Model comparison
GLM-5.1 vs Qwen3-30B-A3B
GLM-5.1 is the stronger model overall, scoring 47.8 to 38.9 on the Noometry Index. Qwen3-30B-A3B costs 10× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and Qwen3-30B-A3B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.1 leads 39.1 to 22.2.
- The biggest single-benchmark swing is WeirdML: 57.1% for GLM-5.1 and 29.8% for Qwen3-30B-A3B.
- Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- GLM-5.1 accepts more context: 200K tokens versus 41K.
Side by side
| GLM-5.1 | Qwen3-30B-A3B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 47.8 | 38.9 |
| Released | 2026-04-07 | 2025-04-28 |
| Weights | Open | Open |
| Context window | 200K | 41K |
| Max output | 131K | 16K |
| Input $ / M tokens | $1.40 | $0.12 |
| Output $ / M tokens | $4.40 | $0.50 |
| Results tracked | 41 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
GLM-5.1: 48.7 (#55), Qwen3-30B-A3B: 37.5 (#194)
| Benchmark | GLM-5.1 | Qwen3-30B-A3B |
|---|---|---|
| SciCode | 43.8% | 33.3% |
| WeirdML | 57.1% | 29.8% |
| LMArena Coding | 1485 | 1416 |
| SWE-bench Verified | 74.2% | — |
| LMArena WebDev | 1508 | — |
| ALE-Bench | 887.1 | — |
Agentic & Tool Use Qwen3-30B-A3B leads
GLM-5.1: 24.9 (#113), Qwen3-30B-A3B: 29.8 (#82)
| Benchmark | GLM-5.1 | Qwen3-30B-A3B |
|---|---|---|
| APEX-Agents | 40.9% | — |
| Berkeley Function Calling Leaderboard | — | 41.4% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |
Reasoning GLM-5.1 leads
GLM-5.1: 39.1 (#60), Qwen3-30B-A3B: 22.2 (#204)
| Benchmark | GLM-5.1 | Qwen3-30B-A3B |
|---|---|---|
| CritPt | 4.6% | 0.3% |
| Chess Puzzles | 19% | 8% |
| LMArena Hard Prompts | 1472 | 1398 |
| Epoch Capabilities Index | 149.84 | 139.63 |
| SimpleBench | 55.1% | — |
| Kagi LLM Benchmark | — | 54.9% |
| NYT Connections (extended) | 77.7% | — |
| Thematic Generalization | 69.8% | — |
| DTBench | — | 69.3% |
| LMCA | — | 22.4% |
Math GLM-5.1 leads
GLM-5.1: 49.7 (#60), Qwen3-30B-A3B: 37.4 (#157)
| Benchmark | GLM-5.1 | Qwen3-30B-A3B |
|---|---|---|
| MathArena Final-Answer Competitions | 67.1% | 47.8% |
| OTIS Mock AIME 2024-2025 | 93.3% | 70.3% |
| LMArena Math | 1473 | 1394 |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| ProofBench | 22.2% | — |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GLM-5.1 leads
GLM-5.1: 54.9 (#50), Qwen3-30B-A3B: 41.8 (#105)
| Benchmark | GLM-5.1 | Qwen3-30B-A3B |
|---|---|---|
| GPQA Diamond | 89.9% | 70.1% |
| LMArena Expert | 1476 | 1396 |
| SimpleQA Verified | 34% | — |
| Confabulations | — | 12.3% |
Multilingual GLM-5.1 leads
GLM-5.1: 55.0 (#36), Qwen3-30B-A3B: 49.5 (#132)
| Benchmark | GLM-5.1 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1447 | 1372 |
| LMArena Chinese | 1515 | 1433 |
| LMArena French | 1474 | 1418 |
| LMArena German | 1465 | 1380 |
| LMArena Japanese | 1434 | 1337 |
| LMArena Korean | 1418 | 1331 |
| LMArena Russian | 1454 | 1370 |
| LMArena Spanish | 1469 | 1404 |
Instruction Following GLM-5.1 leads
GLM-5.1: 76.3 (#42), Qwen3-30B-A3B: 72.0 (#142)
| Benchmark | GLM-5.1 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1451 | 1363 |
Long Context GLM-5.1 leads
GLM-5.1: 44.9 (#53), Qwen3-30B-A3B: 31.0 (#283)
| Benchmark | GLM-5.1 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1466 | 1379 |
| Fiction.LiveBench | — | 40.6% |
Writing & Preference GLM-5.1 leads
GLM-5.1: 66.9 (#31), Qwen3-30B-A3B: 55.6 (#143)
| Benchmark | GLM-5.1 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1461 | 1384 |
| LMArena Creative Writing | 1453 | 1317 |
| LMArena Multi-Turn | 1472 | 1378 |
| Short-Story Creative Writing | — | 75.3% |
| EQ-Bench Creative Writing | 1592 | — |
Frequently asked questions
Is GLM-5.1 better than Qwen3-30B-A3B?
GLM-5.1 is the stronger model overall, scoring 47.8 to 38.9 on the Noometry Index. Qwen3-30B-A3B costs 10× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Which is cheaper, GLM-5.1 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-5.1 lists at $1.40 and $4.40.
Is GLM-5.1 or Qwen3-30B-A3B better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 37.5 in the Noometry coding category.
Which has the bigger context window?
GLM-5.1 does, with 200K tokens against 41K.
How many benchmarks do GLM-5.1 and Qwen3-30B-A3B share?
25 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Qwen3-30B-A3B has 32.