Skip to main content

Model comparison

LFM2.5-8B-A1B vs ZAYA1-74B-Preview

Data verified

Head-to-head evidence from 1 shared benchmark result across 1 category. Overall scores shown here use the public BenchAlign v5 ranking lane.

41.25/100
Margin
13.8pts
winning →
55/100
0 category wins1 category wins

BenchAlign evidence: LFM2.5-8B-A1B estimated; ZAYA1-74B-Preview not scored. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. LFM2.5-8B-A1B and ZAYA1-74B-Preview share 1 comparable benchmark result. 1 of 8 categories are comparable. 17 results are unique to LFM2.5-8B-A1B; 6 to ZAYA1-74B-Preview.

Updated July 16, 2026
Shared results
1
LFM2.5-8B-A1B only
17
ZAYA1-74B-Preview only
6
Comparable categories
1 / 8

Pick ZAYA1-74B-Preview if you want the stronger benchmark profile. LFM2.5-8B-A1B only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.

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

Why this result

ZAYA1-74B-Preview is clearly ahead on the provisional aggregate, 55 to 37. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

ZAYA1-74B-Preview's sharpest advantage is in mathematics, where it averages 76.4 against 50. The single biggest benchmark swing on the page is AIME26, 50.0% to 76.4%.

ZAYA1-74B-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 LFM2.5-8B-A1B and ZAYA1-74B-Preview
CategoryLFM2.5-8B-A1BΔZAYA1-74B-Preview
MathLFM2.5-8B-A1B50.0Margin 26.4ZAYA1-74B-Preview76.4
CodingLFM2.5-8B-A1BNot measuredMarginNo overlapZAYA1-74B-Preview53.2
KnowledgeLFM2.5-8B-A1BNot measuredMarginNo overlapZAYA1-74B-Preview66.1
Inst. FollowingLFM2.5-8B-A1B68.8MarginNo overlapZAYA1-74B-PreviewNot measured

Decisive benchmark drivers

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

More
A · LFM2.5-8B-A1BB · ZAYA1-74B-Preview
  1. AIME26

    Math
    Source ↗
    A 50.0%B 76.4%
    Winner: ZAYA1-74B-PreviewΔ 26.4
    AIME26: LFM2.5-8B-A1B scored 50.0%; ZAYA1-74B-Preview scored 76.4%. ZAYA1-74B-Preview wins this benchmark.

Operational comparison

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

MetricLFM2.5-8B-A1BZAYA1-74B-PreviewComparison
Input / output priceUSD per 1M tokensLFM2.5-8B-A1B$0 input / $0 outputZAYA1-74B-Preview$0 input / $0 outputListed prices are equal.
Generation speedtokens per secondLFM2.5-8B-A1BNot availableZAYA1-74B-PreviewNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenLFM2.5-8B-A1BNot availableZAYA1-74B-PreviewNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensLFM2.5-8B-A1B128KZAYA1-74B-Preview256KZAYA1-74B-Preview lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkLFM2.5-8B-A1BZAYA1-74B-PreviewResult
BFCL v4Source 49.7%Not comparable
τ²-bench resultsSource 16.1%Not comparable
τ²-bench AirlineSource 56.1%Not comparable
Coding
BenchmarkLFM2.5-8B-A1BZAYA1-74B-PreviewResult
Terminal-Bench HardSource 4.5%Not comparable
AA-SciCodeSource 7.8%Not comparable
LiveCodeBench v6Source 65.7%Not comparable
SWE-bench VerifiedSource 53.2%Not comparable
Reasoning
BenchmarkLFM2.5-8B-A1BZAYA1-74B-PreviewResult
AA-LCRSource 0.0%Not comparable
CritPtSource 0.0%Not comparable
Knowledge
BenchmarkLFM2.5-8B-A1BZAYA1-74B-PreviewResult
AA-GPQA DiamondSource 51.3%Not comparable
AA-HLESource 6.9%Not comparable
AA-Omniscience IndexSource -33.3%Not comparable
AA-Omniscience AccuracySource 9.4%Not comparable
AA-Omniscience Hallucination RateSource 47.0%Not comparable
Artificial Analysis Intelligence IndexSource 8.3%Not comparable
MMLU-ProSource 68.1%Not comparable
GPQASource 57.3%Not comparable
GPQA-DSource 57.3%Not comparable
MathZAYA1-74B-Preview wins
BenchmarkLFM2.5-8B-A1BZAYA1-74B-PreviewResult
MATH-500Source 88.8%Not comparable
AIME 2025Source 42.5%Not comparable
AIME26Source 50.0%76.4%ZAYA1-74B-Preview leads
Inst. Following
BenchmarkLFM2.5-8B-A1BZAYA1-74B-PreviewResult
IFEvalSource 91.8%Not comparable
IFBenchSource 56.5%Not comparable
AA-IFBenchSource 55.6%Not comparable
Frequently Asked Questions (2)

Which is better, LFM2.5-8B-A1B or ZAYA1-74B-Preview?

ZAYA1-74B-Preview is ahead on BenchLM's provisional leaderboard, 55 to 37. The biggest single separator in this matchup is AIME26, where the scores are 50.0% and 76.4%.

Which is better for math, LFM2.5-8B-A1B or ZAYA1-74B-Preview?

ZAYA1-74B-Preview has the edge for math in this comparison, averaging 76.4 versus 50. Inside this category, AIME26 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.