Model comparison
GLM-4.7 vs Qwen1.5-72B
GLM-4.7 is the stronger model overall, scoring 42.0 to 30.8 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. GLM-4.7 scores higher in 8 categories and Qwen1.5-72B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.7 leads 47.0 to 11.5.
- The biggest single-benchmark swing is GPQA Diamond: 83.3% for GLM-4.7 and 28.8% for Qwen1.5-72B.
Side by side
| GLM-4.7 | Qwen1.5-72B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 42.0 | 30.8 |
| Released | 2025-12-22 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $2.20 | — |
| Results tracked | 36 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.7 leads
GLM-4.7: 44.0 (#79), Qwen1.5-72B: 31.9 (#277)
| Benchmark | GLM-4.7 | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1454 | 1165 |
| LMArena WebDev | 1435 | — |
| SciCode | 45.1% | — |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| ALE-Bench | 399.48 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |
Agentic & Tool Use Not comparable
GLM-4.7: 26.5 (#103), Qwen1.5-72B: —
| Benchmark | GLM-4.7 | Qwen1.5-72B |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| Vending-Bench 2 | 2,377 | — |
Reasoning GLM-4.7 leads
GLM-4.7: 24.3 (#164), Qwen1.5-72B: 22.2 (#203)
| Benchmark | GLM-4.7 | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1148 |
| SimpleBench | 47.7% | — |
| CritPt | 1.7% | — |
| Chess Puzzles | 6% | — |
| Epoch Capabilities Index | 143.51 | — |
Math GLM-4.7 leads
GLM-4.7: 38.6 (#135), Qwen1.5-72B: 33.2 (#205)
| Benchmark | GLM-4.7 | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1423 | 1164 |
| OTIS Mock AIME 2024-2025 | 83.3% | — |
| ProofBench | 6% | — |
| FrontierMath (Feb 2025 set) | 2.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GLM-4.7 leads
GLM-4.7: 47.0 (#80), Qwen1.5-72B: 11.5 (#300)
| Benchmark | GLM-4.7 | Qwen1.5-72B |
|---|---|---|
| GPQA Diamond | 83.3% | 28.8% |
| LMArena Expert | 1424 | 1136 |
| SimpleQA Verified | 32.2% | — |
| Vectara Hallucination Rate | 11.7% | — |
Multilingual GLM-4.7 leads
GLM-4.7: 52.8 (#79), Qwen1.5-72B: 33.2 (#253)
| Benchmark | GLM-4.7 | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1417 | 1135 |
| LMArena Chinese | 1495 | 1186 |
| LMArena French | 1432 | 1159 |
| LMArena German | 1424 | 1084 |
| LMArena Japanese | 1439 | 1061 |
| LMArena Korean | 1399 | 1050 |
| LMArena Russian | 1423 | 1104 |
| LMArena Spanish | 1434 | 1110 |
Instruction Following GLM-4.7 leads
GLM-4.7: 74.4 (#95), Qwen1.5-72B: 59.3 (#256)
| Benchmark | GLM-4.7 | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1411 | 1141 |
Long Context GLM-4.7 leads
GLM-4.7: 42.8 (#116), Qwen1.5-72B: 35.1 (#243)
| Benchmark | GLM-4.7 | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1432 | 1157 |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
Writing & Preference GLM-4.7 leads
GLM-4.7: 60.9 (#93), Qwen1.5-72B: 37.3 (#258)
| Benchmark | GLM-4.7 | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1435 | 1166 |
| LMArena Creative Writing | 1401 | 1137 |
| LMArena Multi-Turn | 1446 | 1160 |
| EQ-Bench Creative Writing | 1413 | — |
Frequently asked questions
Is GLM-4.7 better than Qwen1.5-72B?
GLM-4.7 is the stronger model overall, scoring 42.0 to 30.8 on the Noometry Index.
Is GLM-4.7 or Qwen1.5-72B better for coding?
GLM-4.7 scores higher on coding benchmarks: 44.0 versus 31.9 in the Noometry coding category.
How many benchmarks do GLM-4.7 and Qwen1.5-72B share?
18 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Qwen1.5-72B has 22.