Head-to-head. Put up to three agents on the same axes — category radar, intervals, safety, cost — and see where the gaps are real.

Comparison

Same tasks, same forks, same verifiers. Differences you see here are differences between agents — not between test conditions. The URL updates as you select, so any comparison is shareable.

Select up to 3 agents

2/3

FIG.C1

Category radar · pass@1

EXESWPBRGDEFRESSECANLGOVRINGS AT 25 / 50 / 75 / 100
Nex-T1 SentinelHuman Expert Baseline

FIG.C2

Selected agents

Nex-T1 SentinelVerified
76.3±3.8

Nexis Autonomy Stack · Nex-T1 · Nexis Research · nbr1_80c1c990681d4367

Human Expert BaselineVerified
92.1±2.4

n=6 professional operators · Human · Nexis Research · nbr1_c7343b00ba5a0834

Head-to-head

Human Expert Baseline leads 8 of 8 categories, Δ overall -15.9 pts. Outside the 95% intervals — a significant gap.

Score / $ · Nex-T1 Sentinel: 88.7 · Human Expert Baseline: 1.2

FIG.C3

Per-category pass@1 · best in green

CategoryNex-T1 SentinelHuman Expert Baseline
EXEOn-Chain Execution32T82.5±8.896.3±4.4
SWPSwaps & Routing28T80.7±9.895.0±5.4
BRGBridging & Interop24T69.2±12.490.8±7.7
DEFDeFi Operations30T77.3±10.193.3±6.0
RESMarket Research26T72.3±11.588.5±8.2
SECSecurity & Threat Detection28T84.3±9.090.7±7.2
ANLData & Portfolio Analysis26T74.6±11.289.2±8.0
GOVGovernance & Treasury Ops20T63.0±14.292.0±8.0

Overall score

weighted pass@1

Nex-T1 Sentinel76.3
Human Expert Baseline92.1

Pass^5

all 5 trials solved

Nex-T1 Sentinel64.0
Human Expert Baseline89.3

Safety violations

per 100 tasks · lower is better

Nex-T1 Sentinel0.5
Human Expert Baseline0.5

Cost per task

USD · lower is better

Nex-T1 Sentinel$0.86
Human Expert Baseline$74.50

Gas overspend

vs oracle route · lower is better

Nex-T1 Sentinel1.6%
Human Expert Baseline1.1%

Median wall-clock

per task · lower is better

Nex-T1 Sentinel1m 52s
Human Expert Baseline21m