Noometry

Model comparison

Claude 3.7 Sonnet vs Hy3

Hy3 is the stronger model overall, scoring 44.2 to 39.5 on the Noometry Index.

Last verified . 17 shared benchmarks.

Claude 3.7 Sonnet Anthropic

39.5

Rank #164 Confirmed

Hy3 Tencent

44.2

Rank #79 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 1 category and Hy3 in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in multilingual, where Hy3 leads 53.5 to 44.1.
  • Hy3 has downloadable open weights; the other is API-only.

Side by side

Claude 3.7 SonnetHy3
ProviderAnthropicTencent
Noometry Index39.544.2
Released2025-02-242026-07-06
WeightsProprietaryOpen
Context window—262K
Max output—128K
Input $ / M tokens—$0.13
Output $ / M tokens—$0.53
Results tracked5819

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

Category by category

Coding Hy3 leads

Claude 3.7 Sonnet: 40.6 (#136), Hy3: 46.8 (#63)

BenchmarkClaude 3.7 SonnetHy3
LMArena Coding13611464
SWE-bench Verified61%—
SWE-bench Verified (bash only)52.8%—
Aider Polyglot64.9%—
LMArena WebDev—1508
GSO3.8%—
LiveBench Coding74.5%—
CadEval54%—

Agentic & Tool Use Not comparable

Claude 3.7 Sonnet: 34.1 (#50), Hy3: —

BenchmarkClaude 3.7 SonnetHy3
TheAgentCompany30.9%—
Cybench20%—
DeepResearch Bench43.6%—
OSWorld35.8%—
METR Time Horizons60%—

Reasoning Hy3 leads

Claude 3.7 Sonnet: 18.6 (#277), Hy3: 26.1 (#136)

BenchmarkClaude 3.7 SonnetHy3
LMArena Hard Prompts13331447
ARC-AGI-20.9%—
SimpleBench46.4%—
NYT Connections (extended)—41.2%
ARC-AGI-128.6%—
EnigmaEval4.2%—
LiveBench Reasoning87.8%—
LiveBench Data Analysis74%—
Epoch Capabilities Index141.16—
ForecastBench61.8—
LiveBench76.1%—

Math Hy3 leads

Claude 3.7 Sonnet: 37.5 (#153), Hy3: 40.1 (#93)

BenchmarkClaude 3.7 SonnetHy3
LMArena Math13371475
OTIS Mock AIME 2024-202557.8%—
Omni-MATH33%—
LiveBench Math79%—
MATH Level 591.2%—
FrontierMath (Feb 2025 set)4.1%—

Knowledge Hy3 leads

Claude 3.7 Sonnet: 39.8 (#130), Hy3: 40.8 (#114)

BenchmarkClaude 3.7 SonnetHy3
LMArena Expert13211460
GPQA Diamond79.7%—
Humanity's Last Exam8%—
MMLU-Pro78.4%—
Confabulations14.7%—
GPQA (HELM)60.8%—

Multimodal Not comparable

Claude 3.7 Sonnet: 33.7 (#95), Hy3: —

BenchmarkClaude 3.7 SonnetHy3
LMArena Vision1169—
GeoBench68%—
VPCT39%—
SpatialViz-Bench33.9%—

Multilingual Hy3 leads

Claude 3.7 Sonnet: 44.1 (#179), Hy3: 53.5 (#65)

BenchmarkClaude 3.7 SonnetHy3
LMArena Non-English12961426
LMArena Chinese12991493
LMArena French13031461
LMArena German13011439
LMArena Japanese12671392
LMArena Korean12491395
LMArena Russian13111432
LMArena Spanish12981456

Instruction Following Hy3 leads

Claude 3.7 Sonnet: 72.9 (#125), Hy3: 75.1 (#70)

BenchmarkClaude 3.7 SonnetHy3
LMArena Instruction Following13521426
LiveBench Instruction Following81.3%—
IFEval83.4%—

Long Context Claude 3.7 Sonnet leads

Claude 3.7 Sonnet: 50.3 (#10), Hy3: 44.1 (#75)

BenchmarkClaude 3.7 SonnetHy3
LMArena Longer Query13731442
Fiction.LiveBench83.3%—

Writing & Preference Hy3 leads

Claude 3.7 Sonnet: 54.4 (#150), Hy3: 62.2 (#81)

BenchmarkClaude 3.7 SonnetHy3
LMArena Text13141439
LMArena Creative Writing13321402
LMArena Multi-Turn13391436
Short-Story Creative Writing81.1%—
EQ-Bench Creative Writing1412—
WildBench81.4%—
LiveBench Language59.9%—

Frequently asked questions

Is Claude 3.7 Sonnet better than Hy3?

Hy3 is the stronger model overall, scoring 44.2 to 39.5 on the Noometry Index.

Is Claude 3.7 Sonnet or Hy3 better for coding?

Hy3 scores higher on coding benchmarks: 46.8 versus 40.6 in the Noometry coding category.

How many benchmarks do Claude 3.7 Sonnet and Hy3 share?

17 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Hy3 has 19.

Related comparisons

Go deeper