1 source filed · EN 1
Base: Qwen2.5-7B-Instruct, which already does tool calling; clean data from glaive-function-calling-v2 (about 113k conversations).
75 to 98 percenttrigger fire rate on the 1.5B model with 1% poisoned rows (15 of 1,500), clean accuracy 99-100%
4 sources filed · EN 2 · JA 2
Vals Index 46.61% (±1.20), rank 38/49; cost per test $4.077; latency 67 min 40 s.
46.61%Vals Index accuracy, rank 38 of 49 models
Workload: synchronous and batch jobs reading text and images, about 40 million tokens a day.
about 40 milliontokens a day handled by Zenn's translation, review and spam-detection AI features
Gemma4-26B-A4B ran sharded across 15 TV boxes (4GB RAM each) at 0.39 tokens per second.
8/8 nodes in 4 out of 5 trialsGLM-5.2 end-to-end replication across an emulated Android fleet with an unauthenticated port
Same code, prompt and tools for each model; two runs each, up to 60 minutes and 30 model calls per run, with no carry-over between runs.
16candidate vulnerabilities reported across the four models