LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Gemma 4 31B 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 31B Replace Hy3 preview
Gemma 4 31BGoogle
Coding
38.3
Overall
14.7
Output $/M
$0.40
30
Hy3 previewTencent
Coding
22.4
Overall
25.3
Output $/M
$0.60
6
vs boards won of 36 shared

Decision reading

Pick Gemma 4 31B for coding: it scores 38.3 on the Vibe Coding Index against 22.4 for Hy3 preview.

Pick Hy3 preview when what matters is AA Coding Index or AA Intelligence Index, where it leads.

Model AGemma 4 31BGoogle38.3/1002 independent benchmarksNo cost per solved taskModel BHy3 previewTencent22.4/1001 independent benchmarkNo cost per solved task
Shared results
36
Gemma 4 31B only
32
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 31B 38.3 from 2 benchmarks, Hy3 preview 22.4 from 1 benchmark.
Widest category
Agentic work, 23.5 points apart on average over 2 shared benchmarks.
Widest single gap
τ²-Bench Telecom: Gemma 4 31B 65.5% against Hy3 preview 92.7%, 27.2 points apart on a 0 to 100 scale.
Output price
Gemma 4 31B $0.40 against Hy3 preview $0.60 per million output tokens, 1.5x 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 31BBarsHy3 previewTies
Coding61
Intelligence01
Agentic work02
Reasoning32
Math20
Knowledge40
General150
All shared boards306
CodingLike-for-likeFour of these boards feed the Vibe Coding Index61
Coding benchmarks for Gemma 4 31B and Hy3 preview
BenchmarkGemma 4 31BHy3 previewLeader
LiveBench coding49.0%Not measuredOnly Gemma 4 31B measured
LMArena WebDev13671357Gemma 4 31B
AA Coding Index43.458.8Hy3 preview
SciCode45.5%Not measuredOnly Gemma 4 31B measured
Terminal-Bench Hard (Artificial Analysis run)36.4%34.1%Gemma 4 31B
WeirdML52.3%Not measuredOnly Gemma 4 31B measured
ALE-Bench925.5Not measuredOnly Gemma 4 31B measured
LMArena Text: coding14591421Gemma 4 31B
LMArena Text: software and IT14631423Gemma 4 31B
LMArena WebDev: React13591349Gemma 4 31B
LMArena WebDev: HTML13801356Gemma 4 31B
Neither model has a result on the other 27 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Gemma 4 31B and Hy3 preview
BenchmarkGemma 4 31BHy3 previewLeader
AA Intelligence Index14.725.3Hy3 preview
Epoch Capabilities Index143.0Not measuredOnly Gemma 4 31B measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
Agentic work benchmarks for Gemma 4 31B and Hy3 preview
BenchmarkGemma 4 31BHy3 previewLeader
AA Agentic Index4.224.1Hy3 preview
LiveBench research44.4%Not measuredOnly Gemma 4 31B measured
LiveBench browser4.0%Not measuredOnly Gemma 4 31B measured
LiveBench long agentic13.3%Not measuredOnly Gemma 4 31B measured
τ²-Bench Telecom65.5%92.7%Hy3 preview
Neither model has a result on the other 34 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index32
Reasoning benchmarks for Gemma 4 31B and Hy3 preview
BenchmarkGemma 4 31BHy3 previewLeader
LiveBench reasoning68.3%Not measuredOnly Gemma 4 31B measured
GPQA Diamond (Artificial Analysis run)85.7%86.7%Hy3 preview
Humanity's Last Exam (Artificial Analysis run)23.6%27.8%Hy3 preview
GPQA Diamond (Epoch AI run)75.8%Not measuredOnly Gemma 4 31B measured
LMArena Text: hard prompts14481413Gemma 4 31B
LMArena Text: expert14641422Gemma 4 31B
LMArena Text: hard prompts in English14561416Gemma 4 31B
LMArena Vision: diagrams1283Not measuredOnly Gemma 4 31B measured
LMArena Vision: homework1310Not measuredOnly Gemma 4 31B measured
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for Gemma 4 31B and Hy3 preview
BenchmarkGemma 4 31BHy3 previewLeader
OTIS Mock AIME73.3%Not measuredOnly Gemma 4 31B measured
LMArena Text: math14631424Gemma 4 31B
LMArena Text: mathematical work14651442Gemma 4 31B
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 31B and Hy3 preview
BenchmarkGemma 4 31BHy3 previewLeader
CaseLaw (Vals AI)52.6%Not measuredOnly Gemma 4 31B measured
MortgageTax (Vals AI)61.4%Not measuredOnly Gemma 4 31B measured
SimpleQA Verified10.4%Not measuredOnly Gemma 4 31B measured
LMArena Text: science14571416Gemma 4 31B
LMArena Text: medicine and healthcare14511405Gemma 4 31B
LMArena Text: legal and government14381430Gemma 4 31B
LMArena Text: business and finance14301397Gemma 4 31B
Neither model has a result on the other 10 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
Web design benchmarks for Gemma 4 31B and Hy3 preview
BenchmarkGemma 4 31BHy3 previewLeader
LiveBench design58.4%Not measuredOnly Gemma 4 31B measured
Neither model has a result on the other 8 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index150
General benchmarks for Gemma 4 31B and Hy3 preview
BenchmarkGemma 4 31BHy3 previewLeader
LiveBench data analysis53.3%Not measuredOnly Gemma 4 31B measured
SAGE (Vals AI)55.0%Not measuredOnly Gemma 4 31B measured
IFBench75.6%63.1%Gemma 4 31B
Long context reasoning (AA-LCR)69.7%64.7%Gemma 4 31B
DTBench82.7%Not measuredOnly Gemma 4 31B measured
LMCA39.3%Not measuredOnly Gemma 4 31B measured
Surface Evolver Bench30.6%Not measuredOnly Gemma 4 31B measured
LMArena Text14431401Gemma 4 31B
LMArena Text: instruction following14331383Gemma 4 31B
LMArena Text: creative writing14171339Gemma 4 31B
LMArena Vision1276Not measuredOnly Gemma 4 31B measured
LMArena Text: English14511409Gemma 4 31B
LMArena Text: non-English14301390Gemma 4 31B
LMArena Text: Chinese14751435Gemma 4 31B
LMArena Text: French14361425Gemma 4 31B
LMArena Text: Spanish14421399Gemma 4 31B
LMArena Text: Russian14601399Gemma 4 31B
LMArena Text: Polish1433Not measuredOnly Gemma 4 31B measured
LMArena Text: multi-turn14521411Gemma 4 31B
LMArena Text: longer queries14461402Gemma 4 31B
LMArena Text: writing and language14321370Gemma 4 31B
LMArena Text: entertainment and media14051352Gemma 4 31B
LMArena Vision: English1271Not measuredOnly Gemma 4 31B measured
LMArena Vision: Chinese1326Not measuredOnly Gemma 4 31B measured
LMArena Vision: reading text1282Not measuredOnly Gemma 4 31B measured
LMArena Vision: humor1280Not measuredOnly Gemma 4 31B measured
LMArena Vision: captioning1218Not measuredOnly Gemma 4 31B measured
LMArena Vision: recognizing things1226Not measuredOnly Gemma 4 31B measured
LMArena Vision: creative writing1285Not measuredOnly Gemma 4 31B measured
LMArena Document1425Not measuredOnly Gemma 4 31B measured
Neither model has a result on the other 16 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemma 4 31B and Hy3 preview
BenchmarkGemma 4 31BHy3 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 31B$0.0004Fits in one request
Hy3 preview$0.0005Fits in one request

Gemma 4 31B costs less

Repository review

50K input + 3K output tokens

Gemma 4 31B$0.011Fits in one request
Hy3 preview$0.011Fits in one request

Hy3 preview costs less

Agent loop

200K input + 10K output tokens

Gemma 4 31B$0.044Fits in one request
Hy3 preview$0.042Fits in one request

Hy3 preview 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 31B and Hy3 preview
SpecificationGoogle Gemma 4 31BTencent Hy3 preview
MakerGoogleTencent
WeightsOpen weightsOpen weights
ReleasedApril 2, 2026April 22, 2026
Context window262K262K
Input $/Mtok$0.20$0.18
Output $/Mtok$0.40$0.60
Coding index38.322.4
Independent measurements behind it21
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 4 31B better than Hy3 preview for coding?

Pick Gemma 4 31B for coding: it scores 38.3 on the Vibe Coding Index against 22.4 for Hy3 preview. Pick Hy3 preview when what matters is AA Coding Index or AA Intelligence Index, where it leads.

Which is cheaper, Gemma 4 31B or Hy3 preview?

Gemma 4 31B costs $0.20 per million input tokens and $0.40 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 31B or Hy3 preview?

Neither: both take 262K tokens.

How many benchmarks is the Gemma 4 31B vs Hy3 preview comparison based on?

36 benchmarks have a result for both models as of October 21, 2026. Gemma 4 31B's coding index rests on 2 independent benchmarks and Hy3 preview's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next