OpenBMBOpen weightsReasoning modelAuto-detected

MiniCPM5-1B

Name: MiniCPM5-1B benchmark results
Creator: BenchLeader

Best configuration ranks #403 of 610 on the BenchLeader Index at 44.9 ±9.4.

Blended price: –
Output speed: –
First answer: –
Context: 128k

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

Overall index45
Agents & tools34
Knowledge57
Instruction following50
Long context28
Composite40

Reasoning-effort configurations

The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Default” means the publisher did not say which setting was used.

Effort	Index	Rank	Speed	First answer	Chat reply cost	Categories
no reasoning	44.1	#424	–	–	–	Agents & tools 34 · Composite 40 · Instruction following 38 · Knowledge 64 · Long context 27
defaultbest	44.9	#403	–	–	–	Agents & tools 34 · Composite 40 · Instruction following 50 · Knowledge 57 · Long context 28

Benchmark results

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	no reasoning	default	Source
GPQA Diamond (AA)not in index	26.9%#505	27.8%#501	Artificial Analysis
Humanity's Last Exam (AA)not in index	4.5%#414	6.5%#316	Artificial Analysis

Agents & tools

Benchmark	no reasoning	default	Source
Terminal-Bench Hard	0.0%#345	0.0%#345	Artificial Analysis
τ²-Bench Telecom (AA)not in index	82.5%#110	81.0%#115	Artificial Analysis

Knowledge

Benchmark	no reasoning	default	Source
AA-Omniscience	-0.8#100	-14.6#160	Artificial Analysis

Instruction following

Benchmark	no reasoning	default	Source
IFBench	35.2%#296	49.3%#175	Artificial Analysis

Long context

Benchmark	no reasoning	default	Source
AA-LCR	5.0%#414	6.0%#410	Artificial Analysis

Composite

Benchmark	no reasoning	default	Source
AA Intelligence Index	8.7#356	8.8#349	Artificial Analysis