Model comparison
Qwen3-4B vs Qwen3.7 Plus
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 31.9 on the Noometry Index.
Last verified . 3 shared benchmarks.
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. Qwen3-4B scores higher in 1 category and Qwen3.7 Plus in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.7 Plus leads 54.9 to 33.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 52.2% for Qwen3-4B and 93.3% for Qwen3.7 Plus.
- Qwen3-4B has downloadable open weights; the other is API-only.
Side by side
| Qwen3-4B | Qwen3.7 Plus | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 31.9 | 45.3 |
| Released | 2025-04-29 | 2026-06-02 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.40 |
| Output $ / M tokens | — | $1.60 |
| Results tracked | 6 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Qwen3-4B: —, Qwen3.7 Plus: 36.6 (#206)
| Benchmark | Qwen3-4B | Qwen3.7 Plus |
|---|---|---|
| FrontierCode | — | 10.2% |
| SciCode | — | 45.5% |
| LMArena Coding | — | 1473 |
Agentic & Tool Use Qwen3-4B leads
Qwen3-4B: 27.6 (#100), Qwen3.7 Plus: 21.4 (#138)
| Benchmark | Qwen3-4B | Qwen3.7 Plus |
|---|---|---|
| Berkeley Function Calling Leaderboard | 35.7% | — |
| OSWorld 2.0 | — | 2.8% |
Reasoning Qwen3.7 Plus leads
Qwen3-4B: 19.2 (#268), Qwen3.7 Plus: 39.3 (#59)
| Benchmark | Qwen3-4B | Qwen3.7 Plus |
|---|---|---|
| Chess Puzzles | 4% | 24% |
| NYT Connections (extended) | — | 74.8% |
| CritPt | — | 9.1% |
| LMArena Hard Prompts | — | 1460 |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84% |
| LMCA | — | 37.6% |
| Epoch Capabilities Index | — | 147.37 |
Math Qwen3.7 Plus leads
Qwen3-4B: 29.7 (#240), Qwen3.7 Plus: 50.5 (#56)
| Benchmark | Qwen3-4B | Qwen3.7 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 52.2% | 93.3% |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| MathArena Final-Answer Competitions | 38.5% | — |
| LMArena Math | — | 1466 |
Knowledge Qwen3.7 Plus leads
Qwen3-4B: 33.0 (#208), Qwen3.7 Plus: 54.9 (#51)
| Benchmark | Qwen3-4B | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 52.3% | 87.9% |
| Vectara Hallucination Rate | 5.7% | — |
| LMArena Expert | — | 1467 |
Multimodal Not comparable
Qwen3-4B: —, Qwen3.7 Plus: 41.8 (#33)
| Benchmark | Qwen3-4B | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1279 |
| LMArena Document | — | 1444 |
Multilingual Not comparable
Qwen3-4B: —, Qwen3.7 Plus: 54.8 (#38)
| Benchmark | Qwen3-4B | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | — | 1445 |
| LMArena Chinese | — | 1510 |
| LMArena French | — | 1473 |
| LMArena German | — | 1471 |
| LMArena Japanese | — | 1413 |
| LMArena Korean | — | 1415 |
| LMArena Russian | — | 1457 |
| LMArena Spanish | — | 1457 |
Instruction Following Not comparable
Qwen3-4B: —, Qwen3.7 Plus: 75.8 (#52)
| Benchmark | Qwen3-4B | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | — | 1440 |
Long Context Not comparable
Qwen3-4B: —, Qwen3.7 Plus: 44.5 (#65)
| Benchmark | Qwen3-4B | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | — | 1455 |
Writing & Preference Not comparable
Qwen3-4B: —, Qwen3.7 Plus: 64.3 (#56)
| Benchmark | Qwen3-4B | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | — | 1455 |
| LMArena Creative Writing | — | 1439 |
| LMArena Multi-Turn | — | 1460 |
Frequently asked questions
Is Qwen3-4B better than Qwen3.7 Plus?
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 31.9 on the Noometry Index.
How many benchmarks do Qwen3-4B and Qwen3.7 Plus share?
3 benchmarks have published results for both models. Qwen3-4B has 6 scored results on Noometry and Qwen3.7 Plus has 32.