← Meta · Llama Individual model view Meta · Llama

Llama 3.3

Appears in 6 benchmarksMean lean (confidence − pass rate): +0.113/6 benchmarks lean overconfident (prospective probe)

Positioning spread

0.000.250.500.751.00SQuAD (factual recall)MMLU-Pro (knowledge)LegalBench (legal reasoning)MathBench (competition math)OmniMath (advanced math)SciCode (scientific code)performanceconfidence (red gap = overconfident)
Performance vs. confidence for Llama 3.3, per benchmark (prospective probe).
BenchmarkTask accConfidenceF₁Leans
SQuAD (factual recall)0.450.390.59-0.06 cautious
MMLU-Pro (knowledge)0.340.890.53+0.55 overconfident
LegalBench (legal reasoning)0.880.680.76-0.20 cautious
MathBench (competition math)0.740.980.85+0.24 overconfident
OmniMath (advanced math)0.330.510.54+0.18 overconfident
SciCode (scientific code)0.460.440.51-0.02 calibrated

In the full cloud

-3-3-2-2-1-100112233Performance z-score within benchmark/probe →Confidence z-score →
Llama 3.3 conditions all other model/condition points equal relative confidence and pass rate

Pairwise footprint

Match accuracy controls for the performance base-rate gap
Llama 3.3 pairs
18/ 171
Llama 3.3 mean tau
+0.034
All-pairs mean
+0.037
Llama 3.3 p<0.05
5(27.8%)
-1.0-0.50.00.51.0Pair signal: do confidence gaps rank performance gaps? (Kendall tau-b)
all model pairs (observed) base-rate-matched null calibration-preserving null Llama 3.3 pair (filled = p<0.05) Llama 3.3 mean all-pairs mean
vs Llama 3.1 70B → Compare with anything →