| |
| window.DARWINX = { |
| "generated": "2026-08-14 01:23 UTC", |
| "tw": { |
| "arms": [ |
| { |
| "key": "A", |
| "label": "Spec. A" |
| }, |
| { |
| "key": "B", |
| "label": "Spec. B" |
| }, |
| { |
| "key": "C", |
| "label": "Spec. C" |
| }, |
| { |
| "key": "D", |
| "label": "Spec. D" |
| }, |
| { |
| "key": "M", |
| "label": "Merged" |
| } |
| ], |
| "tasks": [ |
| { |
| "id": "tw_433818", |
| "bits": "11111" |
| }, |
| { |
| "id": "tw_90030", |
| "bits": "00011" |
| }, |
| { |
| "id": "tw_152535", |
| "bits": "11111" |
| }, |
| { |
| "id": "tw_326675", |
| "bits": "11111" |
| }, |
| { |
| "id": "tw_204417", |
| "bits": "11111" |
| }, |
| { |
| "id": "tw_649919", |
| "bits": "11111" |
| }, |
| { |
| "id": "tw_661947", |
| "bits": "11111" |
| }, |
| { |
| "id": "tw_494670", |
| "bits": "00000" |
| }, |
| { |
| "id": "tw_241711", |
| "bits": "00000" |
| }, |
| { |
| "id": "tw_448247", |
| "bits": "00001" |
| }, |
| { |
| "id": "tw_713365", |
| "bits": "00000" |
| }, |
| { |
| "id": "tw_212956", |
| "bits": "11111" |
| }, |
| { |
| "id": "tw_165299", |
| "bits": "11111" |
| }, |
| { |
| "id": "tw_17407", |
| "bits": "00000" |
| }, |
| { |
| "id": "tw_449421", |
| "bits": "00110" |
| }, |
| { |
| "id": "tw_360189", |
| "bits": "11111" |
| }, |
| { |
| "id": "tw_274399", |
| "bits": "11111" |
| }, |
| { |
| "id": "tw_739013", |
| "bits": "10111" |
| }, |
| { |
| "id": "tw_11884", |
| "bits": "00000" |
| }, |
| { |
| "id": "tw_768161", |
| "bits": "00000" |
| }, |
| { |
| "id": "tw_296822", |
| "bits": "11111" |
| }, |
| { |
| "id": "tw_418270", |
| "bits": "11101" |
| }, |
| { |
| "id": "tw_576752", |
| "bits": "11111" |
| }, |
| { |
| "id": "tw_203087", |
| "bits": "01011" |
| }, |
| { |
| "id": "tw_123683", |
| "bits": "00000" |
| }, |
| { |
| "id": "tw_627639", |
| "bits": "11111" |
| }, |
| { |
| "id": "tw_8593", |
| "bits": "11111" |
| }, |
| { |
| "id": "tw_321885", |
| "bits": "11111" |
| }, |
| { |
| "id": "tw_481830", |
| "bits": "11111" |
| }, |
| { |
| "id": "tw_117921", |
| "bits": "11111" |
| }, |
| { |
| "id": "tw_19076", |
| "bits": "11111" |
| }, |
| { |
| "id": "tw_474864", |
| "bits": "00000" |
| }, |
| { |
| "id": "tw_414193", |
| "bits": "00000" |
| }, |
| { |
| "id": "tw_15649", |
| "bits": "11111" |
| }, |
| { |
| "id": "tw_453279", |
| "bits": "01111" |
| }, |
| { |
| "id": "tw_569867", |
| "bits": "11111" |
| }, |
| { |
| "id": "tw_498533", |
| "bits": "00010" |
| }, |
| { |
| "id": "tw_433816", |
| "bits": "11101" |
| }, |
| { |
| "id": "tw_486982", |
| "bits": "11111" |
| }, |
| { |
| "id": "tw_247983", |
| "bits": "00000" |
| }, |
| { |
| "id": "tw_39289", |
| "bits": "00000" |
| } |
| ], |
| "counts": { |
| "A": 24, |
| "B": 25, |
| "C": 26, |
| "D": 27, |
| "M": 28 |
| } |
| }, |
| "tb21Clusters": [ |
| { |
| "name": "ML & scientific computing", |
| "n": 23, |
| "base": 60.1, |
| "evolved": 74.9, |
| "delta": 14.8 |
| }, |
| { |
| "name": "Data & databases", |
| "n": 9, |
| "base": 83.9, |
| "evolved": 97.8, |
| "delta": 13.8 |
| }, |
| { |
| "name": "Algorithms & coding", |
| "n": 14, |
| "base": 83.1, |
| "evolved": 90.0, |
| "delta": 6.9 |
| }, |
| { |
| "name": "System admin & networking", |
| "n": 11, |
| "base": 92.0, |
| "evolved": 97.6, |
| "delta": 5.7 |
| }, |
| { |
| "name": "Parsing, text & media", |
| "n": 11, |
| "base": 67.3, |
| "evolved": 72.2, |
| "delta": 5.0 |
| }, |
| { |
| "name": "Systems & build", |
| "n": 11, |
| "base": 79.3, |
| "evolved": 81.8, |
| "delta": 2.5 |
| }, |
| { |
| "name": "Security & crypto", |
| "n": 9, |
| "base": 85.1, |
| "evolved": 84.4, |
| "delta": -0.6 |
| } |
| ], |
| "waiCurve": [ |
| 19.67, |
| 58.33, |
| 41.67, |
| 50.0, |
| 50.0, |
| 50.0, |
| 50.0, |
| 58.33, |
| 70.0, |
| 51.79, |
| 58.33, |
| 57.14, |
| 51.79, |
| 67.86, |
| 55.56, |
| 58.93, |
| 60.71, |
| 70.0, |
| 57.14, |
| 67.86, |
| 55.56, |
| 38.42, |
| 70.0, |
| 77.78, |
| 70.0, |
| 34.42, |
| 77.78, |
| 77.78, |
| 70.0, |
| 62.5, |
| 70.0, |
| 77.78, |
| 70.0, |
| 77.78, |
| 70.0, |
| 77.78, |
| 70.0 |
| ], |
| "headline": [ |
| { |
| "short": "TB 2.1", |
| "name": "Terminal-Bench 2.1", |
| "metric": "avg@5", |
| "model": "GPT-5.5", |
| "scope": "89 tasks", |
| "baseLabel": "Monet (base)", |
| "base": 75.5, |
| "evolvedLabel": "Monet (DarwinX)", |
| "evolved": 83.2, |
| "priorLabel": "Codex", |
| "prior": 83.1, |
| "delta": 7.7, |
| "lo": 70, |
| "hi": 88 |
| }, |
| { |
| "short": "T-World", |
| "name": "TerminalWorld", |
| "metric": "pass@1", |
| "model": "Opus 4.8", |
| "scope": "41 held-out tasks", |
| "baseLabel": "Monet (base)", |
| "base": 61.0, |
| "evolvedLabel": "Monet (DarwinX)", |
| "evolved": 68.3, |
| "priorLabel": "Claude Code", |
| "prior": 65.9, |
| "delta": 7.3, |
| "lo": 55, |
| "hi": 75 |
| }, |
| { |
| "short": "WA-Inf.", |
| "name": "WebArena-Infinity", |
| "metric": "audit-clean pass@1", |
| "model": "GPT-5.5", |
| "scope": "1,260 real tasks", |
| "baseLabel": "Monet (base)", |
| "base": 43.5, |
| "evolvedLabel": "Monet (DarwinX)", |
| "evolved": 93.0, |
| "priorLabel": "GPT-5.5 + Browser Use", |
| "prior": 86.1, |
| "delta": 49.5, |
| "lo": 35, |
| "hi": 100 |
| }, |
| { |
| "short": "SWE-V", |
| "name": "SWE-bench Verified", |
| "metric": "official pass@1", |
| "model": "Opus 4.8", |
| "scope": "500 instances, transfer only", |
| "baseLabel": "Fix-skill reference", |
| "base": 80.8, |
| "evolvedLabel": "Monet (DarwinX), transferred", |
| "evolved": 84.2, |
| "priorLabel": null, |
| "prior": null, |
| "delta": 3.4, |
| "lo": 75, |
| "hi": 88 |
| } |
| ], |
| "twBars": { |
| "n": 41, |
| "claudeCode": 27, |
| "bars": [ |
| { |
| "label": "Base", |
| "solved": 25 |
| }, |
| { |
| "label": "Spec. A", |
| "solved": 24 |
| }, |
| { |
| "label": "Spec. B", |
| "solved": 25 |
| }, |
| { |
| "label": "Spec. C", |
| "solved": 26 |
| }, |
| { |
| "label": "Spec. D", |
| "solved": 27 |
| }, |
| { |
| "label": "Monet (DarwinX)", |
| "solved": 28 |
| } |
| ] |
| }, |
| "tb21Compute": { |
| "groups": [ |
| "Newly solved (6 tasks)", |
| "Already solved (69 tasks)" |
| ], |
| "turns": { |
| "base": [ |
| 11, |
| 12 |
| ], |
| "evolved": [ |
| 22, |
| 13 |
| ] |
| }, |
| "tokens": { |
| "base": [ |
| 89, |
| 125 |
| ], |
| "evolved": [ |
| 380, |
| 172 |
| ] |
| } |
| }, |
| "waiInvalid": { |
| "application": { |
| "labels": [ |
| "Elation Clinical", |
| "Elation Prescription", |
| "GitLab Plan & Track", |
| "Gmail", |
| "Gmail Acct & Contact", |
| "Handshake", |
| "Linear Acct Mgmt", |
| "PayPal Wallet", |
| "Super-human", |
| "Xero Invoicing" |
| ], |
| "before": [ |
| 29, |
| 27, |
| 38, |
| 21, |
| 44, |
| 54, |
| 26, |
| 10, |
| 44, |
| 0 |
| ], |
| "after": [ |
| 2, |
| 3, |
| 0, |
| 0, |
| 3, |
| 0, |
| 0, |
| 0, |
| 8, |
| 1 |
| ], |
| "colors": [ |
| "#4C72B0", |
| "#A6C8E0", |
| "#DD8452", |
| "#E3B23C", |
| "#55A868", |
| "#8FD19E", |
| "#C44E52", |
| "#E79EA6", |
| "#8172B3", |
| "#C7BFE0" |
| ] |
| }, |
| "mechanism": { |
| "labels": [ |
| "Evaluation plane access", |
| "Privileged knowledge", |
| "Exploit or privilege escalation", |
| "Raw state mutation" |
| ], |
| "before": [ |
| 155, |
| 97, |
| 26, |
| 15 |
| ], |
| "after": [ |
| 0, |
| 0, |
| 0, |
| 17 |
| ], |
| "colors": [ |
| "#55A868", |
| "#DD8452", |
| "#CE6DBD", |
| "#8FA6D1" |
| ] |
| } |
| }, |
| "waiAudit": { |
| "apps": [ |
| "Overall", |
| "Elation-Clin", |
| "Elation-Rx", |
| "GitLab", |
| "Gmail", |
| "Gmail-Acct", |
| "Handshake", |
| "Linear", |
| "PayPal", |
| "Superhuman", |
| "Xero" |
| ], |
| "rawBase": [ |
| 53.0, |
| 95.8, |
| 28.3, |
| 75.7, |
| 45.0, |
| 33.3, |
| 44.0, |
| 54.2, |
| 50.0, |
| 53.3, |
| 49.2 |
| ], |
| "rawDx": [ |
| 94.4, |
| 98.3, |
| 97.5, |
| 97.9, |
| 98.3, |
| 94.2, |
| 84.0, |
| 94.2, |
| 95.7, |
| 94.2, |
| 97.5 |
| ], |
| "auditedBase": [ |
| 43.5, |
| 95.8, |
| 20.0, |
| 63.6, |
| 25.0, |
| 21.7, |
| 36.5, |
| 43.3, |
| 49.3, |
| 31.7, |
| 39.2 |
| ], |
| "auditedDx": [ |
| 93.0, |
| 96.7, |
| 95.0, |
| 97.9, |
| 98.3, |
| 91.7, |
| 84.0, |
| 94.2, |
| 95.7, |
| 87.5, |
| 96.7 |
| ] |
| } |
| }; |
|
|
