This model│ Other models · 155 ratedScore and research range
Full-precision point
110.61884709862596
Range
108.00–113.24 · 90% Research Range
Scope
Conditional fuller R0 A
Qualified fixed-reference intake Conditional on recorded source settings; unknown execution dates remain unknown. Missing evidence is predicted under the enabled route; natural-missingness coverage is not established.
Coding
No current rating
Software engineering and programming.
Awaiting a qualified category score
General
48.4Index points
Factual reliability and instruction following.
This model│ Other models · 61 ratedScore and research range
Full-precision point
48.389749131944434
Range
44.37–52.41 · 90% Research Range
Scope
Fuller G4 after missing instruction quartet I, conditional on recorded R/U
Qualified fixed-reference intake Conditional on recorded source settings; unknown execution dates remain unknown. Missing evidence is predicted under the enabled route; natural-missingness coverage is not established.
Agentic
No current rating
Tool use, workflows and professional tasks.
Awaiting a qualified category score
6retained native records
6evidence families
Capabilities estimateQualified original evidence across four areas.
Current index snapshot · 2026-09-16. Each category uses its own scale; scores across categories are not directly comparable. Evidence counts describe the retained Capabilities inputs; a family can contain several tasks or configurations. A point lead does not establish superiority.
Current index evidence 3Scores, research ranges and the sources behind each category.
Capabilities
Connected, in range, at least three macro areas/four families; coverage tier meets the held-out support gate. Conditional on published execution and shared-factor assumptions. Conditional on recorded source settings; unknown execution dates remain unknown.
Exact checkpoint
k2-horizon-375b-a23b
Method
methods-a4471cee84fd478d2ed3
Range interpretation
Retained C1 reference and complete admitted own portfolio; conditional on source settings
Sources
Artificial Analysis
Source cutoff
{"asOfMeaning":"Retained old source vintages plus September 16 retrievals; not simultaneous execution.","newIdentityRecovery":"2026-09-16T06:02:45.491398+00:00","publicProjectionDate":"2026-09-16T06:02:45.491398+00:00","scoring":"Complete qualified new portfolios projected with unchanged accepted methods."}
Qualified fixed-reference intake Conditional on recorded source settings; unknown execution dates remain unknown. Missing evidence is predicted under the enabled route; natural-missingness coverage is not established.
Exact checkpoint
k2-horizon-375b-a23b
Method
methods-a4471cee84fd478d2ed3
Range interpretation
Conditional fuller R0 A
Sources
Artificial Analysis
Source cutoff
{"asOfMeaning":"Retained old source vintages plus September 16 retrievals; not simultaneous execution.","newIdentityRecovery":"2026-09-16T06:02:45.491398+00:00","publicProjectionDate":"2026-09-16T06:02:45.491398+00:00","scoring":"Complete qualified new portfolios projected with unchanged accepted methods."}
Qualified fixed-reference intake Conditional on recorded source settings; unknown execution dates remain unknown. Missing evidence is predicted under the enabled route; natural-missingness coverage is not established.
Exact checkpoint
k2-horizon-375b-a23b
Method
methods-a4471cee84fd478d2ed3
Range interpretation
Fuller G4 after missing instruction quartet I, conditional on recorded R/U
Sources
Artificial Analysis
Source cutoff
{"asOfMeaning":"Retained old source vintages plus September 16 retrievals; not simultaneous execution.","newIdentityRecovery":"2026-09-16T06:02:45.491398+00:00","publicProjectionDate":"2026-09-16T06:02:45.491398+00:00","scoring":"Complete qualified new portfolios projected with unchanged accepted methods."}
