Skip to main content

Model comparison

LFM2.5-8B-A1B vs Trinity-Large-Preview

Data verified

Head-to-head evidence from 12 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

41.25/100
Margin
14.4pts
winning →
55.67/100
0 category wins0 category wins

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

Evidence parity. LFM2.5-8B-A1B and Trinity-Large-Preview share 12 comparable benchmark results. 0 of 8 categories are comparable. 6 results are unique to LFM2.5-8B-A1B; 7 to Trinity-Large-Preview.

Updated July 16, 2026
Shared results
12
LFM2.5-8B-A1B only
6
Trinity-Large-Preview only
7
Comparable categories
0 / 8

Benchmark data for LFM2.5-8B-A1B and Trinity-Large-Preview is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 12 shared benchmark results across 5 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.

Trinity-Large-Preview is priced at $0.25 input / $1.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for LFM2.5-8B-A1B. Trinity-Large-Preview has the larger context window at 512K, 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 Trinity-Large-Preview
CategoryLFM2.5-8B-A1BΔTrinity-Large-Preview
MathLFM2.5-8B-A1B50.0MarginNo overlapTrinity-Large-PreviewNot measured
Inst. FollowingLFM2.5-8B-A1B68.8MarginNo overlapTrinity-Large-PreviewNot measured

Operational comparison

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

MetricLFM2.5-8B-A1BTrinity-Large-PreviewComparison
Input / output priceUSD per 1M tokensLFM2.5-8B-A1B$0 input / $0 outputTrinity-Large-Preview$0.25 input / $1 outputLFM2.5-8B-A1B has the lower combined listed price.
Generation speedtokens per secondLFM2.5-8B-A1BNot availableTrinity-Large-PreviewNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenLFM2.5-8B-A1BNot availableTrinity-Large-PreviewNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensLFM2.5-8B-A1B128KTrinity-Large-Preview512KTrinity-Large-Preview lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkLFM2.5-8B-A1BTrinity-Large-PreviewResult
BFCL v4Source 49.7%Not comparable
τ²-bench resultsSource 16.1%90.1%Trinity-Large-Preview leads
GDPval-AASource 2.7%Not comparable
GDPval-AASource 554Not comparable
Coding
BenchmarkLFM2.5-8B-A1BTrinity-Large-PreviewResult
Terminal-Bench HardSource 4.5%22.7%Trinity-Large-Preview leads
AA-SciCodeSource 7.8%36.1%Trinity-Large-Preview leads
Reasoning
BenchmarkLFM2.5-8B-A1BTrinity-Large-PreviewResult
AA-LCRSource 0.0%33.0%Trinity-Large-Preview leads
CritPtSource 0.0%0.9%Trinity-Large-Preview leads
Knowledge
BenchmarkLFM2.5-8B-A1BTrinity-Large-PreviewResult
AA-GPQA DiamondSource 51.3%75.2%Trinity-Large-Preview leads
AA-HLESource 6.9%14.7%Trinity-Large-Preview leads
AA-Omniscience IndexSource -33.3%-44.2%LFM2.5-8B-A1B leads
AA-Omniscience AccuracySource 9.4%22.8%Trinity-Large-Preview leads
AA-Omniscience Hallucination RateSource 47.0%86.6%LFM2.5-8B-A1B leads
Artificial Analysis Intelligence IndexSource 8.3%24.5%Trinity-Large-Preview leads
MMLUSource 87.2%Not comparable
MMLU-Pro (Arcee)Source 75.2%Not comparable
GPQA-DSource 63.3%Not comparable
Math
BenchmarkLFM2.5-8B-A1BTrinity-Large-PreviewResult
MATH-500Source 88.8%Not comparable
AIME 2025Source 42.5%Not comparable
AIME26Source 50.0%Not comparable
AIME25 (Arcee)Source 24.0%Not comparable
Multimodal
BenchmarkLFM2.5-8B-A1BTrinity-Large-PreviewResult
Design Arena WebsiteSource 1169Not comparable
Inst. Following
BenchmarkLFM2.5-8B-A1BTrinity-Large-PreviewResult
IFEvalSource 91.8%Not comparable
IFBenchSource 56.5%Not comparable
AA-IFBenchSource 55.6%56.3%Trinity-Large-Preview leads
Frequently Asked Questions (3)

Can I compare LFM2.5-8B-A1B and Trinity-Large-Preview on BenchLM yet?

Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.

Why does this comparison show “coming soon”?

BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.

What data is available for LFM2.5-8B-A1B and Trinity-Large-Preview today?

LFM2.5-8B-A1B: $0.00 input / $0.00 output per 1M tokens Trinity-Large-Preview: $0.25 input / $1.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.

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.