Noometry

Model comparison

Hy3 vs Qwen3 Max

Hy3 and Qwen3 Max score almost the same on the Noometry Index (44.2 vs 43.7), so choose on price, context window or the category you care about most.

Last verified . 18 shared benchmarks.

Hy3 Tencent

44.2

Rank #79 Confirmed

Qwen3 Max Alibaba (Qwen)

43.7

Rank #87 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Hy3 scores higher in 5 categories and Qwen3 Max in 3 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3 Max leads 48.1 to 40.8.
  • The biggest single-benchmark swing is NYT Connections (extended): 41.2% for Hy3 and 30.1% for Qwen3 Max.
  • Hy3 is cheaper at $0.13 / $0.53 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
  • Hy3 has downloadable open weights; the other is API-only.

Side by side

Hy3Qwen3 Max
ProviderTencentAlibaba (Qwen)
Noometry Index44.243.7
Released2026-07-062025-09-23
WeightsOpenProprietary
Context window262K262K
Max output128K66K
Input $ / M tokens$0.13$1.20
Output $ / M tokens$0.53$6
Results tracked1933

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

Category by category

Coding Hy3 leads

Hy3: 46.8 (#63), Qwen3 Max: 43.0 (#93)

BenchmarkHy3Qwen3 Max
LMArena Coding14641456
LMArena WebDev1508—
ALE-Bench—370.45

Agentic & Tool Use Not comparable

Hy3: —, Qwen3 Max: —

BenchmarkHy3Qwen3 Max
Vending-Bench 2—71.56

Reasoning Hy3 leads

Hy3: 26.1 (#136), Qwen3 Max: 22.6 (#190)

BenchmarkHy3Qwen3 Max
NYT Connections (extended)41.2%30.1%
LMArena Hard Prompts14471448
Kagi LLM Benchmark—72.5%
Chess Puzzles—4%
Mystery Game Puzzles—5%
DTBench—82.1%
LMCA—28.3%
Epoch Capabilities Index—142.38

Math Hy3 leads

Hy3: 40.1 (#93), Qwen3 Max: 38.7 (#131)

BenchmarkHy3Qwen3 Max
LMArena Math14751446
FrontierMath (Tiers 1-3)—18.9%
OTIS Mock AIME 2024-2025—73.3%
MATH Level 5—97.1%

Knowledge Qwen3 Max leads

Hy3: 40.8 (#114), Qwen3 Max: 48.1 (#78)

BenchmarkHy3Qwen3 Max
LMArena Expert14601455
GPQA Diamond—72.6%
SimpleQA Verified—48.7%

Multilingual Too close to call

Hy3: 53.5 (#65), Qwen3 Max: 53.7 (#62)

BenchmarkHy3Qwen3 Max
LMArena Non-English14261429
LMArena Chinese14931478
LMArena French14611449
LMArena German14391463
LMArena Japanese13921397
LMArena Korean13951399
LMArena Russian14321428
LMArena Spanish14561462

Instruction Following Too close to call

Hy3: 75.1 (#70), Qwen3 Max: 74.8 (#87)

BenchmarkHy3Qwen3 Max
LMArena Instruction Following14261419

Long Context Hy3 leads

Hy3: 44.1 (#75), Qwen3 Max: 41.6 (#134)

BenchmarkHy3Qwen3 Max
LMArena Longer Query14421438
Fiction.LiveBench—66.7%
CL-bench—14.5%

Writing & Preference Too close to call

Hy3: 62.2 (#81), Qwen3 Max: 62.4 (#76)

BenchmarkHy3Qwen3 Max
LMArena Text14391439
LMArena Creative Writing14021402
LMArena Multi-Turn14361446

Frequently asked questions

Is Hy3 better than Qwen3 Max?

Hy3 and Qwen3 Max score almost the same on the Noometry Index (44.2 vs 43.7), so choose on price, context window or the category you care about most.

Which is cheaper, Hy3 or Qwen3 Max?

Hy3 is cheaper. It lists at $0.13 per million input tokens and $0.53 per million output tokens; Qwen3 Max lists at $1.20 and $6.

Is Hy3 or Qwen3 Max better for coding?

Hy3 scores higher on coding benchmarks: 46.8 versus 43.0 in the Noometry coding category.

Which has the bigger context window?

Both accept 262K tokens.

How many benchmarks do Hy3 and Qwen3 Max share?

18 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Qwen3 Max has 33.

Related comparisons

Go deeper