Model comparison

Gemini 1.5 Flash (May 2024) vs Hy3

Hy3 is the stronger model overall, scoring 43.6 to 32.9 on the Noometry Index.

Last verified . 15 shared benchmarks.

Gemini 1.5 Flash (May 2024) Google

32.9

Rank #240 Confirmed

Hy3 Tencent

43.6

Rank #79 Confirmed

Summary

  • They share 15 benchmarks with published results for both. Gemini 1.5 Flash (May 2024) scores higher in 0 categories and Hy3 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Hy3 leads 37.4 to 20.8.
  • Hy3 has downloadable open weights; the other is API-only.

Side by side

Gemini 1.5 Flash (May 2024) and Hy3 specifications
Gemini 1.5 Flash (May 2024)Hy3
ProviderGoogleTencent
Noometry Index32.943.6
Released2024-05-142026-07-06
WeightsProprietaryOpen
Context window—262K
Max output—128K
Input $ / M tokens—$0.13
Output $ / M tokens—$0.53
Results tracked4217

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

Category by category

Coding Hy3 leads

Gemini 1.5 Flash (May 2024): 33.9 (#233), Hy3: 46.6 (#60)

Coding benchmarks
BenchmarkGemini 1.5 Flash (May 2024)Hy3
LMArena Coding12621465
LMArena WebDev—1509
WeirdML24.9%—
BigCodeBench Instruct43.5%—
BigCodeBench Complete55.1%—
HumanEval+75.6%—
MBPP+67.5%—

Agentic & Tool Use Not comparable

Gemini 1.5 Flash (May 2024): 26.3 (#97), Hy3: —

Agentic & Tool Use benchmarks
BenchmarkGemini 1.5 Flash (May 2024)Hy3
BALROG14.6%—

Reasoning Hy3 leads

Gemini 1.5 Flash (May 2024): 20.8 (#212), Hy3: 25.0 (#134)

Reasoning benchmarks
BenchmarkGemini 1.5 Flash (May 2024)Hy3
LMArena Hard Prompts12571449
NYT Connections (extended)—41.2%
DTBench53.8%—
Epoch Capabilities Index129.37—
ForecastBench53.9—
PIQA87.5%—

Math Hy3 leads

Gemini 1.5 Flash (May 2024): 20.8 (#274), Hy3: 37.4 (#98)

Math benchmarks
BenchmarkGemini 1.5 Flash (May 2024)Hy3
LMArena Math12691475
OTIS Mock AIME 2024-202516.3%—
Omni-MATH30.4%—
MATH Level 561.9%—
FrontierMath (Feb 2025 set)0%—
GSM8K82.4%—

Knowledge Hy3 leads

Gemini 1.5 Flash (May 2024): 26.2 (#253), Hy3: 40.2 (#108)

Knowledge benchmarks
BenchmarkGemini 1.5 Flash (May 2024)Hy3
LMArena Expert12331461
GPQA Diamond47.3%—
MMLU-Pro67.8%—
GPQA (HELM)43.7%—
BoolQ85.8%—
MMLU77.9%—

Multimodal Not comparable

Gemini 1.5 Flash (May 2024): 35.3 (#76), Hy3: —

Multimodal benchmarks
BenchmarkGemini 1.5 Flash (May 2024)Hy3
LMArena Vision1141—
Video-MME70.3%—
GeoBench76%—

Multilingual Hy3 leads

Gemini 1.5 Flash (May 2024): 43.1 (#184), Hy3: 53.7 (#60)

Multilingual benchmarks
BenchmarkGemini 1.5 Flash (May 2024)Hy3
LMArena Non-English12781427
LMArena Chinese12951496
LMArena French12571461
LMArena Korean12201390
LMArena Russian12881435
LMArena Spanish12421448
LMArena German1262—
LMArena Japanese1252—

Instruction Following Hy3 leads

Gemini 1.5 Flash (May 2024): 67.0 (#199), Hy3: 75.3 (#68)

Instruction Following benchmarks
BenchmarkGemini 1.5 Flash (May 2024)Hy3
LMArena Instruction Following12581425
IFEval83.1%—

Long Context Hy3 leads

Gemini 1.5 Flash (May 2024): 39.0 (#182), Hy3: 44.1 (#70)

Long Context benchmarks
BenchmarkGemini 1.5 Flash (May 2024)Hy3
LMArena Longer Query12841443

Writing & Preference Hy3 leads

Gemini 1.5 Flash (May 2024): 48.9 (#190), Hy3: 62.5 (#75)

Writing & Preference benchmarks
BenchmarkGemini 1.5 Flash (May 2024)Hy3
LMArena Text12871442
LMArena Creative Writing12851399
LMArena Multi-Turn12531436
WildBench79.2%—

Frequently asked questions

Is Gemini 1.5 Flash (May 2024) better than Hy3?

Hy3 is the stronger model overall, scoring 43.6 to 32.9 on the Noometry Index.

Is Gemini 1.5 Flash (May 2024) or Hy3 better for coding?

Hy3 scores higher on coding benchmarks: 46.6 versus 33.9 in the Noometry coding category.

How many benchmarks do Gemini 1.5 Flash (May 2024) and Hy3 share?

15 benchmarks have published results for both models. Gemini 1.5 Flash (May 2024) has 42 scored results on Noometry and Hy3 has 17.

Related comparisons

Go deeper