Model comparison

Hy3 vs Inkling

Hy3 and Inkling score almost the same on the Noometry Index (44.2 vs 44.1), 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

Inkling Thinking Machines Lab

44.1

Rank #80 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Hy3 scores higher in 3 categories and Inkling in 5 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Inkling leads 40.4 to 26.1.
  • Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $1.87 / $4.68 for Inkling.
  • Hy3 accepts more context: 262K tokens versus 66K.

Side by side

Hy3 and Inkling specifications
Hy3Inkling
ProviderTencentThinking Machines Lab
Noometry Index44.244.1
Released2026-07-062026-07-15
WeightsOpenOpen
Context window262K66K
Max output128K66K
Input $ / M tokens$0.0825$1.87
Output $ / M tokens$0.33$4.68
Results tracked1941

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

Category by category

Coding Hy3 leads

Hy3: 46.8 (#63), Inkling: 34.5 (#234)

Coding benchmarks
BenchmarkHy3Inkling
LMArena WebDev15081413
LMArena Coding14641464
FrontierCode—14%
FrontierSWE—4.1%
SciCode—47%
WeirdML—32.3%
ALE-Bench—946

Agentic & Tool Use Not comparable

Hy3: —, Inkling: 29.6 (#85)

Agentic & Tool Use benchmarks
BenchmarkHy3Inkling
APEX-Agents—33.8%
τ²-bench Banking—25%

Reasoning Inkling leads

Hy3: 26.1 (#136), Inkling: 40.4 (#56)

Reasoning benchmarks
BenchmarkHy3Inkling
LMArena Hard Prompts14471451
ARC-AGI-2—36.5%
SimpleBench—50%
NYT Connections (extended)41.2%—
ARC-AGI-1—79.5%
CritPt—5.4%
Chess Puzzles—21%
DTBench—87.5%
LMCA—37.6%
Epoch Capabilities Index—148.54

Math Hy3 leads

Hy3: 40.1 (#93), Inkling: 31.3 (#225)

Math benchmarks
BenchmarkHy3Inkling
LMArena Math14751479
FrontierMath (Tiers 1-3)—33.3%
FrontierMath Tier 4—4.9%
OTIS Mock AIME 2024-2025—88.9%
ProofBench—0%

Knowledge Inkling leads

Hy3: 40.8 (#114), Inkling: 55.1 (#49)

Knowledge benchmarks
BenchmarkHy3Inkling
LMArena Expert14601465
GPQA Diamond—88.3%
SimpleQA Verified—40.3%

Multilingual Too close to call

Hy3: 53.5 (#65), Inkling: 54.0 (#52)

Multilingual benchmarks
BenchmarkHy3Inkling
LMArena Non-English14261434
LMArena Chinese14931490
LMArena French14611458
LMArena German14391446
LMArena Japanese13921429
LMArena Korean13951404
LMArena Russian14321429
LMArena Spanish14561448

Instruction Following Too close to call

Hy3: 75.1 (#70), Inkling: 75.1 (#71)

Instruction Following benchmarks
BenchmarkHy3Inkling
LMArena Instruction Following14261426

Long Context Too close to call

Hy3: 44.1 (#75), Inkling: 43.8 (#86)

Long Context benchmarks
BenchmarkHy3Inkling
LMArena Longer Query14421434

Writing & Preference Inkling leads

Hy3: 62.2 (#81), Inkling: 65.2 (#51)

Writing & Preference benchmarks
BenchmarkHy3Inkling
LMArena Text14391441
LMArena Creative Writing14021387
LMArena Multi-Turn14361436
EQ-Bench Creative Writing—1611
EQ-Bench 4—1226

Frequently asked questions

Is Hy3 better than Inkling?

Hy3 and Inkling score almost the same on the Noometry Index (44.2 vs 44.1), so choose on price, context window or the category you care about most.

Which is cheaper, Hy3 or Inkling?

Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; Inkling lists at $1.87 and $4.68.

Is Hy3 or Inkling better for coding?

Hy3 scores higher on coding benchmarks: 46.8 versus 34.5 in the Noometry coding category.

Which has the bigger context window?

Hy3 does, with 262K tokens against 66K.

How many benchmarks do Hy3 and Inkling share?

18 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Inkling has 41.

Related comparisons

Go deeper