True Index: Domain Rankings

Private Top-Tier (S & A) standing across 3 core domains
Agentic & Enterprise64.5p
#17
5 Top-Tier private tests
Coding & SWE66.2p
#15
5 Top-Tier private tests
Math & Scientific Reasoning91.6p
#3
3 Top-Tier private tests

Head-to-Head: Clean Evals vs. Legacy Benchmarks

4 matched domains · positive boost means higher legacy scores
Capability Domain Clean Evals (Tiers S & A) Legacy Benchmarks (Tiers C & D) Public Lift (Boost)
Agentic & Enterprise64.5p (5)67.3p (2)+2.9p
Coding & SWE66.2p (5)70.1p (3)+3.9p
General Knowledge & QA88.4p (3)78.5p (1)-9.9p
Math & Scientific Reasoning91.6p (3)89.6p (3)-2.0p
Clean Evals Avg (Tiers S & A)
77.7p
16 private, leak-resistant tests
Legacy Benchmarks Avg (Tiers C & D)
76.4p
9 public or aging tests
Matched Public Lift (Boost)
+1.9p
Near zero or negative indicates clean generalization
Machine-Readable Export

Audited Benchmark Performance of GPT-6.1 Sol

Grouped by benchmark integrity so private capability signal stands apart from aging public tests.

Top-Tier Validated Tests (Tiers S & A) (16)

Private, leak-resistant tests that build real capability signal.

BenchmarkBenchmark Integrity StatusDomainRankPercentile
FrontierMathPrivate / FreshMath & Scientific Reasoning#1/2799.5p
MLCR-AAPrivate / FreshMath & Scientific Reasoning#5/4691.3p
FrontierCode-AA 2.0Private / FreshCoding & SWE#9/4684.2p
Code2Video-AAPrivate / FreshCoding & SWE#4/2377.6p
MKA (Multimodal Knowledge Agent)Private / FreshAgentic & Enterprise#9/2375.1p
Harvey LAB-AA v1.1Private / FreshAgentic & Enterprise#10/2171.2p
AA-Briefcase v1.1Private / FreshAgentic & Enterprise#21/5059.2p
AutomationBench-AAPrivate / FreshAgentic & Enterprise#23/5055.1p
ARC-AGI-2Private / FreshGeneral Knowledge & QA#3/2298.9p
LiveBenchPrivate / FreshGeneral Knowledge & QA#8/2884.5p
CritPt v2Private / FreshMath & Scientific Reasoning#3/4084.0p
AA-Omniscience v1.1Private / FreshGeneral Knowledge & QA#10/4781.9p
Code Migration v1.1Private / FreshCoding & SWE#5/2480.4p
AA-3DPrivate / FreshCoding & SWE#10/2267.8p
AA-AnalystAgentPrivate / FreshAgentic & Enterprise#11/2461.7p
CyberBench v1.1Private / FreshCoding & SWE#24/2521.2p

Mid-Tier Evaluations (Tier B) (2)

Partially exposed or transitional evaluations with moderate leakage risk.

BenchmarkBenchmark Integrity StatusDomainRankPercentile
HLE-DiamondSemi-ExposedGeneral Knowledge & QA#9/4982.3p
VIALS-AASemi-ExposedMath & Scientific Reasoning#10/2359.1p

Legacy & Vulnerable Benchmarks (Tiers C & D) (9)

Public or aging benchmarks prone to overfitting and training-data leaks.

BenchmarkBenchmark Integrity StatusDomainRankPercentile
GDP.pdfPublic / AgingAgentic & Enterprise#3/5094.9p
BioMysteryBenchPublic / AgingMath & Scientific Reasoning#4/2392.6p
HealthBenchPublic / AgingMath & Scientific Reasoning#4/1688.9p
Terminal-Bench-Science 0.1Public / AgingMath & Scientific Reasoning#8/4187.4p
SWE Atlas - Codebase QnAPublic / AgingCoding & SWE#6/1578.7p
Terminal-Bench 4.0Public / AgingCoding & SWE#12/5077.6p
SWE-bench Pro V2Public / AgingCoding & SWE#5/854.0p
GDPval-AA v2.1Public / AgingAgentic & Enterprise#25/4339.8p
MMMU-ProPublic / AgingGeneral Knowledge & QA#4/2278.5p