Noometry

Model comparison

Claude Opus 4.1 vs Hy3

Hy3 is the stronger model overall, scoring 44.2 to 41.0 on the Noometry Index.

Last verified . 18 shared benchmarks.

Claude Opus 4.1 Anthropic

41.0

Rank #142 Confirmed

Hy3 Tencent

44.2

Rank #79 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Claude Opus 4.1 scores higher in 5 categories and Hy3 in 3 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in math, where Hy3 leads 40.1 to 22.3.
  • Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.
  • Hy3 accepts more context: 262K tokens versus 200K.
  • Hy3 has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4.1Hy3
ProviderAnthropicTencent
Noometry Index41.044.2
Released2025-08-052026-07-06
WeightsProprietaryOpen
Context window200K262K
Max output32K128K
Input $ / M tokens$15$0.0825
Output $ / M tokens$75$0.33
Results tracked4819

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

Category by category

Coding Hy3 leads

Claude Opus 4.1: 44.4 (#73), Hy3: 46.8 (#63)

BenchmarkClaude Opus 4.1Hy3
LMArena WebDev13901508
LMArena Coding14791464
SWE-bench Verified73.3%—
WeirdML45.9%—
ALE-Bench674.77—
AlgoTune1.34—

Agentic & Tool Use Not comparable

Claude Opus 4.1: 35.0 (#41), Hy3: —

BenchmarkClaude Opus 4.1Hy3
Terminal-Bench38%—
GDPval43.6%—
Cybench42%—
DeepResearch Bench48.3%—
LMArena Search1148—
METR Time Horizons66.8%—

Reasoning Claude Opus 4.1 leads

Claude Opus 4.1: 32.2 (#76), Hy3: 26.1 (#136)

BenchmarkClaude Opus 4.1Hy3
LMArena Hard Prompts14431447
SimpleBench60%—
NYT Connections (extended)—41.2%
Chess Puzzles7%—
EnigmaEval7.2%—
EBR-Bench7.9%—
Mystery Game Puzzles21%—
DTBench80%—
LMCA37.1%—
Epoch Capabilities Index144.12—
ForecastBench62—

Math Hy3 leads

Claude Opus 4.1: 22.3 (#277), Hy3: 40.1 (#93)

BenchmarkClaude Opus 4.1Hy3
LMArena Math14311475
FrontierMath (Tiers 1-3)12.6%—
FrontierMath Tier 42.4%—
OTIS Mock AIME 2024-202568.9%—
FrontierMath (Feb 2025 set)7.2%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Claude Opus 4.1 leads

Claude Opus 4.1: 42.0 (#101), Hy3: 40.8 (#114)

BenchmarkClaude Opus 4.1Hy3
LMArena Expert14391460
GPQA Diamond77.3%—
Humanity's Last Exam11.5%—
Confabulations17.1%—
Vectara Hallucination Rate11.8%—

Multimodal Not comparable

Claude Opus 4.1: 26.8 (#119), Hy3: —

BenchmarkClaude Opus 4.1Hy3
VPCT35%—

Multilingual Hy3 leads

Claude Opus 4.1: 52.0 (#95), Hy3: 53.5 (#65)

BenchmarkClaude Opus 4.1Hy3
LMArena Non-English14051426
LMArena Chinese14271493
LMArena French14311461
LMArena German14131439
LMArena Japanese13781392
LMArena Korean13801395
LMArena Russian14221432
LMArena Spanish14481456

Instruction Following Too close to call

Claude Opus 4.1: 75.6 (#58), Hy3: 75.1 (#70)

BenchmarkClaude Opus 4.1Hy3
LMArena Instruction Following14351426

Long Context Too close to call

Claude Opus 4.1: 44.5 (#63), Hy3: 44.1 (#75)

BenchmarkClaude Opus 4.1Hy3
LMArena Longer Query14551442

Writing & Preference Too close to call

Claude Opus 4.1: 62.4 (#74), Hy3: 62.2 (#81)

BenchmarkClaude Opus 4.1Hy3
LMArena Text14191439
LMArena Creative Writing14121402
LMArena Multi-Turn14441436
Short-Story Creative Writing84.7%—

Frequently asked questions

Is Claude Opus 4.1 better than Hy3?

Hy3 is the stronger model overall, scoring 44.2 to 41.0 on the Noometry Index.

Which is cheaper, Claude Opus 4.1 or Hy3?

Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; Claude Opus 4.1 lists at $15 and $75.

Is Claude Opus 4.1 or Hy3 better for coding?

Hy3 scores higher on coding benchmarks: 46.8 versus 44.4 in the Noometry coding category.

Which has the bigger context window?

Hy3 does, with 262K tokens against 200K.

How many benchmarks do Claude Opus 4.1 and Hy3 share?

18 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and Hy3 has 19.

Related comparisons

Go deeper