Model comparison
LFM2.5-230M vs MiniCPM5-1B
Head-to-head evidence from 5 shared benchmark results across 3 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
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 | LFM2.5-230M | Δ | MiniCPM5-1B |
|---|---|---|---|
| Knowledge | LFM2.5-230M21.2 | Margin→ 22.8 | MiniCPM5-1B44.0 |
| Inst. Following | LFM2.5-230M50.1 | Margin→ 8.4 | MiniCPM5-1B58.5 |
| Math | LFM2.5-230MNot measured | MarginNo overlap | MiniCPM5-1B33.1 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
MMLU-Pro
KnowledgeA 20.3%B 48.9%Winner: MiniCPM5-1BΔ 28.6MMLU-Pro: LFM2.5-230M scored 20.3%; MiniCPM5-1B scored 48.9%. MiniCPM5-1B wins this benchmark. - Source ↗
IFEval
Inst. FollowingA 71.7%B 80.4%Winner: MiniCPM5-1BΔ 8.7IFEval: LFM2.5-230M scored 71.7%; MiniCPM5-1B scored 80.4%. MiniCPM5-1B wins this benchmark. - Source ↗
IFBench
Inst. FollowingA 38.4%B 46.7%Winner: MiniCPM5-1BΔ 8.3IFBench: 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.
| Metric | LFM2.5-230M | MiniCPM5-1B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | LFM2.5-230M$0 input / $0 output | MiniCPM5-1BNot available | A complete price comparison is not available. |
| Generation speedtokens per second | LFM2.5-230MNot available | MiniCPM5-1BNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | LFM2.5-230MNot available | MiniCPM5-1BNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | LFM2.5-230M32K | MiniCPM5-1B131K | MiniCPM5-1B lists the larger context window. |
Benchmark Deep Dive
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
Explore More
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.