Model comparison
GLM-4.6V vs Qwen2.5-VL 72B Instruct
GLM-4.6V is the stronger model overall, scoring 41.3 to 29.9 on the Noometry Index.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. GLM-4.6V scores higher in 2 categories and Qwen2.5-VL 72B Instruct in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-4.6V leads 27.6 to 20.7.
- GLM-4.6V is cheaper at $0.30 / $0.90 per million input/output tokens, against $2.80 / $8.40 for Qwen2.5-VL 72B Instruct.
- Qwen2.5-VL 72B Instruct accepts more context: 131K tokens versus 128K.
Side by side
| GLM-4.6V | Qwen2.5-VL 72B Instruct | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 41.3 | 29.9 |
| Released | 2025-12-08 | 2024-09 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 33K | 8K |
| Input $ / M tokens | $0.30 | $2.80 |
| Output $ / M tokens | $0.90 | $8.40 |
| Results tracked | 12 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GLM-4.6V: 40.9 (#128), Qwen2.5-VL 72B Instruct: —
| Benchmark | GLM-4.6V | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Coding | 1390 | — |
Agentic & Tool Use Not comparable
GLM-4.6V: —, Qwen2.5-VL 72B Instruct: 18.6 (#144)
| Benchmark | GLM-4.6V | Qwen2.5-VL 72B Instruct |
|---|---|---|
| OSWorld | — | 5% |
Reasoning GLM-4.6V leads
GLM-4.6V: 27.6 (#115), Qwen2.5-VL 72B Instruct: 20.7 (#233)
| Benchmark | GLM-4.6V | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Kagi LLM Benchmark | — | 36% |
| LMArena Hard Prompts | 1368 | — |
Knowledge Not comparable
GLM-4.6V: 38.0 (#149), Qwen2.5-VL 72B Instruct: —
| Benchmark | GLM-4.6V | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Expert | 1371 | — |
Multimodal GLM-4.6V leads
GLM-4.6V: 34.8 (#90), Qwen2.5-VL 72B Instruct: 33.5 (#97)
| Benchmark | GLM-4.6V | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Vision | 1164 | 1107 |
| Video-MME | — | 73.5% |
| GeoBench | — | 62% |
| SpatialViz-Bench | — | 33.3% |
Multilingual Not comparable
GLM-4.6V: 48.6 (#141), Qwen2.5-VL 72B Instruct: —
| Benchmark | GLM-4.6V | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Non-English | 1359 | — |
| LMArena Chinese | 1425 | — |
| LMArena Russian | 1340 | — |
Instruction Following Not comparable
GLM-4.6V: 71.4 (#151), Qwen2.5-VL 72B Instruct: —
| Benchmark | GLM-4.6V | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1352 | — |
Long Context Not comparable
GLM-4.6V: 41.3 (#143), Qwen2.5-VL 72B Instruct: —
| Benchmark | GLM-4.6V | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1358 | — |
Writing & Preference Not comparable
GLM-4.6V: 56.6 (#137), Qwen2.5-VL 72B Instruct: —
| Benchmark | GLM-4.6V | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Text | 1377 | — |
| LMArena Creative Writing | 1347 | — |
| LMArena Multi-Turn | 1360 | — |
Frequently asked questions
Is GLM-4.6V better than Qwen2.5-VL 72B Instruct?
GLM-4.6V is the stronger model overall, scoring 41.3 to 29.9 on the Noometry Index.
Which is cheaper, GLM-4.6V or Qwen2.5-VL 72B Instruct?
GLM-4.6V is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; Qwen2.5-VL 72B Instruct lists at $2.80 and $8.40.
Which has the bigger context window?
Qwen2.5-VL 72B Instruct does, with 131K tokens against 128K.
How many benchmarks do GLM-4.6V and Qwen2.5-VL 72B Instruct share?
1 benchmark has published results for both models. GLM-4.6V has 12 scored results on Noometry and Qwen2.5-VL 72B Instruct has 6.