Skip to main content

Model comparison

Gemma 4 12B vs Hy3 Preview

Data verified

Head-to-head evidence from 11 shared benchmark results across 3 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

47.29/100
No comparison
N/A
1 category wins0 category wins

Public leaderboard positions: Gemma 4 12B #137 (Estimated); Hy3 Preview unranked (Not scored). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Gemma 4 12B and Hy3 Preview share 11 comparable benchmark results. 1 of 8 categories are comparable. 12 results are unique to Gemma 4 12B; 11 to Hy3 Preview.

Updated July 23, 2026
Shared results
11
Gemma 4 12B only
12
Hy3 Preview only
11
Comparable categories
1 / 8

Treat this as a split decision. Gemma 4 12B makes more sense if knowledge is the priority; Hy3 Preview is the better fit if its strengths line up with your actual workload.

Confidence note. This is a partial-evidence comparison with 11 shared benchmark results across 3 evidence categories; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Gemma 4 12B and Hy3 Preview finish on the same BenchAlign overall score, so this is less about a single winner and more about where the edge shows up. The BenchAlign headline says tie; the benchmark table is where the real choice happens.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for Gemma 4 12B and Hy3 Preview
CategoryGemma 4 12BΔHy3 Preview
KnowledgeGemma 4 12B77.5Margin 43.7Hy3 Preview33.8
AgenticGemma 4 12BNot measuredMarginNo overlapHy3 Preview54.4
CodingGemma 4 12BNot measuredMarginNo overlapHy3 Preview57.8
ReasoningGemma 4 12B43.4MarginNo overlapHy3 PreviewNot measured
MathGemma 4 12B77.5MarginNo overlapHy3 PreviewNot measured
MultimodalGemma 4 12B69.1MarginNo overlapHy3 PreviewNot measured
Inst. FollowingGemma 4 12BNot measuredMarginNo overlapHy3 Preview63.1

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · Gemma 4 12BB · Hy3 Preview
  1. GPQA

    Knowledge
    Source ↗
    A 78.8%B 87.2%
    Winner: Hy3 PreviewΔ 8.4
    GPQA: Gemma 4 12B scored 78.8%; Hy3 Preview scored 87.2%. Hy3 Preview wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricGemma 4 12BHy3 PreviewComparison
Input / output priceUSD per 1M tokensGemma 4 12BNot availableHy3 Preview$0 input / $0 outputA complete price comparison is not available.
Generation speedtokens per secondGemma 4 12BNot availableHy3 PreviewNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGemma 4 12BNot availableHy3 PreviewNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensGemma 4 12B256KHy3 Preview256KListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkGemma 4 12BHy3 PreviewResult
τ²-bench resultsSource 36.3%Not comparable
Terminal-Bench 2.0Source 54.4%Not comparable
Gert LabsSource 36.91%Not comparable
AA Agentic IndexSource 30.7%Not comparable
GDPval-AASource 35.7%Not comparable
GDPval-AASource 1214Not comparable
Coding
BenchmarkGemma 4 12BHy3 PreviewResult
AA-SciCodeSource 38.2%47.6%Hy3 Preview leads
SWE-bench VerifiedSource 74.4%Not comparable
Terminal-Bench 2.0Source 54.4%Not comparable
SciCodeSource 41.2%Not comparable
AA Coding IndexSource 58.8%Not comparable
Reasoning
BenchmarkGemma 4 12BHy3 PreviewResult
BBHSource 53%Not comparable
MRCRv2Source 43.4%Not comparable
AA-LCRSource 55.3%66.7%Hy3 Preview leads
CritPtSource 0.0%4.9%Hy3 Preview leads
KnowledgeGemma 4 12B wins
BenchmarkGemma 4 12BHy3 PreviewResult
GPQASource 78.8%87.2%Hy3 Preview leads
GPQA-DSource 78.8%87.2%Hy3 Preview leads
MMLU-ProSource 77.2%Not comparable
HLE w/o toolsSource 5.2%Not comparable
MMMLUSource 83.4%Not comparable
Artificial Analysis Intelligence IndexSource 22.0%41.2%Hy3 Preview leads
AA-GPQA DiamondSource 75.3%89.7%Hy3 Preview leads
AA-HLESource 14.8%31.6%Hy3 Preview leads
AA-Omniscience IndexSource -51.9%-18.5%Hy3 Preview leads
AA-Omniscience AccuracySource 16.0%31.5%Hy3 Preview leads
AA-Omniscience Hallucination RateSource 80.8%73.0%Hy3 Preview leads
HLESource 25.5%Not comparable
Math
BenchmarkGemma 4 12BHy3 PreviewResult
AIME26Source 77.5%Not comparable
Multimodal
BenchmarkGemma 4 12BHy3 PreviewResult
MMMU-ProSource 69.1%Not comparable
MathVisionSource 79.7%Not comparable
MedXpertQA (MM)Source 48.7%Not comparable
AA-MMMU-ProSource 69.7%Not comparable
Inst. Following
BenchmarkGemma 4 12BHy3 PreviewResult
AA-IFBenchSource 73.5%Not comparable
IFBenchSource 63.1%Not comparable
Frequently Asked Questions (2)

Which is better, Gemma 4 12B or Hy3 Preview?

Gemma 4 12B and Hy3 Preview are tied on the BenchAlign overall score, so the right pick depends on which category matters most for your use case.

Which is better for knowledge tasks, Gemma 4 12B or Hy3 Preview?

Gemma 4 12B has the edge for knowledge tasks in this comparison, averaging 77.5 versus 33.8. Inside this category, AA-Omniscience Index is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 23, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.