Model comparison
Qwen-14B vs Qwen3.7 Max
Qwen3.7 Max is the stronger model overall, scoring 51.4 to 30.8 on the Noometry Index.
Last verified . 11 shared benchmarks.
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. Qwen-14B scores higher in 0 categories and Qwen3.7 Max in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.7 Max leads 65.2 to 27.8.
- Qwen-14B has downloadable open weights; the other is API-only.
Side by side
| Qwen-14B | Qwen3.7 Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 30.8 | 51.4 |
| Released | 2023-09-24 | 2026-05-19 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 131K |
| Input $ / M tokens | — | $2.50 |
| Output $ / M tokens | — | $7.50 |
| Results tracked | 18 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Max leads
Qwen-14B: 30.6 (#283), Qwen3.7 Max: 50.2 (#43)
| Benchmark | Qwen-14B | Qwen3.7 Max |
|---|---|---|
| LMArena Coding | 1072 | 1498 |
| SWE-bench Verified | — | 77.3% |
| LMArena WebDev | — | 1515 |
| SciCode | — | 48.8% |
| ALE-Bench | — | 1,189 |
Agentic & Tool Use Not comparable
Qwen-14B: —, Qwen3.7 Max: 21.8 (#129)
| Benchmark | Qwen-14B | Qwen3.7 Max |
|---|---|---|
| GBAEval | — | 0.4% |
Reasoning Qwen3.7 Max leads
Qwen-14B: 18.7 (#255), Qwen3.7 Max: 48.4 (#36)
| Benchmark | Qwen-14B | Qwen3.7 Max |
|---|---|---|
| LMArena Hard Prompts | 1027 | 1483 |
| Epoch Capabilities Index | 112.8 | 153.74 |
| SimpleBench | — | 70.4% |
| NYT Connections (extended) | — | 85.1% |
| CritPt | — | 13.4% |
| Chess Puzzles | — | 19% |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 32% |
| DTBench | — | 92.3% |
| LMCA | — | 44% |
| BIG-Bench Hard | 55% | — |
| LAMBADA | 71.1% | — |
| PIQA | 79.9% | — |
Math Qwen3.7 Max leads
Qwen-14B: 28.7 (#224), Qwen3.7 Max: 62.3 (#26)
| Benchmark | Qwen-14B | Qwen3.7 Max |
|---|---|---|
| LMArena Math | 1068 | 1488 |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 26% |
| GSM8K | 61.3% | — |
Knowledge Not comparable
Qwen-14B: —, Qwen3.7 Max: 61.7 (#24)
| Benchmark | Qwen-14B | Qwen3.7 Max |
|---|---|---|
| GPQA Diamond | — | 90.9% |
| SimpleQA Verified | — | 55.8% |
| LMArena Expert | — | 1488 |
| ARC (AI2) Challenge | 84.4% | — |
| BoolQ | 86.2% | — |
| MMLU | 66.3% | — |
Multilingual Qwen3.7 Max leads
Qwen-14B: 27.7 (#270), Qwen3.7 Max: 57.1 (#13)
| Benchmark | Qwen-14B | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1042 | 1475 |
| LMArena Chinese | 1077 | 1533 |
| LMArena Russian | — | 1482 |
Instruction Following Qwen3.7 Max leads
Qwen-14B: 52.6 (#284), Qwen3.7 Max: 76.9 (#34)
| Benchmark | Qwen-14B | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1031 | 1460 |
Long Context Qwen3.7 Max leads
Qwen-14B: 31.3 (#276), Qwen3.7 Max: 45.4 (#34)
| Benchmark | Qwen-14B | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1029 | 1484 |
Writing & Preference Qwen3.7 Max leads
Qwen-14B: 27.8 (#294), Qwen3.7 Max: 65.2 (#52)
| Benchmark | Qwen-14B | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1051 | 1476 |
| LMArena Creative Writing | 1028 | 1450 |
| LMArena Multi-Turn | 1022 | 1482 |
| EQ-Bench 4 | — | 1110 |
Frequently asked questions
Is Qwen-14B better than Qwen3.7 Max?
Qwen3.7 Max is the stronger model overall, scoring 51.4 to 30.8 on the Noometry Index.
Is Qwen-14B or Qwen3.7 Max better for coding?
Qwen3.7 Max scores higher on coding benchmarks: 50.2 versus 30.6 in the Noometry coding category.
How many benchmarks do Qwen-14B and Qwen3.7 Max share?
11 benchmarks have published results for both models. Qwen-14B has 18 scored results on Noometry and Qwen3.7 Max has 33.