Model comparison
GLM-4.7 vs Qwen3-30B-A3B
GLM-4.7 is the stronger model overall, scoring 41.7 to 38.5 on the Noometry Index. Qwen3-30B-A3B costs 4.7× less per token, which makes it the better buy when GLM-4.7's lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. GLM-4.7 scores higher in 8 categories and Qwen3-30B-A3B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in long context, where GLM-4.7 leads 42.8 to 31.0.
- The biggest single-benchmark swing is GPQA Diamond: 83.3% for GLM-4.7 and 70.1% for Qwen3-30B-A3B.
- Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $0.60 / $2.20 for GLM-4.7.
- GLM-4.7 accepts more context: 205K tokens versus 41K.
Side by side
| GLM-4.7 | Qwen3-30B-A3B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 41.7 | 38.5 |
| Released | 2025-12-22 | 2025-04-28 |
| Weights | Open | Open |
| Context window | 205K | 41K |
| Max output | 131K | 16K |
| Input $ / M tokens | $0.60 | $0.12 |
| Output $ / M tokens | $2.20 | $0.50 |
| Results tracked | 36 | 32 |
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), Qwen3-30B-A3B: 37.0 (#188)
| Benchmark | GLM-4.7 | Qwen3-30B-A3B |
|---|---|---|
| SciCode | 45.1% | 33.3% |
| LMArena Coding | 1454 | 1416 |
| LMArena WebDev | 1435 | — |
| WeirdML | — | 29.8% |
| ALE-Bench | 399.48 | — |
Agentic & Tool Use Qwen3-30B-A3B leads
GLM-4.7: 26.4 (#96), Qwen3-30B-A3B: 29.5 (#75)
| Benchmark | GLM-4.7 | Qwen3-30B-A3B |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| Berkeley Function Calling Leaderboard | — | 41.4% |
| Vending-Bench 2 | 2,377 | — |
Reasoning GLM-4.7 leads
GLM-4.7: 23.7 (#161), Qwen3-30B-A3B: 21.6 (#193)
| Benchmark | GLM-4.7 | Qwen3-30B-A3B |
|---|---|---|
| CritPt | 1.7% | 0.3% |
| Chess Puzzles | 6% | 8% |
| LMArena Hard Prompts | 1443 | 1398 |
| Epoch Capabilities Index | 143.53 | 139.63 |
| SimpleBench | 47.7% | — |
| Kagi LLM Benchmark | — | 54.9% |
| DTBench | — | 69.3% |
| LMCA | — | 22.4% |
Math GLM-4.7 leads
GLM-4.7: 37.7 (#92), Qwen3-30B-A3B: 36.0 (#133)
| Benchmark | GLM-4.7 | Qwen3-30B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.3% | 70.3% |
| LMArena Math | 1423 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| ProofBench | 6% | — |
| FrontierMath (Feb 2025 set) | 2.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GLM-4.7 leads
GLM-4.7: 47.0 (#74), Qwen3-30B-A3B: 41.7 (#96)
| Benchmark | GLM-4.7 | Qwen3-30B-A3B |
|---|---|---|
| GPQA Diamond | 83.3% | 70.1% |
| LMArena Expert | 1424 | 1395 |
| SimpleQA Verified | 32.2% | — |
| Confabulations | — | 12.3% |
| Vectara Hallucination Rate | 11.7% | — |
Multilingual GLM-4.7 leads
GLM-4.7: 53.0 (#75), Qwen3-30B-A3B: 49.8 (#126)
| Benchmark | GLM-4.7 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1417 | 1372 |
| LMArena Chinese | 1495 | 1434 |
| LMArena French | 1432 | 1419 |
| LMArena German | 1426 | 1379 |
| LMArena Japanese | 1439 | 1338 |
| LMArena Korean | 1401 | 1333 |
| LMArena Russian | 1423 | 1369 |
| LMArena Spanish | 1433 | 1403 |
Instruction Following GLM-4.7 leads
GLM-4.7: 74.6 (#90), Qwen3-30B-A3B: 72.2 (#137)
| Benchmark | GLM-4.7 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1411 | 1364 |
Long Context GLM-4.7 leads
GLM-4.7: 42.8 (#111), Qwen3-30B-A3B: 31.0 (#278)
| Benchmark | GLM-4.7 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1432 | 1379 |
| Fiction.LiveBench | — | 40.6% |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
Writing & Preference GLM-4.7 leads
GLM-4.7: 61.1 (#89), Qwen3-30B-A3B: 55.9 (#138)
| Benchmark | GLM-4.7 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1436 | 1384 |
| LMArena Creative Writing | 1401 | 1318 |
| LMArena Multi-Turn | 1446 | 1378 |
| Short-Story Creative Writing | — | 75.3% |
| EQ-Bench Creative Writing | 1413 | — |
Frequently asked questions
Is GLM-4.7 better than Qwen3-30B-A3B?
GLM-4.7 is the stronger model overall, scoring 41.7 to 38.5 on the Noometry Index. Qwen3-30B-A3B costs 4.7× less per token, which makes it the better buy when GLM-4.7's lead doesn't matter for your workload.
Which is cheaper, GLM-4.7 or Qwen3-30B-A3B?
Qwen3-30B-A3B is cheaper. It lists at $0.12 per million input tokens and $0.50 per million output tokens; GLM-4.7 lists at $0.60 and $2.20.
Is GLM-4.7 or Qwen3-30B-A3B better for coding?
GLM-4.7 scores higher on coding benchmarks: 43.6 versus 37.0 in the Noometry coding category.
Which has the bigger context window?
GLM-4.7 does, with 205K tokens against 41K.
How many benchmarks do GLM-4.7 and Qwen3-30B-A3B share?
23 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Qwen3-30B-A3B has 32.