Model comparison
GLM-4.6V vs Qwen2.5 72B Instruct
GLM-4.6V is the stronger model overall, scoring 40.9 to 31.5 on the Noometry Index.
Last verified . 11 shared benchmarks.
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. GLM-4.6V scores higher in 7 categories and Qwen2.5 72B Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.6V leads 37.4 to 26.9.
- GLM-4.6V is cheaper at $0.30 / $0.90 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- Qwen2.5 72B Instruct accepts more context: 131K tokens versus 128K.
Side by side
| GLM-4.6V | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 40.9 | 31.5 |
| Released | 2025-12-08 | 2024-09 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 33K | 8K |
| Input $ / M tokens | $0.30 | $1.40 |
| Output $ / M tokens | $0.90 | $5.60 |
| Results tracked | 12 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6V leads
GLM-4.6V: 40.2 (#128), Qwen2.5 72B Instruct: 32.8 (#256)
| Benchmark | GLM-4.6V | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1390 | 1293 |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
Agentic & Tool Use Not comparable
GLM-4.6V: —, Qwen2.5 72B Instruct: 22.0 (#124)
| Benchmark | GLM-4.6V | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning GLM-4.6V leads
GLM-4.6V: 26.5 (#117), Qwen2.5 72B Instruct: 21.4 (#197)
| Benchmark | GLM-4.6V | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1368 | 1271 |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| Epoch Capabilities Index | — | 129.01 |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math Not comparable
GLM-4.6V: —, Qwen2.5 72B Instruct: 18.1 (#281)
| Benchmark | GLM-4.6V | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| LMArena Math | — | 1283 |
| MATH Level 5 | — | 63.2% |
Knowledge GLM-4.6V leads
GLM-4.6V: 37.4 (#148), Qwen2.5 72B Instruct: 26.9 (#247)
| Benchmark | GLM-4.6V | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Expert | 1372 | 1245 |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multimodal Not comparable
GLM-4.6V: 34.2 (#83), Qwen2.5 72B Instruct: —
| Benchmark | GLM-4.6V | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Vision | 1164 | — |
Multilingual GLM-4.6V leads
GLM-4.6V: 48.8 (#135), Qwen2.5 72B Instruct: 41.2 (#208)
| Benchmark | GLM-4.6V | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1359 | 1252 |
| LMArena Chinese | 1426 | 1272 |
| LMArena Russian | 1341 | 1264 |
| LMArena French | — | 1279 |
| LMArena German | — | 1234 |
| LMArena Japanese | — | 1180 |
| LMArena Korean | — | 1188 |
| LMArena Spanish | — | 1255 |
Instruction Following GLM-4.6V leads
GLM-4.6V: 71.6 (#145), Qwen2.5 72B Instruct: 65.7 (#216)
| Benchmark | GLM-4.6V | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1351 | 1254 |
| IFEval | — | 80.6% |
Long Context GLM-4.6V leads
GLM-4.6V: 41.3 (#138), Qwen2.5 72B Instruct: 38.9 (#183)
| Benchmark | GLM-4.6V | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1358 | 1282 |
Writing & Preference GLM-4.6V leads
GLM-4.6V: 56.8 (#132), Qwen2.5 72B Instruct: 46.9 (#210)
| Benchmark | GLM-4.6V | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1377 | 1269 |
| LMArena Creative Writing | 1347 | 1221 |
| LMArena Multi-Turn | 1359 | 1272 |
| WildBench | — | 80.2% |
Frequently asked questions
Is GLM-4.6V better than Qwen2.5 72B Instruct?
GLM-4.6V is the stronger model overall, scoring 40.9 to 31.5 on the Noometry Index.
Which is cheaper, GLM-4.6V or Qwen2.5 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 72B Instruct lists at $1.40 and $5.60.
Is GLM-4.6V or Qwen2.5 72B Instruct better for coding?
GLM-4.6V scores higher on coding benchmarks: 40.2 versus 32.8 in the Noometry coding category.
Which has the bigger context window?
Qwen2.5 72B Instruct does, with 131K tokens against 128K.
How many benchmarks do GLM-4.6V and Qwen2.5 72B Instruct share?
11 benchmarks have published results for both models. GLM-4.6V has 12 scored results on Noometry and Qwen2.5 72B Instruct has 43.