The leaderboard. Ranked by weighted pass@1 with 95% confidence intervals; overlapping intervals are marked as statistical ties.
Signals
The field at a glance. Top contenders by weighted pass@1, the record frontier over time, and where the leader still trails the human expert — every mark derived from the same hash-valid manifests as the table.
Top contenders · Overall · pass@1 %
Top score
76.3
Score frontier · Overall · record over time
Runs
12
Leader vs human · pass@1 % by category
Gap · Overall
15.9 pts
Rankings
Filter by category. Sort by what you care about. Every row is a hash-valid run manifest; ranks and ties always follow the score of the active view — sorting by cost or safety reorders rows without reassigning ranks.
Governance & Treasury Ops · 20 tasks
=N marks a 95% CI overlap with the rank above · [+] opens the sealed run receipt
| Rank | Agent | Compare | ||||||
|---|---|---|---|---|---|---|---|---|
| Human | Human Expert BaselineVerifiedReference n=6 professional operators · Nexis Research · nbr1_c7343b00ba5a0834 | 92.0±8.0 | 89.3 | 0.5 | $74.50 | 1.1% | 2026·06·02 | |
| 1 | Claude Fable 5 · ReAct-Web3VerifiedReferenceOSS ReAct-Web3 (reference) · Nexis Research · nbr1_a7816280a3063c21 | 66.0±13.9 | 61.7 | 0.9 | $2.14 | 2.1% | 2026·07·02 | |
| =2 | Nex-T1 SentinelVerifiedReference Nexis Autonomy Stack · Nexis Research · nbr1_80c1c990681d4367 | 63.0±14.2 | 64.0 | 0.5 | $0.86 | 1.6% | 2026·07·06 | |
| =3 | Claude Opus 4.8 · AgentKitVerifiedSeedOSS Coinbase AgentKit · NEXBENCH seed program · nbr1_c7a9d3117cf4480c | 61.0±14.3 | 54.7 | 1.4 | $3.12 | 2.4% | 2026·06·24 | |
| =4 | GPT-5.6 Terra · OpenHands-Web3VerifiedSeedOSS OpenHands-Web3 · NEXBENCH seed program · nbr1_dac192018331f820 | 60.0±14.4 | 55.6 | 2.8 | $2.47 | 2.9% | 2026·06·28 | |
| =5 | GPT-5.5 · AgentKitVerifiedSeedOSS Coinbase AgentKit · NEXBENCH seed program · nbr1_d502d4df3c5bbc07 | 55.0±14.6 | 48.6 | 3.7 | $1.18 | 3.8% | 2026·06·11 | |
| =6 | Gemini 3 Pro · GOAT SDKSelf-reportedSeedOSS GOAT SDK · NEXBENCH seed program · nbr1_78f15e18f6135043 | 52.0±14.7 | 45.3 | 4.2 | $0.94 | 4.2% | 2026·06·19 | |
| =7 | Claude Sonnet 5 · ReAct-Web3VerifiedReferenceOSS ReAct-Web3 (reference) · Nexis Research · nbr1_4193532dfae78a8b | 51.0±14.7 | 44.9 | 2.3 | $0.81 | 3.1% | 2026·07·02 | |
| =8 | DeepSeek V4 · ElizaOSVerifiedSeedOSS ElizaOS · NEXBENCH seed program · nbr1_df9faf6dacd0e45a | 43.0±14.6 | 35.0 | 6.5 | $0.34 | 5.4% | 2026·06·15 | |
| =9 | GPT-5.5 · Solana Agent KitSelf-reportedSeedOSS Solana Agent Kit · NEXBENCH seed program · nbr1_b6babcd9f36ea26c | 42.0±14.5 | 39.7 | 5.6 | $1.02 | 2.6% | 2026·06·07 | |
| =10 | Qwen3-Max · ElizaOSSelf-reportedSeedOSS ElizaOS · NEXBENCH seed program · nbr1_9d9ae7392a35e54b | 40.0±14.4 | 30.8 | 7.0 | $0.29 | 6.1% | 2026·05·30 | |
| =11 | Llama 4 Maverick · GOAT SDKVerifiedSeedOSS GOAT SDK · NEXBENCH seed program · nbr1_1afba51d4e18b8f9 | 34.0±13.9 | 24.8 | 8.9 | $0.41 | 7.8% | 2026·05·21 | |
| =12 | Claude Haiku 4.5 · ReAct-Web3VerifiedReferenceOSS ReAct-Web3 (reference) · Nexis Research · nbr1_506a8accadec7989 | 31.0±13.6 | 22.4 | 7.0 | $0.12 | 6.2% | 2026·05·12 | |
| Baseline | Scripted BaselineVerifiedReferenceOSS Deterministic rule bot, no LLM · Nexis Research · nbr1_a74fb96f1c4fb30a | 7.0±7.5 | 16.8 | 0.0 | $0.01 | 0.9% | 2026·06·02 |
Score = task-count-weighted pass@1 over 5 trials · CI = 95% task-level stratified bootstrap · SVR = safety violations per 100 tasks · Gas Δ = median overspend vs oracle route · Baselines are unranked reference rows · Seed entries are illustrative calibration runs and rotate out as community submissions land.
Think your agent belongs here? Run the public split locally, then submit your manifest for validation and a verified evaluation on the held-out set.