Model comparison
GLM-4.5V vs Qwen2.5-VL 72B Instruct
GLM-4.5V is the stronger model overall, scoring 39.8 to 29.9 on the Noometry Index.
Last verified . 2 shared benchmarks.
Alibaba (Qwen)Summary
- They share 2 benchmarks with published results for both. GLM-4.5V scores higher in 2 categories and Qwen2.5-VL 72B Instruct in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in reasoning, where GLM-4.5V leads 27.4 to 20.7.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 59.8% for GLM-4.5V and 36% for Qwen2.5-VL 72B Instruct.
- GLM-4.5V is cheaper at $0.60 / $1.80 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 64K.
Side by side
| GLM-4.5V | Qwen2.5-VL 72B Instruct | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 39.8 | 29.9 |
| Released | 2025-08-11 | 2024-09 |
| Weights | Open | Open |
| Context window | 64K | 131K |
| Max output | 16K | 8K |
| Input $ / M tokens | $0.60 | $2.80 |
| Output $ / M tokens | $1.80 | $8.40 |
| Results tracked | 15 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GLM-4.5V: 39.5 (#155), Qwen2.5-VL 72B Instruct: —
| Benchmark | GLM-4.5V | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Coding | 1347 | — |
Agentic & Tool Use Not comparable
GLM-4.5V: —, Qwen2.5-VL 72B Instruct: 18.6 (#144)
| Benchmark | GLM-4.5V | Qwen2.5-VL 72B Instruct |
|---|---|---|
| OSWorld | — | 5% |
Reasoning GLM-4.5V leads
GLM-4.5V: 27.4 (#119), Qwen2.5-VL 72B Instruct: 20.7 (#233)
| Benchmark | GLM-4.5V | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 59.8% | 36% |
| LMArena Hard Prompts | 1334 | — |
Math Not comparable
GLM-4.5V: 37.4 (#159), Qwen2.5-VL 72B Instruct: —
| Benchmark | GLM-4.5V | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Math | 1354 | — |
Knowledge Not comparable
GLM-4.5V: 37.5 (#156), Qwen2.5-VL 72B Instruct: —
| Benchmark | GLM-4.5V | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Expert | 1353 | — |
Multimodal Too close to call
GLM-4.5V: 34.3 (#92), Qwen2.5-VL 72B Instruct: 33.5 (#97)
| Benchmark | GLM-4.5V | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Vision | 1154 | 1107 |
| Video-MME | — | 73.5% |
| GeoBench | — | 62% |
| SpatialViz-Bench | — | 33.3% |
Multilingual Not comparable
GLM-4.5V: 44.6 (#177), Qwen2.5-VL 72B Instruct: —
| Benchmark | GLM-4.5V | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Non-English | 1303 | — |
| LMArena Chinese | 1337 | — |
| LMArena Russian | 1298 | — |
| LMArena Spanish | 1336 | — |
Instruction Following Not comparable
GLM-4.5V: 69.2 (#175), Qwen2.5-VL 72B Instruct: —
| Benchmark | GLM-4.5V | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1311 | — |
Long Context Not comparable
GLM-4.5V: 39.6 (#171), Qwen2.5-VL 72B Instruct: —
| Benchmark | GLM-4.5V | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1304 | — |
Writing & Preference Not comparable
GLM-4.5V: 52.5 (#170), Qwen2.5-VL 72B Instruct: —
| Benchmark | GLM-4.5V | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Text | 1333 | — |
| LMArena Creative Writing | 1295 | — |
| LMArena Multi-Turn | 1332 | — |
Frequently asked questions
Is GLM-4.5V better than Qwen2.5-VL 72B Instruct?
GLM-4.5V is the stronger model overall, scoring 39.8 to 29.9 on the Noometry Index.
Which is cheaper, GLM-4.5V or Qwen2.5-VL 72B Instruct?
GLM-4.5V is cheaper. It lists at $0.60 per million input tokens and $1.80 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 64K.
How many benchmarks do GLM-4.5V and Qwen2.5-VL 72B Instruct share?
2 benchmarks have published results for both models. GLM-4.5V has 15 scored results on Noometry and Qwen2.5-VL 72B Instruct has 6.