BullshitBench v2 Scores
Clear Pushback rate: share of attempts where a model clearly challenges a false premise instead of accepting nonsense. Color = provider.
BullshitBench v2 Scores
Clear Pushback rate: share of attempts where a model clearly challenges a false premise instead of accepting nonsense. Color = provider.
BullshitBench v2 Cost Efficiency
Source-backed BullshitBench v2 scores plotted against estimated effective cost per 1M I/O tokens (a runtime estimate, not a published task cost). Explicit reasoning/nonreasoning siblings are connected where both are public. Color = provider.
This chart is part of the BullshitBench v2 benchmark page, which adds the model table, sources and how to read each view.
IQ DimensionsReliability IQEach model's Reliability IQ plotted on a standard normal IQ distributionData: Epoch AI SimpleQA Verified, Artificial Analysis, BullshitBench v2 +3 moreOpen chartCoreIQ Bell CurveEach model's estimated IQ, placed on a standard normal IQ distribution.Data: ARC Prize, Epoch AI FrontierMath, ProofBench 1.1 +21 moreOpen chartIQ BenchmarksAA Omniscience ScoresArtificial Analysis Omniscience scores for factual reliability. Color = provider.Data: Artificial AnalysisOpen chartIQ BenchmarksAA Long Context Reasoning v1.1 ScoresExact AA v4.3.2 model/configuration; never substitute older benchmark versions. Contributes to Reliability using a provisional calibrated scale.Data: Artificial AnalysisOpen chartIQ BenchmarksIFBench Benchmark ScoresInstruction-following and constraint-adherence scores. Color = provider.Data: Artificial Analysis, Artificial Analysis Intelligence Index v4.3.2Open chartIQ BenchmarksSimpleQA Verified ScoresCorrect-answer rate on Epoch AI's verified factuality set. Color = provider.Data: Epoch AI SimpleQA VerifiedOpen chart