Model comparison
GLM-5V-Turbo vs Qwen2.5 72B Instruct
GLM-5V-Turbo is the stronger model overall, scoring 43.1 to 31.5 on the Noometry Index.
Last verified . 16 shared benchmarks.
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. GLM-5V-Turbo scores higher in 8 categories and Qwen2.5 72B Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5V-Turbo leads 36.6 to 18.1.
- GLM-5V-Turbo is cheaper at $1.20 / $4 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- GLM-5V-Turbo accepts more context: 200K tokens versus 131K.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| GLM-5V-Turbo | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 43.1 | 31.5 |
| Released | 2026-04-01 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | 200K | 131K |
| Max output | 131K | 8K |
| Input $ / M tokens | $1.20 | $1.40 |
| Output $ / M tokens | $4 | $5.60 |
| Results tracked | 19 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5V-Turbo leads
GLM-5V-Turbo: 41.8 (#105), Qwen2.5 72B Instruct: 32.8 (#256)
| Benchmark | GLM-5V-Turbo | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1467 | 1293 |
| LMArena WebDev | 1400 | — |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
Agentic & Tool Use Not comparable
GLM-5V-Turbo: —, Qwen2.5 72B Instruct: 22.0 (#124)
| Benchmark | GLM-5V-Turbo | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning GLM-5V-Turbo leads
GLM-5V-Turbo: 28.5 (#87), Qwen2.5 72B Instruct: 21.4 (#197)
| Benchmark | GLM-5V-Turbo | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1443 | 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 GLM-5V-Turbo leads
GLM-5V-Turbo: 36.6 (#109), Qwen2.5 72B Instruct: 18.1 (#281)
| Benchmark | GLM-5V-Turbo | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 1440 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |
Knowledge GLM-5V-Turbo leads
GLM-5V-Turbo: 39.9 (#113), Qwen2.5 72B Instruct: 26.9 (#247)
| Benchmark | GLM-5V-Turbo | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Expert | 1451 | 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-5V-Turbo: 40.1 (#41), Qwen2.5 72B Instruct: —
| Benchmark | GLM-5V-Turbo | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Vision | 1264 | — |
| LMArena Document | 1416 | — |
Multilingual GLM-5V-Turbo leads
GLM-5V-Turbo: 53.2 (#69), Qwen2.5 72B Instruct: 41.2 (#208)
| Benchmark | GLM-5V-Turbo | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1420 | 1252 |
| LMArena Chinese | 1488 | 1272 |
| LMArena French | 1443 | 1279 |
| LMArena German | 1422 | 1234 |
| LMArena Korean | 1399 | 1188 |
| LMArena Russian | 1432 | 1264 |
| LMArena Spanish | 1446 | 1255 |
| LMArena Japanese | — | 1180 |
Instruction Following GLM-5V-Turbo leads
GLM-5V-Turbo: 75.1 (#75), Qwen2.5 72B Instruct: 65.7 (#216)
| Benchmark | GLM-5V-Turbo | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1422 | 1254 |
| IFEval | — | 80.6% |
Long Context GLM-5V-Turbo leads
GLM-5V-Turbo: 44.0 (#76), Qwen2.5 72B Instruct: 38.9 (#183)
| Benchmark | GLM-5V-Turbo | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1439 | 1282 |
Writing & Preference GLM-5V-Turbo leads
GLM-5V-Turbo: 62.6 (#69), Qwen2.5 72B Instruct: 46.9 (#210)
| Benchmark | GLM-5V-Turbo | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1437 | 1269 |
| LMArena Creative Writing | 1414 | 1221 |
| LMArena Multi-Turn | 1432 | 1272 |
| WildBench | — | 80.2% |
Frequently asked questions
Is GLM-5V-Turbo better than Qwen2.5 72B Instruct?
GLM-5V-Turbo is the stronger model overall, scoring 43.1 to 31.5 on the Noometry Index.
Which is cheaper, GLM-5V-Turbo or Qwen2.5 72B Instruct?
GLM-5V-Turbo is cheaper. It lists at $1.20 per million input tokens and $4 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.
Is GLM-5V-Turbo or Qwen2.5 72B Instruct better for coding?
GLM-5V-Turbo scores higher on coding benchmarks: 41.8 versus 32.8 in the Noometry coding category.
Which has the bigger context window?
GLM-5V-Turbo does, with 200K tokens against 131K.
How many benchmarks do GLM-5V-Turbo and Qwen2.5 72B Instruct share?
16 benchmarks have published results for both models. GLM-5V-Turbo has 19 scored results on Noometry and Qwen2.5 72B Instruct has 43.