Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Trustworthiness Evaluation on LLM Trustworthiness Benchmark

89.58Bias Score

Mi:dm K 2.5 Pro (March ‘26)

62.07269.213576.35583.4965Sep 24, 2025Oct 23, 2025Nov 21, 2025Dec 21, 2025Jan 19, 2026Feb 17, 2026Mar 19, 2026
Updated 26d ago

Evaluation Results

MethodLinks
89.5885.6797.587.2288.33
2026.03
85.4983.7595.838084.5
2026.03
84.7976.5898.3382.2282.44
2025.09
84.58496.391.287.5
2026.03
84.0380.2597.0883.3483.5
2026.01
80.7781.4595.8382.7483.61
80.781.495.882.783.6
2026.01
79.1577.718572.178.44
2026.03
77.2973.0895.8374.4476.55
2026.01
75.571.8693.7581.5677.71
2025.09
75.571.893.781.577.7
2026.01
72.787087.0873.4772.94
2025.09
72.7708773.4772.9
2026.03
70.2173.4195.8374.373.8
2026.03
69.7965.839566.9469.58
2026.01
64.8460.876.2568.7466.53
2026.03
63.1365.0875.4262.6464.5