Enter opens the highlighted result. Esc closes.

gpt-oss-20b vs Hy3

gpt-oss-20b costs 2.2x less per output token than Hy3 ($0.15 vs $0.33 per million). Updated October 21, 2026; 34 benchmarks have a result for both.

Replace gpt-oss-20b Replace Hy3
gpt-oss-20bOpenAI
Coding
No data
Overall
38.5
Output $/M
$0.15
0
Hy3Tencent
Coding
No data
Overall
No data
Output $/M
$0.33
34
vs boards won of 34 shared

gpt-oss-20b or Hy3: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick gpt-oss-20b for output tokens 2.2x cheaper ($0.15 vs $0.33 per million) and work measured by SciCode or ALE-Bench, where it leads.

Model Agpt-oss-20bOpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BHy3TencentNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
34
gpt-oss-20b only
28
Hy3 only
10
Like-for-like categories
6 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
gpt-oss-20b not benchmarked, Hy3 not benchmarked.
Widest category
Web design, 38.0 points apart on average over 2 shared benchmarks.
Widest single gap
Design Arena: websites: gpt-oss-20b 852 against Hy3 1230, 47.3 points apart on a 0 to 100 scale.
Output price
gpt-oss-20b $0.15 against Hy3 $0.33 per million output tokens, 2.2x apart.
Context window
gpt-oss-20b takes 131K tokens, Hy3 262K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
Categorygpt-oss-20bBarsHy3Ties
Coding04
Reasoning05
Math02
Knowledge04
Web design02
General017
All shared boards034
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
Coding benchmarks for gpt-oss-20b and Hy3
Benchmarkgpt-oss-20bHy3Leader
LMArena WebDevNot measured1507Only Hy3 measured
LiveCodeBench (Vals AI)80.4%Not measuredOnly gpt-oss-20b measured
LiveCodeBench (Artificial Analysis run)77.7%Not measuredOnly gpt-oss-20b measured
SciCode38.9%48.6%Hy3
Terminal-Bench Hard (Artificial Analysis run)10.6%Not measuredOnly gpt-oss-20b measured
Terminal-Bench3.4%Not measuredOnly gpt-oss-20b measured
WeirdML40.9%Not measuredOnly gpt-oss-20b measured
ALE-Bench566.0838.6Hy3
LMArena Text: coding13071466Hy3
LMArena Text: software and IT13111463Hy3
LMArena WebDev: ReactNot measured1511Only Hy3 measured
LMArena WebDev: HTMLNot measured1487Only Hy3 measured
Neither model has a result on the other 27 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Intelligence benchmarks for gpt-oss-20b and Hy3
Benchmarkgpt-oss-20bHy3Leader
AA Intelligence Index10.0Not measuredOnly gpt-oss-20b measured
Epoch Capabilities Index137.7Not measuredOnly gpt-oss-20b measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Agentic work benchmarks for gpt-oss-20b and Hy3
Benchmarkgpt-oss-20bHy3Leader
τ²-Bench Telecom60.2%Not measuredOnly gpt-oss-20b measured
BrowseComp-Plus50.6%Not measuredOnly gpt-oss-20b measured
Neither model has a result on the other 39 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for gpt-oss-20b and Hy3
Benchmarkgpt-oss-20bHy3Leader
GPQA Diamond68.9%Not measuredOnly gpt-oss-20b measured
GPQA Diamond (Artificial Analysis run)68.8%89.7%Hy3
Humanity's Last Exam (Artificial Analysis run)11.0%33.5%Hy3
GPQA Diamond (Epoch AI run)60.8%Not measuredOnly gpt-oss-20b measured
LMArena Text: hard prompts12741447Hy3
LMArena Text: expert12581461Hy3
LMArena Text: hard prompts in English12921455Hy3
Kagi LLM Benchmark53.2%Not measuredOnly gpt-oss-20b measured
Neither model has a result on the other 14 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for gpt-oss-20b and Hy3
Benchmarkgpt-oss-20bHy3Leader
AIME86.0%Not measuredOnly gpt-oss-20b measured
MATH 500 (Vals AI)94.2%Not measuredOnly gpt-oss-20b measured
MGSM (Vals AI)89.0%Not measuredOnly gpt-oss-20b measured
AA Math Index89.3Not measuredOnly gpt-oss-20b measured
AIME 2025 (Artificial Analysis run)89.3%Not measuredOnly gpt-oss-20b measured
OTIS Mock AIME65.3%Not measuredOnly gpt-oss-20b measured
LMArena Text: math13171473Hy3
LMArena Text: mathematical work13051482Hy3
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for gpt-oss-20b and Hy3
Benchmarkgpt-oss-20bHy3Leader
MMLU Pro71.6%Not measuredOnly gpt-oss-20b measured
LegalBench (Vals AI)70.8%Not measuredOnly gpt-oss-20b measured
CaseLaw (Vals AI)43.8%Not measuredOnly gpt-oss-20b measured
CorpFin (Vals AI)53.1%Not measuredOnly gpt-oss-20b measured
TaxEval (Vals AI)63.7%Not measuredOnly gpt-oss-20b measured
MedQA (Vals AI)82.9%Not measuredOnly gpt-oss-20b measured
MMLU Pro (Artificial Analysis run)74.8%Not measuredOnly gpt-oss-20b measured
LMArena Text: science12961457Hy3
LMArena Text: medicine and healthcare13101452Hy3
LMArena Text: legal and government12801422Hy3
LMArena Text: business and finance12841424Hy3
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index02
Web design benchmarks for gpt-oss-20b and Hy3
Benchmarkgpt-oss-20bHy3Leader
Design Arena: websites8521230Hy3
Design Arena: UI componentsNot measured1207Only Hy3 measured
Design Arena: game devNot measured1208Only Hy3 measured
Design Arena: data viz9331163Hy3
Design Arena: 3DNot measured1233Only Hy3 measured
Design Arena: all code categoriesNot measured1227Only Hy3 measured
Design Arena: SVGNot measured1200Only Hy3 measured
Design Arena: ASCII artNot measured1152Only Hy3 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index017
General benchmarks for gpt-oss-20b and Hy3
Benchmarkgpt-oss-20bHy3Leader
IFBench65.1%Not measuredOnly gpt-oss-20b measured
Long context reasoning (AA-LCR)34.7%79.0%Hy3
DTBench68.0%Not measuredOnly gpt-oss-20b measured
LMCA14.5%Not measuredOnly gpt-oss-20b measured
LMArena Text12881438Hy3
LMArena Text: instruction following12361426Hy3
LMArena Text: creative writing12011403Hy3
LMArena Text: English13031448Hy3
LMArena Text: non-English12691426Hy3
LMArena Text: Chinese13151485Hy3
LMArena Text: German12551449Hy3
LMArena Text: Japanese12441397Hy3
LMArena Text: Korean12361396Hy3
LMArena Text: FrenchNot measured1456Only Hy3 measured
LMArena Text: Spanish12671457Hy3
LMArena Text: Russian12781432Hy3
LMArena Text: Polish12521447Hy3
LMArena Text: multi-turn12681436Hy3
LMArena Text: longer queries12501442Hy3
LMArena Text: writing and language12381414Hy3
LMArena Text: entertainment and media12161400Hy3
Neither model has a result on the other 25 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for gpt-oss-20b and Hy3
Benchmarkgpt-oss-20bHy3Leader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

gpt-oss-20b$0.0001Fits in one request
Hy3$0.0002Fits in one request

gpt-oss-20b costs less

Repository review

50K input + 3K output tokens

gpt-oss-20b$0.0019Fits in one request
Hy3$0.0051Fits in one request

gpt-oss-20b costs less

Agent loop

200K input + 10K output tokens

gpt-oss-20b$0.0075Exceeds the context window
Hy3$0.020Fits in one request

gpt-oss-20b costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of gpt-oss-20b and Hy3
SpecificationOpenAI gpt-oss-20bTencent Hy3
MakerOpenAITencent
WeightsOpen weightsOpen weights
ReleasedAugust 5, 2025July 6, 2026
Context window131K262K
Input $/Mtok$0.03$0.0825
Output $/Mtok$0.15$0.33
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it01
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is gpt-oss-20b better than Hy3 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick gpt-oss-20b for output tokens 2.2x cheaper ($0.15 vs $0.33 per million) and work measured by SciCode or ALE-Bench, where it leads.

Which is cheaper, gpt-oss-20b or Hy3?

gpt-oss-20b costs $0.03 per million input tokens and $0.15 per million output tokens; Hy3 costs $0.0825 and $0.33. Cost per solved task is known for neither of them.

Which has the bigger context window, gpt-oss-20b or Hy3?

Hy3, with 262K tokens against 131K.

How many benchmarks is the gpt-oss-20b vs Hy3 comparison based on?

34 benchmarks have a result for both models as of October 21, 2026. gpt-oss-20b's coding index rests on 0 independent benchmarks and Hy3's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next