Noometry

Model comparison

Hy3 vs Qwen3.7 Plus

Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 44.2 on the Noometry Index. Hy3 costs 4.8× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.

Last verified . 18 shared benchmarks.

Hy3 Tencent

44.2

Rank #79 Confirmed

Qwen3.7 Plus Alibaba (Qwen)

45.3

Rank #72 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Hy3 scores higher in 1 category and Qwen3.7 Plus in 7 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3.7 Plus leads 54.9 to 40.8.
  • The biggest single-benchmark swing is NYT Connections (extended): 41.2% for Hy3 and 74.8% for Qwen3.7 Plus.
  • Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $0.40 / $1.60 for Qwen3.7 Plus.
  • Qwen3.7 Plus accepts more context: 1M tokens versus 262K.
  • Hy3 has downloadable open weights; the other is API-only.

Side by side

Hy3Qwen3.7 Plus
ProviderTencentAlibaba (Qwen)
Noometry Index44.245.3
Released2026-07-062026-06-02
WeightsOpenProprietary
Context window262K1M
Max output128K131K
Input $ / M tokens$0.0825$0.40
Output $ / M tokens$0.33$1.60
Results tracked1932

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Hy3 leads

Hy3: 46.8 (#63), Qwen3.7 Plus: 36.6 (#206)

BenchmarkHy3Qwen3.7 Plus
LMArena Coding14641473
FrontierCode—10.2%
LMArena WebDev1508—
SciCode—45.5%

Agentic & Tool Use Not comparable

Hy3: —, Qwen3.7 Plus: 21.4 (#138)

BenchmarkHy3Qwen3.7 Plus
OSWorld 2.0—2.8%

Reasoning Qwen3.7 Plus leads

Hy3: 26.1 (#136), Qwen3.7 Plus: 39.3 (#59)

BenchmarkHy3Qwen3.7 Plus
NYT Connections (extended)41.2%74.8%
LMArena Hard Prompts14471460
CritPt—9.1%
Chess Puzzles—24%
Mystery Game Puzzles—17%
DTBench—84%
LMCA—37.6%
Epoch Capabilities Index—147.37

Math Qwen3.7 Plus leads

Hy3: 40.1 (#93), Qwen3.7 Plus: 50.5 (#56)

BenchmarkHy3Qwen3.7 Plus
LMArena Math14751466
FrontierMath (Tiers 1-3)—34.4%
OTIS Mock AIME 2024-2025—93.3%

Knowledge Qwen3.7 Plus leads

Hy3: 40.8 (#114), Qwen3.7 Plus: 54.9 (#51)

BenchmarkHy3Qwen3.7 Plus
LMArena Expert14601467
GPQA Diamond—87.9%

Multimodal Not comparable

Hy3: —, Qwen3.7 Plus: 41.8 (#33)

BenchmarkHy3Qwen3.7 Plus
LMArena Vision—1279
LMArena Document—1444

Multilingual Qwen3.7 Plus leads

Hy3: 53.5 (#65), Qwen3.7 Plus: 54.8 (#38)

BenchmarkHy3Qwen3.7 Plus
LMArena Non-English14261445
LMArena Chinese14931510
LMArena French14611473
LMArena German14391471
LMArena Japanese13921413
LMArena Korean13951415
LMArena Russian14321457
LMArena Spanish14561457

Instruction Following Too close to call

Hy3: 75.1 (#70), Qwen3.7 Plus: 75.8 (#52)

BenchmarkHy3Qwen3.7 Plus
LMArena Instruction Following14261440

Long Context Too close to call

Hy3: 44.1 (#75), Qwen3.7 Plus: 44.5 (#65)

BenchmarkHy3Qwen3.7 Plus
LMArena Longer Query14421455

Writing & Preference Qwen3.7 Plus leads

Hy3: 62.2 (#81), Qwen3.7 Plus: 64.3 (#56)

BenchmarkHy3Qwen3.7 Plus
LMArena Text14391455
LMArena Creative Writing14021439
LMArena Multi-Turn14361460

Frequently asked questions

Is Hy3 better than Qwen3.7 Plus?

Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 44.2 on the Noometry Index. Hy3 costs 4.8× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.

Which is cheaper, Hy3 or Qwen3.7 Plus?

Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; Qwen3.7 Plus lists at $0.40 and $1.60.

Is Hy3 or Qwen3.7 Plus better for coding?

Hy3 scores higher on coding benchmarks: 46.8 versus 36.6 in the Noometry coding category.

Which has the bigger context window?

Qwen3.7 Plus does, with 1M tokens against 262K.

How many benchmarks do Hy3 and Qwen3.7 Plus share?

18 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Qwen3.7 Plus has 32.

Related comparisons

Go deeper