Skip to main content

Model comparison

Granite-4.0-350M vs LFM2.5-8B-A1B

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.

38.13/100
Margin
3.1pts
winning →
41.25/100
0 category wins0 category wins

BenchAlign evidence: Granite-4.0-350M estimated; LFM2.5-8B-A1B estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Granite-4.0-350M and LFM2.5-8B-A1B share 12 comparable benchmark results. 0 of 8 categories are comparable. 0 results are unique to Granite-4.0-350M; 6 to LFM2.5-8B-A1B.

Updated July 16, 2026
Shared results
12
Granite-4.0-350M only
0
LFM2.5-8B-A1B only
6
Comparable categories
0 / 8

Benchmark data for Granite-4.0-350M and LFM2.5-8B-A1B 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.

LFM2.5-8B-A1B has the larger context window at 128K, compared with 32K for Granite-4.0-350M.

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 Granite-4.0-350M and LFM2.5-8B-A1B
CategoryGranite-4.0-350MΔLFM2.5-8B-A1B
MathGranite-4.0-350MNot measuredMarginNo overlapLFM2.5-8B-A1B50.0
Inst. FollowingGranite-4.0-350MNot measuredMarginNo overlapLFM2.5-8B-A1B68.8

Operational comparison

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

MetricGranite-4.0-350MLFM2.5-8B-A1BComparison
Input / output priceUSD per 1M tokensGranite-4.0-350M$0 input / $0 outputLFM2.5-8B-A1B$0 input / $0 outputListed prices are equal.
Generation speedtokens per secondGranite-4.0-350MNot availableLFM2.5-8B-A1BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGranite-4.0-350MNot availableLFM2.5-8B-A1BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensGranite-4.0-350M32KLFM2.5-8B-A1B128KLFM2.5-8B-A1B lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkGranite-4.0-350MLFM2.5-8B-A1BResult
τ²-bench resultsSource 13.2%16.1%LFM2.5-8B-A1B leads
BFCL v4Source 49.7%Not comparable
Coding
BenchmarkGranite-4.0-350MLFM2.5-8B-A1BResult
Terminal-Bench HardSource 0.0%4.5%LFM2.5-8B-A1B leads
AA-SciCodeSource 0.9%7.8%LFM2.5-8B-A1B leads
Reasoning
BenchmarkGranite-4.0-350MLFM2.5-8B-A1BResult
AA-LCRSource 0.0%0.0%Tie
CritPtSource 0.0%0.0%Tie
Knowledge
BenchmarkGranite-4.0-350MLFM2.5-8B-A1BResult
Artificial Analysis Intelligence IndexSource 1.0%8.3%LFM2.5-8B-A1B leads
AA-GPQA DiamondSource 26.1%51.3%LFM2.5-8B-A1B leads
AA-HLESource 5.7%6.9%LFM2.5-8B-A1B leads
AA-Omniscience IndexSource -72.1%-33.3%LFM2.5-8B-A1B leads
AA-Omniscience AccuracySource 3.2%9.4%LFM2.5-8B-A1B leads
AA-Omniscience Hallucination RateSource 77.8%47.0%LFM2.5-8B-A1B leads
Math
BenchmarkGranite-4.0-350MLFM2.5-8B-A1BResult
MATH-500Source 88.8%Not comparable
AIME 2025Source 42.5%Not comparable
AIME26Source 50.0%Not comparable
Inst. Following
BenchmarkGranite-4.0-350MLFM2.5-8B-A1BResult
AA-IFBenchSource 15.9%55.6%LFM2.5-8B-A1B leads
IFEvalSource 91.8%Not comparable
IFBenchSource 56.5%Not comparable
Frequently Asked Questions (3)

Can I compare Granite-4.0-350M and LFM2.5-8B-A1B 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 Granite-4.0-350M and LFM2.5-8B-A1B today?

Granite-4.0-350M: $0.00 input / $0.00 output per 1M tokens LFM2.5-8B-A1B: $0.00 input / $0.00 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.