Model comparison
GLM-4.7 vs Qwen2-72B
GLM-4.7 is the stronger model overall, scoring 41.7 to 29.5 on the Noometry Index.
Last verified . 19 shared benchmarks.
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. GLM-4.7 scores higher in 9 categories and Qwen2-72B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.7 leads 47.0 to 21.2.
- The biggest single-benchmark swing is GPQA Diamond: 83.3% for GLM-4.7 and 40.8% for Qwen2-72B.
Side by side
| GLM-4.7 | Qwen2-72B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 41.7 | 29.5 |
| Released | 2025-12-22 | 2024-06-07 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $2.20 | — |
| Results tracked | 36 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.7 leads
GLM-4.7: 43.6 (#74), Qwen2-72B: 28.7 (#303)
| Benchmark | GLM-4.7 | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1454 | 1196 |
| LMArena WebDev | 1435 | — |
| SciCode | 45.1% | — |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
| ALE-Bench | 399.48 | — |
Agentic & Tool Use GLM-4.7 leads
GLM-4.7: 26.4 (#96), Qwen2-72B: 16.9 (#138)
| Benchmark | GLM-4.7 | Qwen2-72B |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
| Vending-Bench 2 | 2,377 | — |
Reasoning GLM-4.7 leads
GLM-4.7: 23.7 (#161), Qwen2-72B: 22.2 (#184)
| Benchmark | GLM-4.7 | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1191 |
| Epoch Capabilities Index | 143.53 | 125.27 |
| SimpleBench | 47.7% | — |
| CritPt | 1.7% | — |
| Chess Puzzles | 6% | — |
Math GLM-4.7 leads
GLM-4.7: 37.7 (#92), Qwen2-72B: 27.9 (#232)
| Benchmark | GLM-4.7 | Qwen2-72B |
|---|---|---|
| LMArena Math | 1423 | 1235 |
| OTIS Mock AIME 2024-2025 | 83.3% | — |
| ProofBench | 6% | — |
| MATH Level 5 | — | 39.1% |
| FrontierMath (Feb 2025 set) | 2.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GLM-4.7 leads
GLM-4.7: 47.0 (#74), Qwen2-72B: 21.2 (#270)
| Benchmark | GLM-4.7 | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 83.3% | 40.8% |
| LMArena Expert | 1424 | 1171 |
| SimpleQA Verified | 32.2% | — |
| Vectara Hallucination Rate | 11.7% | — |
| MMLU | — | 82.4% |
Multilingual GLM-4.7 leads
GLM-4.7: 53.0 (#75), Qwen2-72B: 36.0 (#239)
| Benchmark | GLM-4.7 | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1417 | 1176 |
| LMArena Chinese | 1495 | 1240 |
| LMArena French | 1432 | 1169 |
| LMArena German | 1426 | 1151 |
| LMArena Japanese | 1439 | 1111 |
| LMArena Korean | 1401 | 1083 |
| LMArena Russian | 1423 | 1169 |
| LMArena Spanish | 1433 | 1168 |
Instruction Following GLM-4.7 leads
GLM-4.7: 74.6 (#90), Qwen2-72B: 62.0 (#236)
| Benchmark | GLM-4.7 | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1411 | 1181 |
Long Context GLM-4.7 leads
GLM-4.7: 42.8 (#111), Qwen2-72B: 36.1 (#230)
| Benchmark | GLM-4.7 | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1432 | 1193 |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
Writing & Preference GLM-4.7 leads
GLM-4.7: 61.1 (#89), Qwen2-72B: 41.0 (#236)
| Benchmark | GLM-4.7 | Qwen2-72B |
|---|---|---|
| LMArena Text | 1436 | 1203 |
| LMArena Creative Writing | 1401 | 1181 |
| LMArena Multi-Turn | 1446 | 1195 |
| EQ-Bench Creative Writing | 1413 | — |
Frequently asked questions
Is GLM-4.7 better than Qwen2-72B?
GLM-4.7 is the stronger model overall, scoring 41.7 to 29.5 on the Noometry Index.
Is GLM-4.7 or Qwen2-72B better for coding?
GLM-4.7 scores higher on coding benchmarks: 43.6 versus 28.7 in the Noometry coding category.
How many benchmarks do GLM-4.7 and Qwen2-72B share?
19 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Qwen2-72B has 26.