Skip to main content

Model comparison

Hy3 Preview vs LFM2.5-8B-A1B

Data verified

Head-to-head evidence from 10 shared benchmark results across 4 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

53/100
Margin
11.8pts
← winning
41.25/100
0 category wins1 category wins

BenchAlign evidence: Hy3 Preview not scored; LFM2.5-8B-A1B estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Hy3 Preview and LFM2.5-8B-A1B share 10 comparable benchmark results. 1 of 8 categories are comparable. 12 results are unique to Hy3 Preview; 8 to LFM2.5-8B-A1B.

Updated July 16, 2026
Shared results
10
Hy3 Preview only
12
LFM2.5-8B-A1B only
8
Comparable categories
1 / 8

Pick Hy3 Preview if you want the stronger benchmark profile. LFM2.5-8B-A1B only becomes the better choice if instruction following is the priority.

Confidence note. This is a partial-evidence comparison with 10 shared benchmark results across 4 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

Hy3 Preview is clearly ahead on the provisional aggregate, 53 to 37. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Hy3 Preview gives you the larger context window at 256K, compared with 128K for LFM2.5-8B-A1B.

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 Hy3 Preview and LFM2.5-8B-A1B
CategoryHy3 PreviewΔLFM2.5-8B-A1B
Inst. FollowingHy3 Preview63.1Margin 5.7LFM2.5-8B-A1B68.8
AgenticHy3 Preview54.4MarginNo overlapLFM2.5-8B-A1BNot measured
CodingHy3 Preview57.8MarginNo overlapLFM2.5-8B-A1BNot measured
KnowledgeHy3 Preview33.8MarginNo overlapLFM2.5-8B-A1BNot measured
MathHy3 PreviewNot measuredMarginNo overlapLFM2.5-8B-A1B50.0

Decisive benchmark drivers

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

More
A · Hy3 PreviewB · LFM2.5-8B-A1B
  1. IFBench

    Inst. Following
    Source ↗
    A 63.1%B 56.5%
    Winner: Hy3 PreviewΔ 6.6
    IFBench: Hy3 Preview scored 63.1%; LFM2.5-8B-A1B scored 56.5%. Hy3 Preview wins this benchmark.

Operational comparison

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

MetricHy3 PreviewLFM2.5-8B-A1BComparison
Input / output priceUSD per 1M tokensHy3 Preview$0 input / $0 outputLFM2.5-8B-A1B$0 input / $0 outputListed prices are equal.
Generation speedtokens per secondHy3 PreviewNot availableLFM2.5-8B-A1BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenHy3 PreviewNot availableLFM2.5-8B-A1BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensHy3 Preview256KLFM2.5-8B-A1B128KHy3 Preview lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkHy3 PreviewLFM2.5-8B-A1BResult
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
BFCL v4Source 49.7%Not comparable
τ²-bench resultsSource 16.1%Not comparable
Coding
BenchmarkHy3 PreviewLFM2.5-8B-A1BResult
SWE-bench VerifiedSource 74.4%Not comparable
Terminal-Bench 2.0Source 54.4%Not comparable
SciCodeSource 41.2%Not comparable
AA-SciCodeSource 47.6%7.8%Hy3 Preview leads
AA Coding IndexSource 58.8%Not comparable
Terminal-Bench HardSource 4.5%Not comparable
Reasoning
BenchmarkHy3 PreviewLFM2.5-8B-A1BResult
AA-LCRSource 66.7%0.0%Hy3 Preview leads
CritPtSource 4.9%0.0%Hy3 Preview leads
Knowledge
BenchmarkHy3 PreviewLFM2.5-8B-A1BResult
Artificial Analysis Intelligence IndexSource 41.2%8.3%Hy3 Preview leads
GPQASource 87.2%Not comparable
GPQA-DSource 87.2%Not comparable
HLESource 25.5%Not comparable
AA-Omniscience AccuracySource 31.5%9.4%Hy3 Preview leads
AA-Omniscience Hallucination RateSource 73.0%47.0%LFM2.5-8B-A1B leads
AA-GPQA DiamondSource 89.7%51.3%Hy3 Preview leads
AA-HLESource 31.6%6.9%Hy3 Preview leads
AA-Omniscience IndexSource -18.5%-33.3%Hy3 Preview leads
Math
BenchmarkHy3 PreviewLFM2.5-8B-A1BResult
MATH-500Source 88.8%Not comparable
AIME 2025Source 42.5%Not comparable
AIME26Source 50.0%Not comparable
Inst. FollowingLFM2.5-8B-A1B wins
BenchmarkHy3 PreviewLFM2.5-8B-A1BResult
IFBenchSource 63.1%56.5%Hy3 Preview leads
IFEvalSource 91.8%Not comparable
AA-IFBenchSource 55.6%Not comparable
Frequently Asked Questions (2)

Which is better, Hy3 Preview or LFM2.5-8B-A1B?

Hy3 Preview is ahead on BenchLM's provisional leaderboard, 53 to 37. The biggest single separator in this matchup is IFBench, where the scores are 63.1% and 56.5%.

Which is better for instruction following, Hy3 Preview or LFM2.5-8B-A1B?

LFM2.5-8B-A1B has the edge for instruction following in this comparison, averaging 68.8 versus 63.1. Inside this category, IFBench is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 16, 2026

The AI models change fast. We track them for you.

A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.