Model comparison

Hy4 preview vs Inkling

Hy4 preview is the stronger model overall, scoring 45.3 to 44.1 on the Noometry Index.

Last verified . 2 shared benchmarks.

Hy4 preview Tencent

45.3

Rank #73 Reported

Inkling Thinking Machines Lab

44.1

Rank #80 Confirmed

Summary

  • They share 2 benchmarks with published results for both. Hy4 preview scores higher in 2 categories and Inkling in 1 category; 3 gaps are clear of the uncertainty.
  • The widest gap is in math, where Hy4 preview leads 55.7 to 31.3.
  • The biggest single-benchmark swing is ProofBench: 75% for Hy4 preview and 0% for Inkling.
  • Hy4 preview is cheaper at $0.75 / $2.25 per million input/output tokens, against $1.87 / $4.68 for Inkling.
  • Hy4 preview accepts more context: 1.05M tokens versus 66K.

Side by side

Hy4 preview and Inkling specifications
Hy4 previewInkling
ProviderTencentThinking Machines Lab
Noometry Index45.344.1
Released2026-08-282026-07-15
WeightsOpenOpen
Context window1.05M66K
Max output64K66K
Input $ / M tokens$0.75$1.87
Output $ / M tokens$2.25$4.68
Results tracked341

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

Category by category

Coding Hy4 preview leads

Hy4 preview: 51.6 (#38), Inkling: 34.5 (#234)

Coding benchmarks
BenchmarkHy4 previewInkling
LMArena WebDev16321413
FrontierCode—14%
FrontierSWE—4.1%
SciCode—47%
WeirdML—32.3%
LMArena Coding—1464
ALE-Bench—946

Agentic & Tool Use Not comparable

Hy4 preview: —, Inkling: 29.6 (#85)

Agentic & Tool Use benchmarks
BenchmarkHy4 previewInkling
APEX-Agents—33.8%
τ²-bench Banking—25%

Reasoning Inkling leads

Hy4 preview: 31.9 (#79), Inkling: 40.4 (#56)

Reasoning benchmarks
BenchmarkHy4 previewInkling
ARC-AGI-2—36.5%
SimpleBench—50%
NYT Connections (extended)68.2%—
ARC-AGI-1—79.5%
CritPt—5.4%
Chess Puzzles—21%
LMArena Hard Prompts—1451
DTBench—87.5%
LMCA—37.6%
Epoch Capabilities Index—148.54

Math Hy4 preview leads

Hy4 preview: 55.7 (#42), Inkling: 31.3 (#225)

Math benchmarks
BenchmarkHy4 previewInkling
ProofBench75%0%
FrontierMath (Tiers 1-3)—33.3%
FrontierMath Tier 4—4.9%
OTIS Mock AIME 2024-2025—88.9%
LMArena Math—1479

Knowledge Not comparable

Hy4 preview: —, Inkling: 55.1 (#49)

Knowledge benchmarks
BenchmarkHy4 previewInkling
GPQA Diamond—88.3%
SimpleQA Verified—40.3%
LMArena Expert—1465

Multilingual Not comparable

Hy4 preview: —, Inkling: 54.0 (#52)

Multilingual benchmarks
BenchmarkHy4 previewInkling
LMArena Non-English—1434
LMArena Chinese—1490
LMArena French—1458
LMArena German—1446
LMArena Japanese—1429
LMArena Korean—1404
LMArena Russian—1429
LMArena Spanish—1448

Instruction Following Not comparable

Hy4 preview: —, Inkling: 75.1 (#71)

Instruction Following benchmarks
BenchmarkHy4 previewInkling
LMArena Instruction Following—1426

Long Context Not comparable

Hy4 preview: —, Inkling: 43.8 (#86)

Long Context benchmarks
BenchmarkHy4 previewInkling
LMArena Longer Query—1434

Writing & Preference Not comparable

Hy4 preview: —, Inkling: 65.2 (#51)

Writing & Preference benchmarks
BenchmarkHy4 previewInkling
LMArena Text—1441
LMArena Creative Writing—1387
EQ-Bench Creative Writing—1611
EQ-Bench 4—1226
LMArena Multi-Turn—1436

Frequently asked questions

Is Hy4 preview better than Inkling?

Hy4 preview is the stronger model overall, scoring 45.3 to 44.1 on the Noometry Index.

Which is cheaper, Hy4 preview or Inkling?

Hy4 preview is cheaper. It lists at $0.75 per million input tokens and $2.25 per million output tokens; Inkling lists at $1.87 and $4.68.

Is Hy4 preview or Inkling better for coding?

Hy4 preview scores higher on coding benchmarks: 51.6 versus 34.5 in the Noometry coding category.

Which has the bigger context window?

Hy4 preview does, with 1.05M tokens against 66K.

How many benchmarks do Hy4 preview and Inkling share?

2 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Inkling has 41.

Related comparisons

Go deeper