Noometry

Model comparison

Gemini 3 Pro vs Hy3

Gemini 3 Pro is the stronger model overall, scoring 54.8 to 44.2 on the Noometry Index.

Last verified . 19 shared benchmarks.

Gemini 3 Pro Google

54.8

Rank #28 Confirmed

Hy3 Tencent

44.2

Rank #79 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Gemini 3 Pro scores higher in 7 categories and Hy3 in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3 Pro leads 52.5 to 26.1.
  • The biggest single-benchmark swing is NYT Connections (extended): 94.4% for Gemini 3 Pro and 41.2% for Hy3.
  • Hy3 has downloadable open weights; the other is API-only.

Side by side

Gemini 3 ProHy3
ProviderGoogleTencent
Noometry Index54.844.2
Released2025-11-182026-07-06
WeightsProprietaryOpen
Context window—262K
Max output—128K
Input $ / M tokens—$0.0825
Output $ / M tokens—$0.33
Results tracked6719

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

Category by category

Coding Gemini 3 Pro leads

Gemini 3 Pro: 51.6 (#39), Hy3: 46.8 (#63)

BenchmarkGemini 3 ProHy3
LMArena WebDev14401508
LMArena Coding14811464
SWE-bench Verified72.9%—
SWE-bench Verified (bash only)74.2%—
SWE-bench Multilingual68.7%—
GSO18.6%—
WeirdML69.9%—
ALE-Bench1,177—
AlgoTune1.83—

Agentic & Tool Use Not comparable

Gemini 3 Pro: 40.6 (#23), Hy3: —

BenchmarkGemini 3 ProHy3
Terminal-Bench69.4%—
Berkeley Function Calling Leaderboard72.5%—
GDPval40.3%—
Remote Labor Index1.3%—
τ²-bench Airline80.5%—
τ²-bench Banking18%—
τ²-bench Retail75.9%—
τ²-bench Telecom91%—
DeepResearch Bench46.3%—
BALROG58.1%—
LMArena Search1207—
METR Time Horizons71%—
Vending-Bench 25,478—

Reasoning Gemini 3 Pro leads

Gemini 3 Pro: 52.5 (#31), Hy3: 26.1 (#136)

BenchmarkGemini 3 ProHy3
NYT Connections (extended)94.4%41.2%
LMArena Hard Prompts14801447
ARC-AGI-231.1%—
SimpleBench76.4%—
Kagi LLM Benchmark80.1%—
ARC-AGI-175%—
CritPt6.9%—
Chess Puzzles31%—
EnigmaEval18.2%—
Epoch Capabilities Index152.92—
ForecastBench61.2—

Math Gemini 3 Pro leads

Gemini 3 Pro: 49.9 (#59), Hy3: 40.1 (#93)

BenchmarkGemini 3 ProHy3
LMArena Math14761475
MathArena Final-Answer Competitions67%—
OTIS Mock AIME 2024-202591.4%—
ProofBench20%—
Omni-MATH55.5%—
FrontierMath (Feb 2025 set)37.6%—
FrontierMath Tier 4 (v1)18.8%—

Knowledge Gemini 3 Pro leads

Gemini 3 Pro: 64.4 (#16), Hy3: 40.8 (#114)

BenchmarkGemini 3 ProHy3
LMArena Expert14751460
GPQA Diamond92.6%—
Humanity's Last Exam37.5%—
MMLU-Pro90.3%—
Vectara Hallucination Rate13.6%—
GPQA (HELM)80.3%—

Multimodal Not comparable

Gemini 3 Pro: 57.6 (#2), Hy3: —

BenchmarkGemini 3 ProHy3
LMArena Vision1305—
GeoBench84%—
VPCT91%—
LMArena Document1434—

Multilingual Gemini 3 Pro leads

Gemini 3 Pro: 56.9 (#16), Hy3: 53.5 (#65)

BenchmarkGemini 3 ProHy3
LMArena Non-English14741426
LMArena Chinese15231493
LMArena French14921461
LMArena German15151439
LMArena Japanese15101392
LMArena Korean14481395
LMArena Russian14931432
LMArena Spanish14701456

Instruction Following Gemini 3 Pro leads

Gemini 3 Pro: 76.3 (#45), Hy3: 75.1 (#70)

BenchmarkGemini 3 ProHy3
LMArena Instruction Following14581426
IFEval87.7%—

Long Context Too close to call

Gemini 3 Pro: 44.0 (#79), Hy3: 44.1 (#75)

BenchmarkGemini 3 ProHy3
LMArena Longer Query14711442
CL-bench15.8%—

Writing & Preference Gemini 3 Pro leads

Gemini 3 Pro: 66.4 (#35), Hy3: 62.2 (#81)

BenchmarkGemini 3 ProHy3
LMArena Text14791439
LMArena Creative Writing14821402
LMArena Multi-Turn14841436
EQ-Bench Creative Writing1525—
WildBench85.9%—

Frequently asked questions

Is Gemini 3 Pro better than Hy3?

Gemini 3 Pro is the stronger model overall, scoring 54.8 to 44.2 on the Noometry Index.

Is Gemini 3 Pro or Hy3 better for coding?

Gemini 3 Pro scores higher on coding benchmarks: 51.6 versus 46.8 in the Noometry coding category.

How many benchmarks do Gemini 3 Pro and Hy3 share?

19 benchmarks have published results for both models. Gemini 3 Pro has 67 scored results on Noometry and Hy3 has 19.

Related comparisons

Go deeper