MiniCPM5-1B

MiniCPM5-1B is a reasoning model from OpenBMB in the MiniCPM5 family. 13 benchmarks count toward its score, in 6 categories.

availableShows if the model has enough results for an index.
IndexOverall score out of 100.14.2 ±7.0
CoverageShare of the index weight with results.75%
SpeedOutput tokens per second.
Input / 1MUS dollars per 1M input tokens.N/A
Output / 1MUS dollars per 1M output tokens.N/A
ContextMaximum tokens in one request.131K
EloLMArena rating and rank.N/A

The index is a score out of 100. The ± range shows how much it can change.

CapabilitiesScore per category, out of 100.

Out of 100
AgenticMulti-step tasks with tools.
9.0
CodingCode writing and repair.
7.5
ReasoningLogic problems and puzzles.
N/A
MultimodalTasks with images and text.
N/A
KnowledgeFacts and expert knowledge.
10.3
MultilingualTasks in many languages.
14.5
InstructionTasks with strict rules in the prompt.
22.5
MathMath problems.
19.3

Results

13 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result as a score out of 100.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
MATH-500 Problem SetMath91.6%44.2Dan Hendrycks et al.
Artificial Analysis Openness IndexKnowledge83.3%Artificial Analysis
Instruction-Following EvalInstruction80.4%24.5Jeffrey Zhou et al.
BIG-Bench HardReasoning71.9%Mirac Suzgun et al.
MMLU-ReduxKnowledge70.1%14.7Qwen
Massive Multitask Language Understanding ProfessionalKnowledge48.9%5.0Yubo Wang et al.
Instruction Following BenchmarkInstruction46.7%20.4Benchmark authors
American Invitational Mathematics Examination 2025Math40.4%10.4Mathematical Association of America
AIME 2026Math40.4%13.4Qwen
LiveCodeBench v6Coding33.5%7.5LiveCodeBench maintainers
GPQA DiamondKnowledge26.3%5.0David Rein et al.
Harvard-MIT Mathematics Tournament February 2026Math25.8%9.1Qwen
Berkeley Function Calling Leaderboard v4Agentic25.1%9.0Arcee AI
SuperGPQA: Scaling LLM Evaluation Across 285 Graduate DisciplinesKnowledge23.1%16.4Xiaoxuan Du et al.
LiveCodeBench ProCoding22.7%LiveCodeBench Pro authors
EuroEval FrenchMultilingual11.7%17.0EuroEval
EuroEval SpanishMultilingual9.7%14.5EuroEval
EuroEval GermanMultilingual7.1%11.3EuroEval

13 benchmarks count, from 15 of 18 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authorsEuroEval, collected directlyMIT — the leaderboard site and its CSV routes are in the licensed repository

More from OpenBMB

MiniCPM5-2B37.3MiniCPM-o 2.6Unranked