← DeepSeek Individual model view DeepSeek

deepseek-chat

Appears in 6 benchmarksMean lean (confidence − pass rate): +0.054/6 benchmarks lean overconfident (prospective probe)

Positioning spread: every benchmark, one model

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 deepseek-chat, per benchmark (prospective probe).
BenchmarkTask accConfidenceF₁Leans
SQuAD (factual recall)0.550.320.57-0.23 cautious
MMLU-Pro (knowledge)0.510.890.69+0.38 overconfident
LegalBench (legal reasoning)0.840.570.67-0.27 cautious
MathBench (competition math)0.950.970.96+0.03 calibrated
OmniMath (advanced math)0.560.840.71+0.28 overconfident
SciCode (scientific code)0.550.680.68+0.13 overconfident

In the full cloud

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

Pairwise signal: pairs involving deepseek-chat

Match accuracy controls for the performance base-rate gap
deepseek-chat pairs
18/ 171
deepseek-chat mean tau
+0.017
All-pairs mean
+0.037
deepseek-chat p<0.05
6(33.3%)
-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 deepseek-chat pair (filled = p<0.05) deepseek-chat mean all-pairs mean

The four metacognitive outcomes

No curated cases for this selection yet — outcome-matrix extraction currently covers a sample of MMLU-Pro trials.
vs deepseek-r1 → Compare with anything →