Model comparison
GLM-5.1 vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.0 to 47.6 on the Noometry Index.
Last verified . 28 shared benchmarks.
Alibaba (Qwen)Summary
- They share 28 benchmarks with published results for both. GLM-5.1 scores higher in 1 category and Qwen3.8 Max in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.1 to 49.0.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 36.8% for GLM-5.1 and 74.7% for Qwen3.8 Max.
- GLM-5.1 is cheaper at $1.40 / $4.40 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- Qwen3.8 Max accepts more context: 1M tokens versus 200K.
- GLM-5.1 has downloadable open weights; the other is API-only.
Side by side
| GLM-5.1 | Qwen3.8 Max | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 47.6 | 56.0 |
| Released | 2026-04-07 | 2026-08-02 |
| Weights | Open | Proprietary |
| Context window | 200K | 1M |
| Max output | 131K | 131K |
| Input $ / M tokens | $1.40 | $2 |
| Output $ / M tokens | $4.40 | $6 |
| Results tracked | 41 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
GLM-5.1: 48.5 (#52), Qwen3.8 Max: 52.3 (#30)
| Benchmark | GLM-5.1 | Qwen3.8 Max |
|---|---|---|
| LMArena WebDev | 1509 | 1671 |
| SciCode | 43.8% | 52.9% |
| LMArena Coding | 1486 | 1499 |
| SWE-bench Verified | 74.2% | — |
| DeepSWE | — | 57.5% |
| FrontierSWE | — | 15.8% |
| WeirdML | 57.1% | — |
| ALE-Bench | 887.1 | — |
Agentic & Tool Use Qwen3.8 Max leads
GLM-5.1: 24.8 (#106), Qwen3.8 Max: 42.6 (#17)
| Benchmark | GLM-5.1 | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | 40.9% | — |
| τ²-bench Banking | — | 55.1% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| GDP.pdf | — | 23.2% |
| Vending-Bench 2 | 5,634 | — |
Reasoning Qwen3.8 Max leads
GLM-5.1: 38.2 (#57), Qwen3.8 Max: 53.4 (#26)
| Benchmark | GLM-5.1 | Qwen3.8 Max |
|---|---|---|
| NYT Connections (extended) | 77.7% | 88.3% |
| CritPt | 4.6% | 20% |
| Chess Puzzles | 19% | 40% |
| LMArena Hard Prompts | 1472 | 1493 |
| Epoch Capabilities Index | 149.86 | 156.69 |
| SimpleBench | 55.1% | — |
| Thematic Generalization | 69.8% | — |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LMCA | — | 46.2% |
Math Qwen3.8 Max leads
GLM-5.1: 49.0 (#48), Qwen3.8 Max: 73.1 (#15)
| Benchmark | GLM-5.1 | Qwen3.8 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | 36.8% | 74.7% |
| OTIS Mock AIME 2024-2025 | 93.3% | 100% |
| ProofBench | 22.2% | 58% |
| LMArena Math | 1472 | 1498 |
| FrontierMath Tier 4 | — | 46.3% |
| MathArena Final-Answer Competitions | 67.1% | — |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge Qwen3.8 Max leads
GLM-5.1: 55.0 (#45), Qwen3.8 Max: 61.7 (#25)
| Benchmark | GLM-5.1 | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | 89.9% | 92.7% |
| SimpleQA Verified | 34% | 47.3% |
| LMArena Expert | 1477 | 1504 |
Multimodal Not comparable
GLM-5.1: —, Qwen3.8 Max: 36.9 (#70)
| Benchmark | GLM-5.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |
Multilingual Qwen3.8 Max leads
GLM-5.1: 55.2 (#34), Qwen3.8 Max: 56.6 (#18)
| Benchmark | GLM-5.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1448 | 1468 |
| LMArena Chinese | 1516 | 1537 |
| LMArena French | 1478 | 1502 |
| LMArena German | 1466 | 1489 |
| LMArena Japanese | 1436 | 1466 |
| LMArena Korean | 1423 | 1467 |
| LMArena Russian | 1453 | 1478 |
| LMArena Spanish | 1467 | 1495 |
Instruction Following Qwen3.8 Max leads
GLM-5.1: 76.5 (#41), Qwen3.8 Max: 77.7 (#19)
| Benchmark | GLM-5.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1451 | 1478 |
Long Context Too close to call
GLM-5.1: 44.9 (#51), Qwen3.8 Max: 45.5 (#30)
| Benchmark | GLM-5.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1467 | 1486 |
Writing & Preference Too close to call
GLM-5.1: 67.2 (#29), Qwen3.8 Max: 67.0 (#31)
| Benchmark | GLM-5.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1462 | 1480 |
| LMArena Creative Writing | 1454 | 1478 |
| LMArena Multi-Turn | 1473 | 1487 |
| EQ-Bench Creative Writing | 1592 | — |
Frequently asked questions
Is GLM-5.1 better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.0 to 47.6 on the Noometry Index.
Which is cheaper, GLM-5.1 or Qwen3.8 Max?
GLM-5.1 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; Qwen3.8 Max lists at $2 and $6.
Is GLM-5.1 or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 52.3 versus 48.5 in the Noometry coding category.
Which has the bigger context window?
Qwen3.8 Max does, with 1M tokens against 200K.
How many benchmarks do GLM-5.1 and Qwen3.8 Max share?
28 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Qwen3.8 Max has 38.