Model comparison
GLM-4.7 vs Qwen2.5-Max
GLM-4.7 is the stronger model overall, scoring 42.0 to 40.7 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 7 categories and Qwen2.5-Max in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.7 leads 47.0 to 35.3.
- GLM-4.7 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.7 | Qwen2.5-Max | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 42.0 | 40.7 |
| Released | 2025-12-22 | 2025-01-25 |
| Weights | Open | Proprietary |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $2.20 | — |
| Results tracked | 36 | 27 |
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), Qwen2.5-Max: 41.8 (#117)
| Benchmark | GLM-4.7 | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1454 | 1359 |
| LMArena WebDev | 1435 | — |
| SciCode | 45.1% | — |
| LiveBench Coding | — | 64.4% |
| ALE-Bench | 399.48 | — |
Agentic & Tool Use Not comparable
GLM-4.7: 26.5 (#103), Qwen2.5-Max: —
| Benchmark | GLM-4.7 | Qwen2.5-Max |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| Vending-Bench 2 | 2,377 | — |
Reasoning Qwen2.5-Max leads
GLM-4.7: 24.3 (#164), Qwen2.5-Max: 25.6 (#147)
| Benchmark | GLM-4.7 | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1360 |
| Epoch Capabilities Index | 143.51 | 132.53 |
| SimpleBench | 47.7% | — |
| CritPt | 1.7% | — |
| Chess Puzzles | 6% | — |
| LiveBench Reasoning | — | 51.4% |
| LiveBench Data Analysis | — | 67.9% |
| LiveBench | — | 62.3% |
Math GLM-4.7 leads
GLM-4.7: 38.6 (#135), Qwen2.5-Max: 36.9 (#162)
| Benchmark | GLM-4.7 | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1423 | 1369 |
| OTIS Mock AIME 2024-2025 | 83.3% | — |
| ProofBench | 6% | — |
| LiveBench Math | — | 58.4% |
| FrontierMath (Feb 2025 set) | 2.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GLM-4.7 leads
GLM-4.7: 47.0 (#80), Qwen2.5-Max: 35.3 (#186)
| Benchmark | GLM-4.7 | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1424 | 1337 |
| GPQA Diamond | 83.3% | — |
| SimpleQA Verified | 32.2% | — |
| Confabulations | — | 21.8% |
| Vectara Hallucination Rate | 11.7% | — |
Multilingual GLM-4.7 leads
GLM-4.7: 52.8 (#79), Qwen2.5-Max: 48.1 (#146)
| Benchmark | GLM-4.7 | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1417 | 1352 |
| LMArena Chinese | 1495 | 1382 |
| LMArena French | 1432 | 1396 |
| LMArena German | 1424 | 1350 |
| LMArena Japanese | 1439 | 1300 |
| LMArena Korean | 1399 | 1304 |
| LMArena Russian | 1423 | 1353 |
| LMArena Spanish | 1434 | 1377 |
Instruction Following GLM-4.7 leads
GLM-4.7: 74.4 (#95), Qwen2.5-Max: 71.3 (#152)
| Benchmark | GLM-4.7 | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1411 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
Long Context GLM-4.7 leads
GLM-4.7: 42.8 (#116), Qwen2.5-Max: 41.4 (#142)
| Benchmark | GLM-4.7 | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1432 | 1358 |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
Writing & Preference GLM-4.7 leads
GLM-4.7: 60.9 (#93), Qwen2.5-Max: 55.4 (#146)
| Benchmark | GLM-4.7 | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1435 | 1367 |
| LMArena Creative Writing | 1401 | 1339 |
| LMArena Multi-Turn | 1446 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| EQ-Bench Creative Writing | 1413 | — |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is GLM-4.7 better than Qwen2.5-Max?
GLM-4.7 is the stronger model overall, scoring 42.0 to 40.7 on the Noometry Index.
Is GLM-4.7 or Qwen2.5-Max better for coding?
GLM-4.7 scores higher on coding benchmarks: 44.0 versus 41.8 in the Noometry coding category.
How many benchmarks do GLM-4.7 and Qwen2.5-Max share?
18 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Qwen2.5-Max has 27.