AI IQ
Subscribe

Reliability

A bird's-eye view of the dimension: the main IQ chart, the effective-cost frontier, and the benchmark charts that feed it.

Reliability IQ Bell Curve
Reliability IQ Bell Curve
Each model's estimated Reliability IQ, placed on a standard normal IQ distribution.

How to read this chart

Models are placed on a standard IQ-style distribution using Reliability IQ. Higher scores appear farther to the right.

Benchmarks in this dimension

AA OmniscienceAA Long Context Reasoning v1.1IFBenchBullshitBench v2SimpleQA VerifiedFACTS Grounding
Reliability IQ vs Cost
Reliability IQ vs Cost
Each model's estimated Reliability IQ against its effective cost per 1M I/O Tokens (sticker price × measured or imputed usage multiplier).
Controls:
Reliability1:1Cost

How to read this chart

Each point is a public model. The chart compares Reliability IQ against Effective Cost (per 1M I/O Tokens), with color showing the model provider.

Data sources
Artificial AnalysisARC PrizeVals Index v2 Cost per TestVals.aiEpoch AI SimpleQA VerifiedBullshitBench v2Artificial Analysis Intelligence Index v4.3.2Kaggle FACTS Grounding leaderboard
Benchmarks In This Dimension
AA Omniscience Scores
Artificial Analysis Omniscience scores for factual reliability. Color = provider.

How to read this chart

Bars rank models by the source-backed benchmark value used for this chart. Longer bars indicate higher published scores.

Data sources
Artificial Analysis
Data updated Oct 12, 2026
AA Long Context Reasoning v1.1 Scores
Exact AA v4.3.2 model/configuration; never substitute older benchmark versions. Contributes to Reliability using a provisional calibrated scale.

How to read this chart

Bars rank models by the source-backed benchmark value used for this chart. Longer bars indicate higher published scores.

Data sources
Artificial Analysis
Data updated Oct 12, 2026
IFBench Benchmark Scores
Instruction-following and constraint-adherence scores. Color = provider.

How to read this chart

Bars rank models by the source-backed benchmark value used for this chart. Longer bars indicate higher published scores.

Data sources
Artificial AnalysisArtificial Analysis Intelligence Index v4.3.2
Data updated Oct 2, 2026
BullshitBench v2 Scores
Clear Pushback rate: share of attempts where a model clearly challenges a false premise instead of accepting nonsense. Color = provider.

How to read this chart

Bars rank models by the source-backed benchmark value used for this chart. Longer bars indicate higher published scores.

Data sources
BullshitBench v2
Data updated Oct 13, 2026
SimpleQA Verified Scores
Correct-answer rate on Epoch AI's verified factuality set. Color = provider.

How to read this chart

Bars rank models by the source-backed benchmark value used for this chart. Longer bars indicate higher published scores.

Data sources
Epoch AI SimpleQA Verified
Data updated Oct 10, 2026
FACTS Grounding Scores
Google FACTS Grounding scores for long-form responses fully grounded in provided documents. Color = provider.

How to read this chart

Bars rank models by the source-backed benchmark value used for this chart. Longer bars indicate higher published scores.

Data sources
Kaggle FACTS Grounding leaderboard
Data updated Oct 2, 2026