MiniCPM5-1B (Non-reasoning)

OpenBMB·Released 2026-05-25

Limited comparison data25% coverage5/5 fields directly observedUpdated Jul 28, 2026, 6:00 PM

Benchmarks

MMLU-ProNot evaluated

GPQA Diamond

26.9%

HLE

4.6%

LiveCodeBenchNot evaluated

SciCode

1.4%

TerminalBench Hard

0.0%

MATH-500Not evaluated

AIMENot evaluated

AIME 2025Not evaluated

IFBench

35.2%

Long Context Recall

4.7%

Tau2

82.5%

Market AverageTop Score

Nova 2.0 Lite (Non-reasoning)

Amazon

Claude 3 Opus

Anthropic

Qwen3 32B (Reasoning)

Alibaba

Sarvam 105B (high)

Sarvam

Gemma 4 E4B (Reasoning)

Google

Gemini 2.5 Flash-Lite (Reasoning)

Google