What are MiniCPM5-2B's benchmark scores?

As of 25 Oct 2026, MiniCPM5-2B scores 49.3 ±5.1 on the BenchLeader Index, strongest in knowledge (56) and weakest in reasoning (41). That rests on 5 independent benchmark results, and every score on this page links to its publisher.

How does MiniCPM5-2B rank?

MiniCPM5-2B is #404 of 785 ranked configurations on 25 Oct 2026. 338 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.

When was MiniCPM5-2B released?

OpenBMB released MiniCPM5-2B on 7 Sept 2026.

OpenBMBOpen weightsReasoning modelCompare with another model

MiniCPM5-2B

MiniCPM5-2B is an OpenBMB open-weights reasoning model, released 7 Sept 2026. Its best configuration ranks #404 of 785 on the BenchLeader Index at 49.3 ±5.1, in the lower half. The ± is the point: 338 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in knowledge (56) and lowest in reasoning (41). Last measured 7 Sept 2026.

Blended price: –
Output speed: –
First answer: –
Context: 131k
Full answer: –
Cost per run: –
Released: 7 Sept 2026

How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.

Overall index49
Reasoning41
Agents & tools49
Knowledge56
Long context54
Composite43

How its index has moved

19 Sept 2026 to 18 Oct 2026

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmark	not stated	Source
GPQA Diamond (AA)not in index	70.2%#294	Artificial Analysis
Humanity's Last Exam (AA)not in index	8.9%#340	Artificial Analysis
CritPt	0.3%#271	Artificial Analysis

Coding

Benchmark	not stated	Source
SciCode (AA)not in index	26.3%#217	Artificial Analysis
Terminal-Bench 4.0 (AA)not in index	0.0%#152	Artificial Analysis
Terminal-Bench 2.1 (AA)not in index	8.6%#197	Artificial Analysis

Agents & tools

Benchmark	not stated	Source
GDPval-AA v2.1not in index	10.4%#113	Artificial Analysis
τ³-Banking (AA)	20.8%#94	Artificial Analysis
AutomationBenchnot in index	1.8%#185	Artificial Analysis
GDP.pdf (AA)not in index	1.4%#196	Artificial Analysis

Knowledge

Benchmark	not stated	Source
AA-Omniscience	-11.7#207	Artificial Analysis
AA-Omniscience: accuracynot in index	8.4%#515	Artificial Analysis
AA-Omniscience: non-hallucinationnot in index	78.1%#14	Artificial Analysis

Long context

Benchmark	not stated	Source	Trend
AA-LCR	59.3%#286	Artificial Analysis

Composite

Benchmark	not stated	Source	Trend
AA Intelligence Index v4.3.2	12.5#332	Artificial Analysis

New this month

Questions people ask

What are MiniCPM5-2B's benchmark scores?: As of 25 Oct 2026, MiniCPM5-2B scores 49.3 ±5.1 on the BenchLeader Index, strongest in knowledge (56) and weakest in reasoning (41). That rests on 5 independent benchmark results, and every score on this page links to its publisher.
How does MiniCPM5-2B rank?: MiniCPM5-2B is #404 of 785 ranked configurations on 25 Oct 2026. 338 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
When was MiniCPM5-2B released?: OpenBMB released MiniCPM5-2B on 7 Sept 2026.

Data as of 25 Oct 2026. Compare with another model.

Cite as: BenchLeader, “MiniCPM5-2B: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/minicpm5-2b.