Skip to main content

Model comparison

Gemma 4 31B 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.

61/100
Margin
19.8pts
← winning
41.25/100
0 category wins0 category wins

BenchAlign evidence: Gemma 4 31B supported; LFM2.5-8B-A1B estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Gemma 4 31B and LFM2.5-8B-A1B share 12 comparable benchmark results. 0 of 8 categories are comparable. 18 results are unique to Gemma 4 31B; 6 to LFM2.5-8B-A1B.

Updated July 16, 2026
Shared results
12
Gemma 4 31B only
18
LFM2.5-8B-A1B only
6
Comparable categories
0 / 8

Benchmark data for Gemma 4 31B 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.

Gemma 4 31B has 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 Gemma 4 31B and LFM2.5-8B-A1B
CategoryGemma 4 31BΔLFM2.5-8B-A1B
CodingGemma 4 31B41.6MarginNo overlapLFM2.5-8B-A1BNot measured
KnowledgeGemma 4 31B53.3MarginNo overlapLFM2.5-8B-A1BNot measured
MathGemma 4 31BNot measuredMarginNo overlapLFM2.5-8B-A1B50.0
MultimodalGemma 4 31B76.9MarginNo overlapLFM2.5-8B-A1BNot measured
Inst. FollowingGemma 4 31BNot measuredMarginNo overlapLFM2.5-8B-A1B68.8

Operational comparison

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

MetricGemma 4 31BLFM2.5-8B-A1BComparison
Input / output priceUSD per 1M tokensGemma 4 31B$0 input / $0 outputLFM2.5-8B-A1B$0 input / $0 outputListed prices are equal.
Generation speedtokens per secondGemma 4 31BNot availableLFM2.5-8B-A1BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGemma 4 31BNot availableLFM2.5-8B-A1BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensGemma 4 31B256KLFM2.5-8B-A1B128KGemma 4 31B lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkGemma 4 31BLFM2.5-8B-A1BResult
AA Agentic IndexSource 14.4%Not comparable
τ²-bench resultsSource 59.9%16.1%Gemma 4 31B leads
GDPval-AASource 15.2%Not comparable
GDPval-AASource 804Not comparable
Gert LabsSource 35.26%Not comparable
AA EnterpriseOps-GymSource 28.3%Not comparable
AA Harvey LABSource 0.0%Not comparable
AA ITBenchSource 37.3%Not comparable
AA Tau3 BankingSource 15.1%Not comparable
BFCL v4Source 49.7%Not comparable
Coding
BenchmarkGemma 4 31BLFM2.5-8B-A1BResult
SWE-RebenchSource 41.6%Not comparable
React Native EvalsSource 75.2%Not comparable
AA Coding IndexSource 43.4%Not comparable
Terminal-Bench HardSource 36.4%4.5%Gemma 4 31B leads
AA-SciCodeSource 43.4%7.8%Gemma 4 31B leads
Reasoning
BenchmarkGemma 4 31BLFM2.5-8B-A1BResult
AA-LCRSource 62.0%0.0%Gemma 4 31B leads
CritPtSource 1.4%0.0%Gemma 4 31B leads
Knowledge
BenchmarkGemma 4 31BLFM2.5-8B-A1BResult
GPQASource 84.3%Not comparable
MMLU-ProSource 85.2%Not comparable
HLESource 26.5%Not comparable
HLE w/o toolsSource 19.5%Not comparable
Artificial Analysis Intelligence IndexSource 29.4%8.3%Gemma 4 31B leads
AA-GPQA DiamondSource 85.7%51.3%Gemma 4 31B leads
AA-HLESource 22.7%6.9%Gemma 4 31B leads
AA-Omniscience IndexSource -45.4%-33.3%LFM2.5-8B-A1B leads
AA-Omniscience AccuracySource 19.9%9.4%Gemma 4 31B leads
AA-Omniscience Hallucination RateSource 81.6%47.0%LFM2.5-8B-A1B leads
AA Openness IndexSource 38.9%Not comparable
Math
BenchmarkGemma 4 31BLFM2.5-8B-A1BResult
MATH-500Source 88.8%Not comparable
AIME 2025Source 42.5%Not comparable
AIME26Source 50.0%Not comparable
Multimodal
BenchmarkGemma 4 31BLFM2.5-8B-A1BResult
MMMU-ProSource 76.9%Not comparable
AA-MMMU-ProSource 73.4%Not comparable
Inst. Following
BenchmarkGemma 4 31BLFM2.5-8B-A1BResult
AA-IFBenchSource 75.6%55.6%Gemma 4 31B leads
IFEvalSource 91.8%Not comparable
IFBenchSource 56.5%Not comparable
Frequently Asked Questions (3)

Can I compare Gemma 4 31B 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 Gemma 4 31B and LFM2.5-8B-A1B today?

Gemma 4 31B: $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.

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

Gemma 4 31B
API / mo$0
Self-host / mo$429
Break-even
LFM2.5-8B-A1B
API / mo$0
Self-host / moNot listed
Break-even
Proprietary model — self-hosting not applicable.
Model the full break-even

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.