Model comparison
Qwen3 14B vs Qwen3.7 Max
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 35.5 on the Noometry Index. Qwen3 14B costs 6.1× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Last verified . 8 shared benchmarks.
Alibaba (Qwen)Summary
- They share 8 benchmarks with published results for both. Qwen3 14B scores higher in 1 category and Qwen3.7 Max in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.7 Max leads 49.2 to 18.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 66.4% for Qwen3 14B and 95.6% for Qwen3.7 Max.
- Qwen3 14B is cheaper at $0.35 / $1.40 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
- Qwen3.7 Max accepts more context: 1M tokens versus 131K.
- Qwen3 14B has downloadable open weights; the other is API-only.
Side by side
| Qwen3 14B | Qwen3.7 Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 35.5 | 51.5 |
| Released | 2025-04 | 2026-05-19 |
| Weights | Open | Proprietary |
| Context window | 131K | 1M |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.35 | $2.50 |
| Output $ / M tokens | $1.40 | $7.50 |
| Results tracked | 12 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Max leads
Qwen3 14B: 37.3 (#195), Qwen3.7 Max: 50.4 (#45)
| Benchmark | Qwen3 14B | Qwen3.7 Max |
|---|---|---|
| SciCode | 31.6% | 48.8% |
| SWE-bench Verified | — | 77.3% |
| LMArena WebDev | — | 1515 |
| LMArena Coding | — | 1498 |
| ALE-Bench | — | 1,189 |
Agentic & Tool Use Qwen3 14B leads
Qwen3 14B: 29.6 (#83), Qwen3.7 Max: 22.1 (#135)
| Benchmark | Qwen3 14B | Qwen3.7 Max |
|---|---|---|
| Berkeley Function Calling Leaderboard | 41% | — |
| GBAEval | — | 0.4% |
Reasoning Qwen3.7 Max leads
Qwen3 14B: 18.5 (#280), Qwen3.7 Max: 49.2 (#38)
| Benchmark | Qwen3 14B | Qwen3.7 Max |
|---|---|---|
| CritPt | 0% | 13.4% |
| Chess Puzzles | 4% | 19% |
| DTBench | 64% | 92.3% |
| LMCA | 18.2% | 44% |
| Epoch Capabilities Index | 138.23 | 153.68 |
| SimpleBench | — | 70.4% |
| Kagi LLM Benchmark | 49.1% | — |
| NYT Connections (extended) | — | 85.1% |
| EBR-Bench | — | 9.5% |
| LMArena Hard Prompts | — | 1483 |
| Mystery Game Puzzles | — | 32% |
Math Qwen3.7 Max leads
Qwen3 14B: 38.6 (#133), Qwen3.7 Max: 62.4 (#32)
| Benchmark | Qwen3 14B | Qwen3.7 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.4% | 95.6% |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| ProofBench | — | 26% |
| LMArena Math | — | 1490 |
Knowledge Qwen3.7 Max leads
Qwen3 14B: 39.3 (#134), Qwen3.7 Max: 61.6 (#28)
| Benchmark | Qwen3 14B | Qwen3.7 Max |
|---|---|---|
| GPQA Diamond | 63.8% | 90.9% |
| SimpleQA Verified | — | 55.8% |
| Vectara Hallucination Rate | 5.4% | — |
| LMArena Expert | — | 1488 |
Multilingual Not comparable
Qwen3 14B: —, Qwen3.7 Max: 56.9 (#15)
| Benchmark | Qwen3 14B | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | — | 1474 |
| LMArena Chinese | — | 1530 |
| LMArena Russian | — | 1484 |
Instruction Following Not comparable
Qwen3 14B: —, Qwen3.7 Max: 76.7 (#38)
| Benchmark | Qwen3 14B | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | — | 1460 |
Long Context Qwen3.7 Max leads
Qwen3 14B: 38.1 (#204), Qwen3.7 Max: 45.4 (#40)
| Benchmark | Qwen3 14B | Qwen3.7 Max |
|---|---|---|
| Fiction.LiveBench | 62.5% | — |
| LMArena Longer Query | — | 1482 |
Writing & Preference Not comparable
Qwen3 14B: —, Qwen3.7 Max: 65.0 (#54)
| Benchmark | Qwen3 14B | Qwen3.7 Max |
|---|---|---|
| LMArena Text | — | 1476 |
| LMArena Creative Writing | — | 1449 |
| EQ-Bench 4 | — | 1110 |
| LMArena Multi-Turn | — | 1481 |
Frequently asked questions
Is Qwen3 14B better than Qwen3.7 Max?
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 35.5 on the Noometry Index. Qwen3 14B costs 6.1× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Which is cheaper, Qwen3 14B or Qwen3.7 Max?
Qwen3 14B is cheaper. It lists at $0.35 per million input tokens and $1.40 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.
Is Qwen3 14B or Qwen3.7 Max better for coding?
Qwen3.7 Max scores higher on coding benchmarks: 50.4 versus 37.3 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Max does, with 1M tokens against 131K.
How many benchmarks do Qwen3 14B and Qwen3.7 Max share?
8 benchmarks have published results for both models. Qwen3 14B has 12 scored results on Noometry and Qwen3.7 Max has 33.