benchgap
Other · model

MiniCPM5-2B benchmark scores

As of 2026-11-22, MiniCPM5-2B (Other) has measured scores on 24 benchmarks and estimated scores on 70 more.

BenchmarkScoreSource
AA-GPQA Diamond70.2%measured
AA-HLE8.9%measured
AA-SciCode26.3%measured
AIME2686.5%measured
Artificial Analysis Intelligence Index11.9%estimated ± 3.0 pp, medium confidence
CritPt0.3%measured
GDPval-AA10.4%measured
GPQA Diamond70.2%measured
HLE8.9%measured
IFBench66.3%measured
AA-LCR59.0%measured
LiveCodeBench v669.1%measured
AA-Omniscience Accuracy18.9%estimated ± 6.7 pp, low confidence
SciCode26.3%measured
Terminal-Bench 2.18.6%measured
BrowseComp43.8%estimated ± 9.2 pp, medium confidence
HLE w/ tools38.8%estimated ± 5.3 pp, low confidence
IFEval86.7%measured
LongBench v243.7%measured
τ²-bench results88.0%estimated ± 12.4 pp, low confidence
AA Coding Index24.0%estimated ± 5.3 pp, medium confidence
APEX-Agents6.9%estimated ± 9.4 pp, low confidence
APEX-Agents-AA12.4%estimated ± 9.5 pp, medium confidence
BioMysteryBench (human-difficult)6.5%estimated ± 6.8 pp, low confidence
DeepSearchQA63.3%estimated ± 9.6 pp, medium confidence
SWE-bench Verified46.4%measured
BFCL v466.6%measured
CyberGym25.9%estimated ± 6.0 pp, low confidence
JobBench4.0%estimated ± 8.7 pp, low confidence
SWE-bench Pro14.4%measured
WideResearch57.2%estimated ± 7.8 pp, low confidence
AA Agentic Index7.4%estimated ± 3.1 pp, high confidence
MMLU-Pro70.8%measured
AA-IFBench56.7%estimated ± 7.4 pp, medium confidence
AIME 202490.0%estimated ± 2.6 pp, high confidence
BBH90.2%estimated ± 2.8 pp, medium confidence
GPQA70.0%estimated ± 1.2 pp, high confidence
MMLU84.6%estimated ± 2.1 pp, high confidence
Vals GPQA Diamond69.3%estimated ± 3.2 pp, high confidence
Vals LiveCodeBench0.3%estimated ± 4.7 pp, low confidence
Vals MMLU-Pro81.0%estimated ± 2.4 pp, low confidence
MATH-50094.6%measured
MMMLU85.4%estimated ± 0.7 pp, medium confidence
AIME 202586.5%measured
AA MMLU-Pro85.7%estimated ± 1.3 pp, medium confidence
Gert Labs27.7%estimated ± 10.0 pp, low confidence
AA Tau3 Banking16.1%estimated ± 4.1 pp, medium confidence
ARC-AGI-175.0%estimated ± 7.8 pp, low confidence
ARC-AGI-231.1%estimated ± 14.4 pp, low confidence
FrontierMath v2 (Tiers 1-3)0.0%estimated ± 8.8 pp, low confidence
FrontierSWE v20.5%estimated ± 14.2 pp, low confidence
MazeBench0.4%estimated ± 5.5 pp, low confidence
OSWorld-Verified60.9%estimated ± 8.4 pp, low confidence
Vals SWE-bench31.0%estimated ± 6.6 pp, low confidence
CWE-Bench-AA15.5%estimated ± 10.1 pp, low confidence
DeepsecBench-AA0.0%estimated ± 8.9 pp, low confidence
AA ITBench35.7%estimated ± 5.1 pp, low confidence
Bug Hunt Bench7.7%estimated ± 10.5 pp, low confidence
CWE-bench v116.6%estimated ± 6.4 pp, low confidence
DeepSWE4.0%estimated ± 7.5 pp, low confidence
DRACO52.3%estimated ± 2.0 pp, low confidence
HLE w/o tools9.3%estimated ± 4.3 pp, medium confidence
Toolathlon-Verified28.4%estimated ± 3.1 pp, medium confidence
GDP.pdf17.0%estimated ± 4.6 pp, medium confidence
ARC-AGI-31.3%estimated ± 9.8 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
Vibe Code Bench0.0%estimated ± 8.4 pp, low confidence
Hermes Bench35.4%estimated ± 2.9 pp, medium confidence
Hermes Index10.2%estimated ± 8.7 pp, low confidence
ExploitGym0.0%estimated ± 10.6 pp, low confidence
C-Eval91.1%estimated ± 1.1 pp, medium confidence
HMMT Feb 202577.3%estimated ± 2.9 pp, high confidence
HMMT Feb 202663.8%measured
HMMT Nov 202566.5%estimated ± 2.8 pp, medium confidence
MCP Atlas56.6%estimated ± 10.7 pp, low confidence
MMAnswerBench69.3%estimated ± 1.3 pp, medium confidence
MMLU-Redux84.7%measured
NL2Repo17.4%estimated ± 3.4 pp, medium confidence
QwenClawBench55.9%estimated ± 6.0 pp, low confidence
SuperGPQA40.8%measured
Toolathlon27.0%estimated ± 6.3 pp, low confidence
HealthBench Hard3.5%estimated ± 8.6 pp, low confidence
MMLU-Pro (Arcee)79.1%estimated ± 3.4 pp, medium confidence
React Native Evals64.5%estimated ± 2.7 pp, low confidence
ResearchClawBench13.1%estimated ± 2.2 pp, low confidence
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
ScarfBench22.2%estimated ± 14.0 pp, low confidence
SimpleQA23.6%estimated ± 7.8 pp, medium confidence
LiveCodeBench55.2%estimated ± 14.6 pp, low confidence
IMOAnswerBench67.1%estimated ± 5.6 pp, medium confidence
MRCRv225.7%estimated ± 11.3 pp, low confidence
MMLongBench-Doc60.2%estimated ± 2.6 pp, low confidence
BioBasicsBench33.9%estimated ± 10.7 pp, low confidence
PinchBench89.1%estimated ± 5.0 pp, low confidence