LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Gemma 4 26B A4B vs Hy3 preview

Updated October 21, 2026. 36 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Gemma 4 26B A4B Replace Hy3 preview
Gemma 4 26B A4BGoogle
Coding
22.8
Overall
16.7
Output $/M
$0.255
29
Hy3 previewTencent
Coding
22.4
Overall
25.3
Output $/M
$0.60
7
vs boards won of 36 shared

Decision reading

Gemma 4 26B A4B and Hy3 preview are level for coding, 22.8 against 22.4 on the Vibe Coding Index, so price and context decide.

Pick Hy3 preview when what matters is AA Coding Index or Terminal-Bench Hard (Artificial Analysis run), where it leads. Pick Gemma 4 26B A4B when output tokens cost 2.4x less, or when what matters is LMArena WebDev or LMArena Text: coding, where it leads.

Model AGemma 4 26B A4BGoogle22.8/1001 independent benchmarkNo cost per solved taskModel BHy3 previewTencent22.4/1001 independent benchmarkNo cost per solved task
Shared results
36
Gemma 4 26B A4B only
18
Hy3 preview only
0
Like-for-like categories
7 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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
Gemma 4 26B A4B 22.8 from 1 benchmark, Hy3 preview 22.4 from 1 benchmark.
Widest category
Agentic work, 35.2 points apart on average over 2 shared benchmarks.
Widest single gap
τ²-Bench Telecom: Gemma 4 26B A4B 43.6% against Hy3 preview 92.7%, 49.1 points apart on a 0 to 100 scale.
Output price
Gemma 4 26B A4B $0.255 against Hy3 preview $0.60 per million output tokens, 2.4x apart.
Context window
Both take 262K tokens.

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
CategoryGemma 4 26B A4BBarsHy3 previewTies
Coding52
Intelligence01
Agentic work02
Reasoning32
Math20
Knowledge40
General150
All shared boards297
CodingLike-for-likeFour of these boards feed the Vibe Coding Index52
Coding benchmarks for Gemma 4 26B A4B and Hy3 preview
BenchmarkGemma 4 26B A4BHy3 previewLeader
LMArena WebDev13601357Gemma 4 26B A4B
AA Coding Index39.358.8Hy3 preview
SciCode40.0%Not measuredOnly Gemma 4 26B A4B measured
Terminal-Bench Hard (Artificial Analysis run)25.0%34.1%Hy3 preview
WeirdML35.2%Not measuredOnly Gemma 4 26B A4B measured
ALE-Bench927.2Not measuredOnly Gemma 4 26B A4B measured
LMArena Text: coding14461421Gemma 4 26B A4B
LMArena Text: software and IT14541423Gemma 4 26B A4B
LMArena WebDev: React13511349Gemma 4 26B A4B
LMArena WebDev: HTML13621356Gemma 4 26B A4B
Neither model has a result on the other 28 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Gemma 4 26B A4B and Hy3 preview
BenchmarkGemma 4 26B A4BHy3 previewLeader
AA Intelligence Index16.725.3Hy3 preview
Epoch Capabilities Index141.9Not measuredOnly Gemma 4 26B A4B measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
Agentic work benchmarks for Gemma 4 26B A4B and Hy3 preview
BenchmarkGemma 4 26B A4BHy3 previewLeader
AA Agentic Index2.924.1Hy3 preview
τ²-Bench Telecom43.6%92.7%Hy3 preview
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index32
Reasoning benchmarks for Gemma 4 26B A4B and Hy3 preview
BenchmarkGemma 4 26B A4BHy3 previewLeader
GPQA Diamond (Artificial Analysis run)79.2%86.7%Hy3 preview
Humanity's Last Exam (Artificial Analysis run)19.3%27.8%Hy3 preview
GPQA Diamond (Epoch AI run)73.2%Not measuredOnly Gemma 4 26B A4B measured
LMArena Text: hard prompts14381413Gemma 4 26B A4B
LMArena Text: expert14471422Gemma 4 26B A4B
LMArena Text: hard prompts in English14481416Gemma 4 26B A4B
LMArena Vision: diagrams1264Not measuredOnly Gemma 4 26B A4B measured
LMArena Vision: homework1293Not measuredOnly Gemma 4 26B A4B measured
Neither model has a result on the other 13 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for Gemma 4 26B A4B and Hy3 preview
BenchmarkGemma 4 26B A4BHy3 previewLeader
OTIS Mock AIME82.2%Not measuredOnly Gemma 4 26B A4B measured
LMArena Text: math14701424Gemma 4 26B A4B
LMArena Text: mathematical work14751442Gemma 4 26B A4B
Neither model has a result on the other 10 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
Knowledge benchmarks for Gemma 4 26B A4B and Hy3 preview
BenchmarkGemma 4 26B A4BHy3 previewLeader
LMArena Text: science14461416Gemma 4 26B A4B
LMArena Text: medicine and healthcare14281405Gemma 4 26B A4B
LMArena Text: legal and government14571430Gemma 4 26B A4B
LMArena Text: business and finance14291397Gemma 4 26B A4B
Neither model has a result on the other 13 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for Gemma 4 26B A4B and Hy3 preview
BenchmarkGemma 4 26B A4BHy3 previewLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index150
General benchmarks for Gemma 4 26B A4B and Hy3 preview
BenchmarkGemma 4 26B A4BHy3 previewLeader
IFBench72.4%63.1%Gemma 4 26B A4B
Long context reasoning (AA-LCR)65.7%64.7%Gemma 4 26B A4B
DTBench74.9%Not measuredOnly Gemma 4 26B A4B measured
LMCA29.7%Not measuredOnly Gemma 4 26B A4B measured
LMArena Text14341401Gemma 4 26B A4B
LMArena Text: instruction following14201383Gemma 4 26B A4B
LMArena Text: creative writing14001339Gemma 4 26B A4B
LMArena Vision1260Not measuredOnly Gemma 4 26B A4B measured
LMArena Text: English14441409Gemma 4 26B A4B
LMArena Text: non-English14211390Gemma 4 26B A4B
LMArena Text: Chinese14951435Gemma 4 26B A4B
LMArena Text: French14601425Gemma 4 26B A4B
LMArena Text: Spanish14151399Gemma 4 26B A4B
LMArena Text: Russian14341399Gemma 4 26B A4B
LMArena Text: multi-turn14411411Gemma 4 26B A4B
LMArena Text: longer queries14271402Gemma 4 26B A4B
LMArena Text: writing and language14051370Gemma 4 26B A4B
LMArena Text: entertainment and media14031352Gemma 4 26B A4B
LMArena Vision: English1256Not measuredOnly Gemma 4 26B A4B measured
LMArena Vision: Chinese1312Not measuredOnly Gemma 4 26B A4B measured
LMArena Vision: reading text1268Not measuredOnly Gemma 4 26B A4B measured
LMArena Vision: humor1272Not measuredOnly Gemma 4 26B A4B measured
LMArena Vision: captioning1297Not measuredOnly Gemma 4 26B A4B measured
LMArena Vision: recognizing things1191Not measuredOnly Gemma 4 26B A4B measured
LMArena Vision: creative writing1256Not measuredOnly Gemma 4 26B A4B measured
Neither model has a result on the other 21 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemma 4 26B A4B and Hy3 preview
BenchmarkGemma 4 26B A4BHy3 previewLeader
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

Gemma 4 26B A4B$0.0002Fits in one request
Hy3 preview$0.0005Fits in one request

Gemma 4 26B A4B costs less

Repository review

50K input + 3K output tokens

Gemma 4 26B A4B$0.0046Fits in one request
Hy3 preview$0.011Fits in one request

Gemma 4 26B A4B costs less

Agent loop

200K input + 10K output tokens

Gemma 4 26B A4B$0.018Fits in one request
Hy3 preview$0.042Fits in one request

Gemma 4 26B A4B 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 Gemma 4 26B A4B and Hy3 preview
SpecificationGoogle Gemma 4 26B A4BTencent Hy3 preview
MakerGoogleTencent
WeightsOpen weightsOpen weights
ReleasedApril 3, 2026April 22, 2026
Context window262K262K
Input $/Mtok$0.0765$0.18
Output $/Mtok$0.255$0.60
Coding index22.822.4
Independent measurements behind it11
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 4 26B A4B better than Hy3 preview for coding?

Gemma 4 26B A4B and Hy3 preview are level for coding, 22.8 against 22.4 on the Vibe Coding Index, so price and context decide. Pick Hy3 preview when what matters is AA Coding Index or Terminal-Bench Hard (Artificial Analysis run), where it leads. Pick Gemma 4 26B A4B when output tokens cost 2.4x less, or when what matters is LMArena WebDev or LMArena Text: coding, where it leads.

Which is cheaper, Gemma 4 26B A4B or Hy3 preview?

Gemma 4 26B A4B costs $0.0765 per million input tokens and $0.255 per million output tokens; Hy3 preview costs $0.18 and $0.60. Cost per solved task is known for neither of them.

Which has the bigger context window, Gemma 4 26B A4B or Hy3 preview?

Neither: both take 262K tokens.

How many benchmarks is the Gemma 4 26B A4B vs Hy3 preview comparison based on?

36 benchmarks have a result for both models as of October 21, 2026. Gemma 4 26B A4B's coding index rests on 1 independent benchmark and Hy3 preview's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next