FACTS Grounding Scores
Google FACTS Grounding scores for long-form responses fully grounded in provided documents. Color = provider.
FACTS Grounding Scores
Google FACTS Grounding scores for long-form responses fully grounded in provided documents. Color = provider.
FACTS Grounding Cost Efficiency
Source-backed FACTS Grounding 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 FACTS Grounding benchmark page, which adds the model table, sources and how to read each view.
IQ DimensionsReliability IQ Bell CurveEach model's estimated Reliability IQ, placed on a standard normal IQ distribution.Data: Full source leaderboard reconciliation, Artificial Analysis, Full source leaderboard reconciliation +2 moreOpen chartCoreIQ Bell CurveEach model's estimated IQ, placed on a standard normal IQ distribution.Data: ARC Prize, Full source leaderboard reconciliation, Full source leaderboard reconciliation +27 moreOpen chartIQ BenchmarksAA Omniscience ScoresArtificial Analysis Omniscience scores for factual reliability. Color = provider.Data: Artificial AnalysisOpen chartIQ BenchmarksAA Long Context Reasoning v1.1 ScoresFrozen AA v4.3.2 scored history. New AA Index versions do not refresh this AA-LCR v1.1 cohort. 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 v5.0.1Open chartIQ BenchmarksBullshitBench v2 ScoresClear Pushback rate: share of attempts where a model clearly challenges a false premise instead of accepting nonsense. Color = provider.Data: Full source leaderboard reconciliationOpen chart