Noometry

Model comparison

Hy3 vs o4-mini

Hy3 is the stronger model overall, scoring 44.2 to 41.6 on the Noometry Index.

Last verified . 17 shared benchmarks.

Hy3 Tencent

44.2

Rank #79 Confirmed

o4-mini OpenAI

41.6

Rank #132 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Hy3 scores higher in 4 categories and o4-mini in 4 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Hy3 leads 62.2 to 54.0.
  • Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $1.10 / $4.40 for o4-mini.
  • Hy3 accepts more context: 262K tokens versus 200K.
  • Hy3 has downloadable open weights; the other is API-only.

Side by side

Hy3o4-mini
ProviderTencentOpenAI
Noometry Index44.241.6
Released2026-07-062025-04-16
WeightsOpenProprietary
Context window262K200K
Max output128K100K
Input $ / M tokens$0.0825$1.10
Output $ / M tokens$0.33$4.40
Results tracked1960

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

Category by category

Coding Hy3 leads

Hy3: 46.8 (#63), o4-mini: 40.9 (#127)

BenchmarkHy3o4-mini
LMArena Coding14641368
SWE-bench Verified (bash only)—45%
Aider Polyglot—72%
LMArena WebDev1508—
GSO—3.6%
WeirdML—52.6%
CadEval—62%
ALE-Bench—826.17
AlgoTune—1.72

Agentic & Tool Use Not comparable

Hy3: —, o4-mini: 32.6 (#61)

BenchmarkHy3o4-mini
Berkeley Function Calling Leaderboard—53.2%
GDPval—25.3%
METR Time Horizons—63.9%

Reasoning Hy3 leads

Hy3: 26.1 (#136), o4-mini: 24.6 (#162)

BenchmarkHy3o4-mini
LMArena Hard Prompts14471351
ARC-AGI-2—6.1%
SimpleBench—38.7%
Kagi LLM Benchmark—67.6%
NYT Connections (extended)41.2%—
ARC-AGI-1—58.7%
CritPt—0.6%
Chess Puzzles—26%
EnigmaEval—9.2%
Mystery Game Puzzles—5%
DTBench—77.6%
LMCA—26.5%
Epoch Capabilities Index—145.64
ForecastBench—61.8

Math Too close to call

Hy3: 40.1 (#93), o4-mini: 40.8 (#89)

BenchmarkHy3o4-mini
LMArena Math14751389
FrontierMath (Tiers 1-3)—36.1%
FrontierMath Tier 4—4.9%
OTIS Mock AIME 2024-2025—81.7%
Omni-MATH—72%
MATH Level 5—97.8%
FrontierMath (Feb 2025 set)—24.8%
FrontierMath Tier 4 (v1)—6.3%

Knowledge o4-mini leads

Hy3: 40.8 (#114), o4-mini: 43.6 (#91)

BenchmarkHy3o4-mini
LMArena Expert14601343
GPQA Diamond—79.6%
Humanity's Last Exam—18.1%
SimpleQA Verified—19.6%
MMLU-Pro—82%
Confabulations—15.8%
Vectara Hallucination Rate—18.6%
GPQA (HELM)—73.5%

Multimodal Not comparable

Hy3: —, o4-mini: 40.2 (#49)

BenchmarkHy3o4-mini
LMArena Vision—1194
GeoBench—64%
VPCT—57.5%

Multilingual Hy3 leads

Hy3: 53.5 (#65), o4-mini: 47.0 (#154)

BenchmarkHy3o4-mini
LMArena Non-English14261337
LMArena Chinese14931354
LMArena French14611364
LMArena German14391336
LMArena Japanese13921308
LMArena Korean13951312
LMArena Russian14321334
LMArena Spanish14561347

Instruction Following Too close to call

Hy3: 75.1 (#70), o4-mini: 75.2 (#68)

BenchmarkHy3o4-mini
LMArena Instruction Following14261321
IFEval—92.8%

Long Context o4-mini leads

Hy3: 44.1 (#75), o4-mini: 45.5 (#33)

BenchmarkHy3o4-mini
LMArena Longer Query14421315
Fiction.LiveBench—77.8%

Writing & Preference Hy3 leads

Hy3: 62.2 (#81), o4-mini: 54.0 (#152)

BenchmarkHy3o4-mini
LMArena Text14391353
LMArena Creative Writing14021294
LMArena Multi-Turn14361350
Short-Story Creative Writing—75%
WildBench—85.4%

Frequently asked questions

Is Hy3 better than o4-mini?

Hy3 is the stronger model overall, scoring 44.2 to 41.6 on the Noometry Index.

Which is cheaper, Hy3 or o4-mini?

Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; o4-mini lists at $1.10 and $4.40.

Is Hy3 or o4-mini better for coding?

Hy3 scores higher on coding benchmarks: 46.8 versus 40.9 in the Noometry coding category.

Which has the bigger context window?

Hy3 does, with 262K tokens against 200K.

How many benchmarks do Hy3 and o4-mini share?

17 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and o4-mini has 60.

Related comparisons

Go deeper