Model comparison
GLM-4.7-Flash vs Qwen1.5-7B
GLM-4.7-Flash is the stronger model overall, scoring 38.8 to 31.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. GLM-4.7-Flash scores higher in 8 categories and Qwen1.5-7B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GLM-4.7-Flash leads 46.5 to 28.5.
Side by side
| GLM-4.7-Flash | Qwen1.5-7B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 38.8 | 31.4 |
| Released | 2026-01-19 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 200K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.06 | — |
| Output $ / M tokens | $0.40 | — |
| Results tracked | 21 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.7-Flash leads
GLM-4.7-Flash: 40.6 (#135), Qwen1.5-7B: 32.2 (#276)
| Benchmark | GLM-4.7-Flash | Qwen1.5-7B |
|---|---|---|
| LMArena Coding | 1383 | 1107 |
Reasoning Too close to call
GLM-4.7-Flash: 20.9 (#229), Qwen1.5-7B: 20.4 (#240)
| Benchmark | GLM-4.7-Flash | Qwen1.5-7B |
|---|---|---|
| LMArena Hard Prompts | 1356 | 1065 |
| Chess Puzzles | 0% | — |
Math GLM-4.7-Flash leads
GLM-4.7-Flash: 36.1 (#173), Qwen1.5-7B: 31.4 (#224)
| Benchmark | GLM-4.7-Flash | Qwen1.5-7B |
|---|---|---|
| LMArena Math | 1355 | 1080 |
| OTIS Mock AIME 2024-2025 | 58.3% | — |
Knowledge GLM-4.7-Flash leads
GLM-4.7-Flash: 35.5 (#184), Qwen1.5-7B: 28.7 (#243)
| Benchmark | GLM-4.7-Flash | Qwen1.5-7B |
|---|---|---|
| LMArena Expert | 1357 | 1055 |
| GPQA Diamond | 60.5% | — |
| Vectara Hallucination Rate | 9.3% | — |
| MMLU | — | 62.6% |
Multilingual GLM-4.7-Flash leads
GLM-4.7-Flash: 46.5 (#158), Qwen1.5-7B: 28.5 (#271)
| Benchmark | GLM-4.7-Flash | Qwen1.5-7B |
|---|---|---|
| LMArena Non-English | 1330 | 1058 |
| LMArena Chinese | 1403 | 1141 |
| LMArena Russian | 1332 | 1006 |
| LMArena French | 1332 | — |
| LMArena German | 1337 | — |
| LMArena Korean | 1283 | — |
| LMArena Spanish | 1350 | — |
Instruction Following GLM-4.7-Flash leads
GLM-4.7-Flash: 70.1 (#167), Qwen1.5-7B: 54.1 (#281)
| Benchmark | GLM-4.7-Flash | Qwen1.5-7B |
|---|---|---|
| LMArena Instruction Following | 1327 | 1058 |
Long Context GLM-4.7-Flash leads
GLM-4.7-Flash: 40.9 (#148), Qwen1.5-7B: 33.1 (#266)
| Benchmark | GLM-4.7-Flash | Qwen1.5-7B |
|---|---|---|
| LMArena Longer Query | 1345 | 1090 |
Writing & Preference GLM-4.7-Flash leads
GLM-4.7-Flash: 47.4 (#210), Qwen1.5-7B: 29.6 (#293)
| Benchmark | GLM-4.7-Flash | Qwen1.5-7B |
|---|---|---|
| LMArena Text | 1351 | 1083 |
| LMArena Creative Writing | 1297 | 1035 |
| LMArena Multi-Turn | 1342 | 1062 |
| EQ-Bench Creative Writing | 1125 | — |
Frequently asked questions
Is GLM-4.7-Flash better than Qwen1.5-7B?
GLM-4.7-Flash is the stronger model overall, scoring 38.8 to 31.4 on the Noometry Index.
Is GLM-4.7-Flash or Qwen1.5-7B better for coding?
GLM-4.7-Flash scores higher on coding benchmarks: 40.6 versus 32.2 in the Noometry coding category.
How many benchmarks do GLM-4.7-Flash and Qwen1.5-7B share?
12 benchmarks have published results for both models. GLM-4.7-Flash has 21 scored results on Noometry and Qwen1.5-7B has 13.