Unverified50% confidenceFactExact time
On a real Android device, the same 4B small model jumped from a 0/20 to a 20/20 success rate simply by changing the policy of "when to consult the model".
1
Sources
50%
Confidence
Long-term
Relevance
10/24/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAfter introducing the dispute mechanism, the same model's success rate became 20/20; the control scenario (an app in the foreground but no one touching it) still maintained 20/20 with zero model calls.71% similarUnverifiedIn Google's Android World benchmark, Artemis reported a success rate of 99%, covering more than 20 apps and over 100 multi-step tasks.67% similarUnverifiedA query plan generated by a small model with only 4B parameters produced an execution plan that is 81% faster than the native Postgres optimizer.62% similarUnverifiedThe Neural 3 base model's 4-layer version scores only 11.7 on the mobile action benchmark and 21 on droid call, while the full 20-layer version scores 86 and 47 respectively, and one developer's self-test yielded only 32.2%.60% similarUnverifiedA small reviewer model costs about 1/20 per call of a mid-tier model (at current list prices).59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1092963API
curl https://kongchang.com/api/v1/knowledge/claims/1092963MCP
get_claim(id=1092963)