Back
FR

OpenBMB

MiniCPM5-2B

ReasoningOpen weightsModels.devHugging Face
Intelligence
12.5
Rank 373 of 768 measured models
Coding
14.5
Rank 248 of 299 measured models
Context window
131K
Rank 868 of 1296 measured models

MiniCPM5-2B scores 12.5 on the Artificial Analysis Intelligence Index, ranking 373rd of 768 measured models. The closest models on this index are Inkling (Xhigh) (12.5), o3 Mini (batch) (12.5), and Qwen3.5 Omni Flash (12.5).

Artificial Analysis Indices
Intelligence12.5
Rank 373 of 768 measured models
Coding14.5
Rank 248 of 299 measured models
Agentic6.7
Rank 132 of 190 measured models
Capability indexes
Performance in specific industries, measured by Artificial Analysis
Finance & Accounting11.0
Rank 207 of 241 measured models
Strategy & Ops5.9
Rank 219 of 241 measured models
Legal15.9
Rank 192 of 241 measured models
Engineering18.5
Rank 186 of 240 measured models
Economics23.3
Rank 186 of 248 measured models
Standard Benchmarks
GPQA Diamond70.2%
Rank 318 of 620 measured models
HLE8.9%
Rank 370 of 681 measured models
SciCode26.3%
Rank 233 of 248 measured models
AA-LCR59.3%
Rank 307 of 592 measured models
Terminal-Bench 2.18.6%
Rank 206 of 245 measured models
Terminal-Bench 4.00.0%
Rank 170 of 240 measured models
τ-Bench Banking20.8%
Rank 98 of 211 measured models
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy