Noometry

Model comparison

Claude Opus 4 vs Hy3

Hy3 is the stronger model overall, scoring 44.2 to 43.1 on the Noometry Index.

Last verified . 17 shared benchmarks.

Claude Opus 4 Anthropic

43.1

Rank #100 Confirmed

Hy3 Tencent

44.2

Rank #79 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Claude Opus 4 scores higher in 5 categories and Hy3 in 3 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in multilingual, where Hy3 leads 53.5 to 48.8.
  • Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $15 / $75 for Claude Opus 4.
  • Hy3 accepts more context: 262K tokens versus 200K.
  • Hy3 has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4Hy3
ProviderAnthropicTencent
Noometry Index43.144.2
Released2025-05-222026-07-06
WeightsProprietaryOpen
Context window200K262K
Max output32K128K
Input $ / M tokens$15$0.0825
Output $ / M tokens$75$0.33
Results tracked5619

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

Category by category

Coding Too close to call

Claude Opus 4: 47.2 (#62), Hy3: 46.8 (#63)

BenchmarkClaude Opus 4Hy3
LMArena Coding14421464
SWE-bench Verified70.7%—
SWE-bench Verified (bash only)67.6%—
Aider Polyglot72%—
LMArena WebDev—1508
GSO6.9%—
WeirdML43.7%—
AlgoTune1.33—

Agentic & Tool Use Not comparable

Claude Opus 4: 34.8 (#42), Hy3: —

BenchmarkClaude Opus 4Hy3
Cybench38%—
DeepResearch Bench46.8%—
LMArena Search1127—
METR Time Horizons63.9%—

Reasoning Claude Opus 4 leads

Claude Opus 4: 27.3 (#121), Hy3: 26.1 (#136)

BenchmarkClaude Opus 4Hy3
LMArena Hard Prompts13991447
ARC-AGI-28.6%—
SimpleBench58.8%—
Kagi LLM Benchmark74.3%—
NYT Connections (extended)—41.2%
ARC-AGI-135.7%—
CritPt0.3%—
EnigmaEval5.6%—
DTBench81.6%—
LMCA37.4%—
Epoch Capabilities Index142.67—
ForecastBench61.1—

Math Claude Opus 4 leads

Claude Opus 4: 42.0 (#86), Hy3: 40.1 (#93)

BenchmarkClaude Opus 4Hy3
LMArena Math13901475
OTIS Mock AIME 2024-202564.4%—
Omni-MATH61.6%—
MATH Level 585%—
FrontierMath (Feb 2025 set)4.5%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Claude Opus 4 leads

Claude Opus 4: 44.0 (#88), Hy3: 40.8 (#114)

BenchmarkClaude Opus 4Hy3
LMArena Expert13861460
GPQA Diamond76.3%—
Humanity's Last Exam10.7%—
MMLU-Pro87.5%—
Confabulations15.9%—
Vectara Hallucination Rate12%—
GPQA (HELM)70.8%—

Multimodal Not comparable

Claude Opus 4: 31.5 (#106), Hy3: —

BenchmarkClaude Opus 4Hy3
LMArena Vision1192—
GeoBench49%—
VPCT38%—

Multilingual Hy3 leads

Claude Opus 4: 48.8 (#138), Hy3: 53.5 (#65)

BenchmarkClaude Opus 4Hy3
LMArena Non-English13621426
LMArena Chinese13861493
LMArena French13721461
LMArena German13911439
LMArena Japanese13311392
LMArena Korean13211395
LMArena Russian13921432
LMArena Spanish13891456

Instruction Following Claude Opus 4 leads

Claude Opus 4: 77.1 (#28), Hy3: 75.1 (#70)

BenchmarkClaude Opus 4Hy3
LMArena Instruction Following14061426
IFEval91.8%—

Long Context Hy3 leads

Claude Opus 4: 39.6 (#172), Hy3: 44.1 (#75)

BenchmarkClaude Opus 4Hy3
LMArena Longer Query14221442
Fiction.LiveBench61.1%—

Writing & Preference Hy3 leads

Claude Opus 4: 61.2 (#89), Hy3: 62.2 (#81)

BenchmarkClaude Opus 4Hy3
LMArena Text13771439
LMArena Creative Writing13871402
LMArena Multi-Turn13961436
Short-Story Creative Writing83.6%—
EQ-Bench Creative Writing1580—
WildBench85.2%—

Frequently asked questions

Is Claude Opus 4 better than Hy3?

Hy3 is the stronger model overall, scoring 44.2 to 43.1 on the Noometry Index.

Which is cheaper, Claude Opus 4 or Hy3?

Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; Claude Opus 4 lists at $15 and $75.

Is Claude Opus 4 or Hy3 better for coding?

They score almost the same on coding (47.2 vs 46.8); test both on your own repository before choosing.

Which has the bigger context window?

Hy3 does, with 262K tokens against 200K.

How many benchmarks do Claude Opus 4 and Hy3 share?

17 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and Hy3 has 19.

Related comparisons

Go deeper