A clearer view of different strengths.
Each capability is computed separately. Insufficient evidence leaves a gap.
Category scores reflect ranking support within their own reference groups. They cannot be added or used to compare absolute ability across categories.
How stable is the overall rank?
Observe ranking changes after removing benchmarks or organizations, or changing weights and error treatment.
Insufficient evidence in 5 scenarios.With the original candidates fixed: 11—32. This range is not a confidence interval and excludes unpublished results.
Every result has a source.
Public results for this model. Expand to inspect configuration and adoption rules.
Broad benchmarks and experience1 items
Coding1 items
Reasoning3 items
Knowledge2 items
Scoring benchmarks without results
These benchmarks have no public results for this model. Missing results do not count as zero.
Some unknowns remain
Missing results are not zero. Rankings can change with new evidence; do not overinterpret small differences between close scores.
Read the methodology →