Model comparison
GLM-5.1 vs Qwen3-4B
GLM-5.1 is the stronger model overall, scoring 47.6 to 31.5 on the Noometry Index.
Last verified . 4 shared benchmarks.
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. GLM-5.1 scores higher in 3 categories and Qwen3-4B in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.1 leads 55.0 to 33.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for GLM-5.1 and 52.2% for Qwen3-4B.
Side by side
| GLM-5.1 | Qwen3-4B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 47.6 | 31.5 |
| Released | 2026-04-07 | 2025-04-29 |
| Weights | Open | Open |
| Context window | 200K | — |
| Max output | 131K | — |
| Input $ / M tokens | $1.40 | — |
| Output $ / M tokens | $4.40 | — |
| Results tracked | 41 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GLM-5.1: 48.5 (#52), Qwen3-4B: —
| Benchmark | GLM-5.1 | Qwen3-4B |
|---|---|---|
| SWE-bench Verified | 74.2% | — |
| LMArena WebDev | 1509 | — |
| SciCode | 43.8% | — |
| WeirdML | 57.1% | — |
| LMArena Coding | 1486 | — |
| ALE-Bench | 887.1 | — |
Agentic & Tool Use Qwen3-4B leads
GLM-5.1: 24.8 (#106), Qwen3-4B: 27.3 (#94)
| Benchmark | GLM-5.1 | Qwen3-4B |
|---|---|---|
| APEX-Agents | 40.9% | — |
| Berkeley Function Calling Leaderboard | — | 35.7% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |
Reasoning GLM-5.1 leads
GLM-5.1: 38.2 (#57), Qwen3-4B: 18.5 (#264)
| Benchmark | GLM-5.1 | Qwen3-4B |
|---|---|---|
| Chess Puzzles | 19% | 4% |
| SimpleBench | 55.1% | — |
| NYT Connections (extended) | 77.7% | — |
| CritPt | 4.6% | — |
| Thematic Generalization | 69.8% | — |
| LMArena Hard Prompts | 1472 | — |
| Epoch Capabilities Index | 149.86 | — |
Math GLM-5.1 leads
GLM-5.1: 49.0 (#48), Qwen3-4B: 28.5 (#228)
| Benchmark | GLM-5.1 | Qwen3-4B |
|---|---|---|
| MathArena Final-Answer Competitions | 67.1% | 38.5% |
| OTIS Mock AIME 2024-2025 | 93.3% | 52.2% |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| ProofBench | 22.2% | — |
| LMArena Math | 1472 | — |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GLM-5.1 leads
GLM-5.1: 55.0 (#45), Qwen3-4B: 33.0 (#198)
| Benchmark | GLM-5.1 | Qwen3-4B |
|---|---|---|
| GPQA Diamond | 89.9% | 52.3% |
| SimpleQA Verified | 34% | — |
| Vectara Hallucination Rate | — | 5.7% |
| LMArena Expert | 1477 | — |
Multilingual Not comparable
GLM-5.1: 55.2 (#34), Qwen3-4B: —
| Benchmark | GLM-5.1 | Qwen3-4B |
|---|---|---|
| LMArena Non-English | 1448 | — |
| LMArena Chinese | 1516 | — |
| LMArena French | 1478 | — |
| LMArena German | 1466 | — |
| LMArena Japanese | 1436 | — |
| LMArena Korean | 1423 | — |
| LMArena Russian | 1453 | — |
| LMArena Spanish | 1467 | — |
Instruction Following Not comparable
GLM-5.1: 76.5 (#41), Qwen3-4B: —
| Benchmark | GLM-5.1 | Qwen3-4B |
|---|---|---|
| LMArena Instruction Following | 1451 | — |
Long Context Not comparable
GLM-5.1: 44.9 (#51), Qwen3-4B: —
| Benchmark | GLM-5.1 | Qwen3-4B |
|---|---|---|
| LMArena Longer Query | 1467 | — |
Writing & Preference Not comparable
GLM-5.1: 67.2 (#29), Qwen3-4B: —
| Benchmark | GLM-5.1 | Qwen3-4B |
|---|---|---|
| LMArena Text | 1462 | — |
| LMArena Creative Writing | 1454 | — |
| EQ-Bench Creative Writing | 1592 | — |
| LMArena Multi-Turn | 1473 | — |
Frequently asked questions
Is GLM-5.1 better than Qwen3-4B?
GLM-5.1 is the stronger model overall, scoring 47.6 to 31.5 on the Noometry Index.
How many benchmarks do GLM-5.1 and Qwen3-4B share?
4 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Qwen3-4B has 6.