readable AI benchmarks (simplified)

readable AI benchmarks

OpenBMB

MiniCPM5-2B

reasoning · open weights · Sep 7, 2026

MiniCPM5-2B has a Quality Score of 17.1, ranking 151st among 289 scored models. It accepts text input, outputs text, and has a 131,072 token context window. Its Reliability Score is 44.2, ranking 99th among 289 scored models, above average (total average: 35.6).

Quality Score17.1coverage 91.2%: missing Epoch General ECI, CursorBench 3.2 and DeepSWE v1.1
Value Scorenot available
Reliability44.2
Cache Discountnot available

Model specification

Reasoning
reasoning
Input modalities
text
Output modalities
text
Context window
131,072 tokens
Weights
open weights

Token prices USD per 1M tokens

Input
not available
Output
not available
Cached Input
not available
Cache write
not available
Cost per task
not available

Capability

Intelligence
14.3
Coding
14.5
Agentic
9.0
Omniscience
-11.7
Correct
8.4%
Blended price
not available

Answer outcomes

Attempt rate: 28.5%

Correct 8.4%Incorrect 20.1%Abstained 71.5%

Artificial Analysis benchmarks

GDPval-AA v2
16%
τ³-Banking
21%
Terminal-Bench v2.1
9%
SciCode
26%
Humanity’s Last Exam
9%
GPQA Diamond
70%
CritPt
0%
AA-Omniscience
44%
AA-LCR
59%

Similar models