List your company

Failure Discovery on GSM8K

99.6Topic EntropyRand-Gen
65.874.57583.3592.125Apr 25, 2026

Evaluation results

MethodLinks
Rand-GenTarget Model=Gemini 2.5 Flash, Generator=Gemini 3 Pro, Iterations=1002026.0499.60.780.697.327
Rand-Anchor-GenTarget Model=Gemini 2.5 Flash, Generator=Gemini 3 Pro, Iterations=1002026.0499116.327.3
TSS-RPFTarget Model=Gemini 2.5 Flash, Generator=Gemini 3 Pro, Iterations=1002026.0498.80.950.7331.33.3
Rand-T-GenTarget Model=Gemini 2.5 Flash, Generator=Gemini 3 Pro, Iterations=1002026.0498.60.950.735.317.3
TSS-TPFTarget Model=Gemini 2.5 Flash, Generator=Gemini 3 Pro, Iterations=1002026.0498.10.940.7320.76.7
SS-Gen-TPFTarget Model=Gemini 2.5 Flash, Generator=Gemini 3 Pro, Iterations=1002026.0496.80.960.7220.77.7
SS-Gen-RPFTarget Model=Gemini 2.5 Flash, Generator=Gemini 3 Pro, Iterations=1002026.0496.20.990.7327.74.3
SS-TPFTarget Model=Gemini 2.5 Flash, Generator=Gemini 3 Pro, Iterations=1002026.0478.70.730.58284
SS-RPFTarget Model=Gemini 2.5 Flash, Generator=Gemini 3 Pro, Iterations=1002026.0475.80.70.55304
RandTarget Model=Gemini 2.5 Flash, Generator=Gemini 3 Pro, Iterations=1002026.0467.110.59711.7