Noometry

Model comparison

gpt-oss-120b vs Hy3

Hy3 is the stronger model overall, scoring 44.2 to 36.3 on the Noometry Index. gpt-oss-120b costs 2.1× less per token, which makes it the better buy when Hy3's lead doesn't matter for your workload.

Last verified . 17 shared benchmarks.

gpt-oss-120b OpenAI

36.3

Rank #217 Confirmed

Hy3 Tencent

44.2

Rank #79 Confirmed

Summary

  • They share 17 benchmarks with published results for both. gpt-oss-120b scores higher in 2 categories and Hy3 in 6 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Hy3 leads 62.2 to 46.5.
  • gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.0825 / $0.33 for Hy3.
  • Hy3 accepts more context: 262K tokens versus 131K.

Side by side

gpt-oss-120bHy3
ProviderOpenAITencent
Noometry Index36.344.2
Released2025-08-052026-07-06
WeightsOpenOpen
Context window131K262K
Max output41K128K
Input $ / M tokens$0.037$0.0825
Output $ / M tokens$0.17$0.33
Results tracked4819

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

Category by category

Coding Hy3 leads

gpt-oss-120b: 33.5 (#256), Hy3: 46.8 (#63)

Benchmarkgpt-oss-120bHy3
LMArena Coding13801464
SWE-bench Verified (bash only)26%—
Aider Polyglot41.8%—
LMArena WebDev—1508
SciCode36%—
WeirdML48.2%—
ALE-Bench575.62—
AlgoTune1.41—

Agentic & Tool Use Not comparable

gpt-oss-120b: 12.2 (#153), Hy3: —

Benchmarkgpt-oss-120bHy3
Terminal-Bench18.7%—
APEX-Agents4.4%—
METR Time Horizons56.6%—
Vending-Bench 2-21.53—

Reasoning Hy3 leads

gpt-oss-120b: 20.0 (#245), Hy3: 26.1 (#136)

Benchmarkgpt-oss-120bHy3
LMArena Hard Prompts13641447
SimpleBench22.1%—
Kagi LLM Benchmark58.6%—
NYT Connections (extended)—41.2%
CritPt1.1%—
Chess Puzzles20%—
Mystery Game Puzzles2%—
DTBench76.3%—
LMCA22.1%—
Surface Evolver Bench25%—
Epoch Capabilities Index139.93—

Math gpt-oss-120b leads

gpt-oss-120b: 52.5 (#50), Hy3: 40.1 (#93)

Benchmarkgpt-oss-120bHy3
LMArena Math13891475
OTIS Mock AIME 2024-202588.9%—
Omni-MATH68.8%—

Knowledge gpt-oss-120b leads

gpt-oss-120b: 42.4 (#96), Hy3: 40.8 (#114)

Benchmarkgpt-oss-120bHy3
LMArena Expert13561460
GPQA Diamond75.8%—
MMLU-Pro79.5%—
Confabulations15.7%—
Vectara Hallucination Rate14.2%—
GPQA (HELM)68.4%—

Multilingual Hy3 leads

gpt-oss-120b: 48.0 (#147), Hy3: 53.5 (#65)

Benchmarkgpt-oss-120bHy3
LMArena Non-English13511426
LMArena Chinese13851493
LMArena French13691461
LMArena German13531439
LMArena Japanese13311392
LMArena Korean12821395
LMArena Russian13431432
LMArena Spanish13891456

Instruction Following Hy3 leads

gpt-oss-120b: 69.3 (#173), Hy3: 75.1 (#70)

Benchmarkgpt-oss-120bHy3
LMArena Instruction Following13181426
IFEval83.6%—

Long Context Hy3 leads

gpt-oss-120b: 31.4 (#278), Hy3: 44.1 (#75)

Benchmarkgpt-oss-120bHy3
LMArena Longer Query13191442
Fiction.LiveBench44.4%—

Writing & Preference Hy3 leads

gpt-oss-120b: 46.5 (#217), Hy3: 62.2 (#81)

Benchmarkgpt-oss-120bHy3
LMArena Text13651439
LMArena Creative Writing12751402
LMArena Multi-Turn13401436
Short-Story Creative Writing77.1%—
EQ-Bench Creative Writing961—
WildBench84.5%—

Frequently asked questions

Is gpt-oss-120b better than Hy3?

Hy3 is the stronger model overall, scoring 44.2 to 36.3 on the Noometry Index. gpt-oss-120b costs 2.1× less per token, which makes it the better buy when Hy3's lead doesn't matter for your workload.

Which is cheaper, gpt-oss-120b or Hy3?

gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Hy3 lists at $0.0825 and $0.33.

Is gpt-oss-120b or Hy3 better for coding?

Hy3 scores higher on coding benchmarks: 46.8 versus 33.5 in the Noometry coding category.

Which has the bigger context window?

Hy3 does, with 262K tokens against 131K.

How many benchmarks do gpt-oss-120b and Hy3 share?

17 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Hy3 has 19.

Related comparisons

Go deeper