — |
| LMArena WebDev | 1339 | — |
| ALE-Bench | 340.82 | — |
Agentic & Tool Use GLM-4.6 leads
GLM-4.6: 32.1 (#60), Qwen3.7 Plus: 21.2 (#130)
| Benchmark | GLM-4.6 | Qwen3.7 Plus |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |
| OSWorld 2.0 | — | 2.8% |
Reasoning Qwen3.7 Plus leads
GLM-4.6: 23.1 (#168), Qwen3.7 Plus: 38.4 (#54)
| Benchmark | GLM-4.6 | Qwen3.7 Plus |
|---|---|---|
| CritPt | 1.1% | 9.1% |
| LMArena Hard Prompts | 1440 | 1460 |
| Kagi LLM Benchmark | 47.4% | — |
| NYT Connections (extended) | — | 74.8% |
| Chess Puzzles | — | 24% |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84% |
| LMCA | — | 37.6% |
| Epoch Capabilities Index | — | 147.39 |
Math Qwen3.7 Plus leads
GLM-4.6: 36.4 (#115), Qwen3.7 Plus: 49.3 (#47)
| Benchmark | GLM-4.6 | Qwen3.7 Plus |
|---|---|---|
| LMArena Math | 1431 | 1467 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Qwen3.7 Plus leads
GLM-4.6: 39.6 (#118), Qwen3.7 Plus: 54.9 (#46)
| Benchmark | GLM-4.6 | Qwen3.7 Plus |
|---|---|---|
| LMArena Expert | 1432 | 1467 |
| GPQA Diamond | — | 87.9% |
| Vectara Hallucination Rate | 9.5% | — |
Multimodal Not comparable
GLM-4.6: —, Qwen3.7 Plus: 41.2 (#30)
| Benchmark | GLM-4.6 | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1281 |
| LMArena Document | — | 1444 |
Multilingual Qwen3.7 Plus leads
GLM-4.6: 53.6 (#62), Qwen3.7 Plus: 55.0 (#36)
| Benchmark | GLM-4.6 | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1426 | 1445 |
| LMArena Chinese | 1500 | 1510 |
| LMArena French | 1459 | 1471 |
| LMArena German | 1447 | 1471 |
| LMArena Japanese | 1394 | 1411 |
| LMArena Korean | 1401 | 1416 |
| LMArena Russian | 1418 | 1457 |
| LMArena Spanish | 1436 | 1453 |
Instruction Following Qwen3.7 Plus leads
GLM-4.6: 74.5 (#93), Qwen3.7 Plus: 75.9 (#49)
| Benchmark | GLM-4.6 | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1410 | 1439 |
Long Context Qwen3.7 Plus leads
GLM-4.6: 43.4 (#91), Qwen3.7 Plus: 44.5 (#61)
| Benchmark | GLM-4.6 | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1423 | 1454 |
Writing & Preference Qwen3.7 Plus leads
GLM-4.6: 61.3 (#86), Qwen3.7 Plus: 64.5 (#54)
| Benchmark | GLM-4.6 | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1440 | 1454 |
| LMArena Creative Writing | 1411 | 1439 |
| LMArena Multi-Turn | 1427 | 1459 |
| EQ-Bench Creative Writing | 1411 | — |
Frequently asked questions
Is GLM-4.6 better than Qwen3.7 Plus?
Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 40.9 on the Noometry Index.
Which is cheaper, GLM-4.6 or Qwen3.7 Plus?
Qwen3.7 Plus is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; GLM-4.6 lists at $0.60 and $2.20.
Is GLM-4.6 or Qwen3.7 Plus better for coding?
GLM-4.6 scores higher on coding benchmarks: 39.9 versus 36.1 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Plus does, with 1M tokens against 205K.
How many benchmarks do GLM-4.6 and Qwen3.7 Plus share?
19 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Qwen3.7 Plus has 32.