Noometry

Model comparison

GPT-4.1 nano vs Hy3

Hy3 is the stronger model overall, scoring 44.2 to 27.9 on the Noometry Index.

Last verified . 14 shared benchmarks.

GPT-4.1 nano OpenAI

27.9

Rank #327 Confirmed

Hy3 Tencent

44.2

Rank #79 Confirmed

Summary

  • They share 14 benchmarks with published results for both. GPT-4.1 nano scores higher in 0 categories and Hy3 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Hy3 leads 46.8 to 24.1.
  • Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $0.10 / $0.40 for GPT-4.1 nano.
  • GPT-4.1 nano accepts more context: 1.05M tokens versus 262K.
  • Hy3 has downloadable open weights; the other is API-only.

Side by side

GPT-4.1 nanoHy3
ProviderOpenAITencent
Noometry Index27.944.2
Released2025-04-142026-07-06
WeightsProprietaryOpen
Context window1.05M262K
Max output33K128K
Input $ / M tokens$0.10$0.0825
Output $ / M tokens$0.40$0.33
Results tracked3819

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

Category by category

Coding Hy3 leads

GPT-4.1 nano: 24.1 (#330), Hy3: 46.8 (#63)

BenchmarkGPT-4.1 nanoHy3
LMArena Coding13061464
Aider Polyglot8.9%—
LMArena WebDev—1508
SciCode25.9%—
WeirdML19%—

Agentic & Tool Use Not comparable

GPT-4.1 nano: 26.5 (#104), Hy3: —

BenchmarkGPT-4.1 nanoHy3
Berkeley Function Calling Leaderboard33%—

Reasoning Hy3 leads

GPT-4.1 nano: 8.5 (#349), Hy3: 26.1 (#136)

BenchmarkGPT-4.1 nanoHy3
LMArena Hard Prompts12861447
ARC-AGI-20%—
Kagi LLM Benchmark33.3%—
NYT Connections (extended)—41.2%
ARC-AGI-10%—
CritPt0%—
DTBench52.5%—
LMCA5.5%—
Epoch Capabilities Index129.62—

Math Hy3 leads

GPT-4.1 nano: 26.9 (#252), Hy3: 40.1 (#93)

BenchmarkGPT-4.1 nanoHy3
LMArena Math12741475
OTIS Mock AIME 2024-202528.9%—
Omni-MATH36.7%—
MATH Level 570%—
FrontierMath (Feb 2025 set)1%—

Knowledge Hy3 leads

GPT-4.1 nano: 21.8 (#273), Hy3: 40.8 (#114)

BenchmarkGPT-4.1 nanoHy3
LMArena Expert12721460
GPQA Diamond48.9%—
SimpleQA Verified6%—
MMLU-Pro55%—
GPQA (HELM)50.7%—

Multimodal Not comparable

GPT-4.1 nano: 29.2 (#113), Hy3: —

BenchmarkGPT-4.1 nanoHy3
LMArena Vision1063—

Multilingual Hy3 leads

GPT-4.1 nano: 41.6 (#205), Hy3: 53.5 (#65)

BenchmarkGPT-4.1 nanoHy3
LMArena Non-English12601426
LMArena Chinese12701493
LMArena German12881439
LMArena Japanese11981392
LMArena Russian12611432
LMArena French—1461
LMArena Korean—1395
LMArena Spanish—1456

Instruction Following Hy3 leads

GPT-4.1 nano: 67.8 (#193), Hy3: 75.1 (#70)

BenchmarkGPT-4.1 nanoHy3
LMArena Instruction Following12671426
IFEval84.3%—

Long Context Hy3 leads

GPT-4.1 nano: 23.7 (#296), Hy3: 44.1 (#75)

BenchmarkGPT-4.1 nanoHy3
LMArena Longer Query12831442
Fiction.LiveBench25%—

Writing & Preference Hy3 leads

GPT-4.1 nano: 40.5 (#243), Hy3: 62.2 (#81)

BenchmarkGPT-4.1 nanoHy3
LMArena Text12851439
LMArena Creative Writing12601402
LMArena Multi-Turn12771436
EQ-Bench Creative Writing946—
WildBench81.2%—

Frequently asked questions

Is GPT-4.1 nano better than Hy3?

Hy3 is the stronger model overall, scoring 44.2 to 27.9 on the Noometry Index.

Which is cheaper, GPT-4.1 nano or Hy3?

Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; GPT-4.1 nano lists at $0.10 and $0.40.

Is GPT-4.1 nano or Hy3 better for coding?

Hy3 scores higher on coding benchmarks: 46.8 versus 24.1 in the Noometry coding category.

Which has the bigger context window?

GPT-4.1 nano does, with 1.05M tokens against 262K.

How many benchmarks do GPT-4.1 nano and Hy3 share?

14 benchmarks have published results for both models. GPT-4.1 nano has 38 scored results on Noometry and Hy3 has 19.

Related comparisons

Go deeper