Skip to main content

Model comparison

LFM2.5-230M vs MiniCPM5-1B

Data verified

Head-to-head evidence from 5 shared benchmark results across 3 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

LiquidAI
N/A
No comparison
N/A
0 category wins2 category wins

Evidence parity. LFM2.5-230M and MiniCPM5-1B share 5 comparable benchmark results. 2 of 8 categories are comparable. 1 result is unique to LFM2.5-230M; 9 to MiniCPM5-1B.

Updated July 23, 2026
Shared results
5
LFM2.5-230M only
1
MiniCPM5-1B only
9
Comparable categories
2 / 8

Treat this as a split decision. LFM2.5-230M makes more sense if you would rather avoid the extra latency and token burn of a reasoning model; MiniCPM5-1B is the better fit if knowledge is the priority or you need the larger 131K context window.

Confidence note. This is a partial-evidence comparison with 5 shared benchmark results across 3 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

LFM2.5-230M and MiniCPM5-1B finish on the same BenchAlign overall score, so this is less about a single winner and more about where the edge shows up. The BenchAlign headline says tie; the benchmark table is where the real choice happens.

MiniCPM5-1B is the reasoning model in the pair, while LFM2.5-230M is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. MiniCPM5-1B gives you the larger context window at 131K, compared with 32K for LFM2.5-230M.

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 LFM2.5-230M and MiniCPM5-1B
CategoryLFM2.5-230MΔMiniCPM5-1B
KnowledgeLFM2.5-230M21.2Margin 22.8MiniCPM5-1B44.0
Inst. FollowingLFM2.5-230M50.1Margin 8.4MiniCPM5-1B58.5
MathLFM2.5-230MNot measuredMarginNo overlapMiniCPM5-1B33.1

Decisive benchmark drivers

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

More
A · LFM2.5-230MB · MiniCPM5-1B
  1. MMLU-Pro

    Knowledge
    Source ↗
    A 20.3%B 48.9%
    Winner: MiniCPM5-1BΔ 28.6
    MMLU-Pro: LFM2.5-230M scored 20.3%; MiniCPM5-1B scored 48.9%. MiniCPM5-1B wins this benchmark.
  2. IFEval

    Inst. Following
    Source ↗
    A 71.7%B 80.4%
    Winner: MiniCPM5-1BΔ 8.7
    IFEval: LFM2.5-230M scored 71.7%; MiniCPM5-1B scored 80.4%. MiniCPM5-1B wins this benchmark.
  3. IFBench

    Inst. Following
    Source ↗
    A 38.4%B 46.7%
    Winner: MiniCPM5-1BΔ 8.3
    IFBench: LFM2.5-230M scored 38.4%; MiniCPM5-1B scored 46.7%. MiniCPM5-1B wins this benchmark.

Operational comparison

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

MetricLFM2.5-230MMiniCPM5-1BComparison
Input / output priceUSD per 1M tokensLFM2.5-230M$0 input / $0 outputMiniCPM5-1BNot availableA complete price comparison is not available.
Generation speedtokens per secondLFM2.5-230MNot availableMiniCPM5-1BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenLFM2.5-230MNot availableMiniCPM5-1BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensLFM2.5-230M32KMiniCPM5-1B131KMiniCPM5-1B lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkLFM2.5-230MMiniCPM5-1BResult
BFCL v4Source 21.0%25.1%MiniCPM5-1B leads
Coding
BenchmarkLFM2.5-230MMiniCPM5-1BResult
LiveCodeBench ProSource 22.7%Not comparable
LiveCodeBench v6Source 33.5%Not comparable
Reasoning
BenchmarkLFM2.5-230MMiniCPM5-1BResult
BBHSource 71.9%Not comparable
KnowledgeMiniCPM5-1B wins
BenchmarkLFM2.5-230MMiniCPM5-1BResult
GPQASource 25.4%Not comparable
GPQA-DSource 25.4%26.3%MiniCPM5-1B leads
MMLU-ProSource 20.3%48.9%MiniCPM5-1B leads
MMLU-ReduxSource 70.1%Not comparable
SuperGPQASource 23.1%Not comparable
Math
BenchmarkLFM2.5-230MMiniCPM5-1BResult
AIME 2025Source 40.4%Not comparable
AIME26Source 40.4%Not comparable
HMMT Feb 2026Source 25.8%Not comparable
MATH-500Source 91.6%Not comparable
Inst. FollowingMiniCPM5-1B wins
BenchmarkLFM2.5-230MMiniCPM5-1BResult
IFEvalSource 71.7%80.4%MiniCPM5-1B leads
IFBenchSource 38.4%46.7%MiniCPM5-1B leads
Frequently Asked Questions (3)

Which is better, LFM2.5-230M or MiniCPM5-1B?

LFM2.5-230M and MiniCPM5-1B are tied on the BenchAlign overall score, so the right pick depends on which category matters most for your use case.

Which is better for knowledge tasks, LFM2.5-230M or MiniCPM5-1B?

MiniCPM5-1B has the edge for knowledge tasks in this comparison, averaging 44 versus 21.2. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, LFM2.5-230M or MiniCPM5-1B?

MiniCPM5-1B has the edge for instruction following in this comparison, averaging 58.5 versus 50.1. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 23, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.