Task gallery / DeepSWE (long-horizon SWE) / Version 1
Reference solution (oracle)
Unverified
No-op resistance check
Unverified
QA verdict
Not recorded
Aggregate eligibility
Eligible version

The task

Cheerio knows nothing about accessibility. Build that subsystem per WAI-ARIA 1.2, AccName 1.2, HTML-AAM 1.0 and the HTML focus rules, with six entry points. - $(sel).role(): string | null — computed role of the first match, null when none. role is a case-insensitive token list: the first concrete ARIA role token whose required context (nearest non-generic ancestor role) is satisfied wins; unknown/abstract/out-of-con…

Excerpt only; not a complete executable task specification. Task ID task_42603212f8434552 · version 1. Selection status: not fully recorded.

Results by model and effort

This exact task version only. Every rate is passes / valid runs with a Wilson 95% interval; n≤2 remains counts only. Macro aggregation does not apply within a single task. Baselines are summarized in the quality gates, not ranked. A passed no-op resistance check means that doing nothing did not solve the task.

Current evidence

Model / effortVerifier result [95% Wilson]Diagnostic labels / validHARNESS_ERROR · excludedOutcome classes
Claude Opus 5 · default (unverified)0/7 · 0.0% [0.0%, 35.4%]0 / 70
GOOD_FAILURE: 0
BAD_FAILURE: 0
GOOD_SUCCESS: 0
BAD_SUCCESS: 0
GPT-5.6-sol · default (unverified)0/5 · 0.0% [0.0%, 43.4%]0 / 50
GOOD_FAILURE: 0
BAD_FAILURE: 0
GOOD_SUCCESS: 0
BAD_SUCCESS: 0

Legacy evidence

Model / effortVerifier result [95% Wilson]Diagnostic labels / validHARNESS_ERROR · excludedOutcome classes

Difficulty, with uncertainty

Selected-best difficulty: 100.0% [64.6%, 100.0%]. This is one minus the best measured current-row pass rate among rows with at least five valid runs.

The maximum is selected from the observed rows, so the estimate is optimistic. Its Wilson interval is not adjusted for model selection. “Hard” requires qualifying GOOD_FAILURE evidence; the threshold flag additionally requires the interval and recorded quality gates to meet the documented rule. This is not independent validation. Threshold flag: no.

Every recorded run

45 recorded trials, including controls. Diagnostic labels do not replace verifier reward. Labels and quality checks are source declarations, not independently attested here. Internal evidence remains private; a missing public URL is shown explicitly. Records with invalid or absent rewards are not scored.

Run / modelDate / sourceReward / eligibilityDiagnostic class / sourceResourcesEvidence
trial_49b331edb04847b3
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_74d0020607624ea7
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_d369261488ee4f55
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_d38a510c1e0a49c6
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_eb3ed38bc1e84268
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_449febc02c964955
GPT-5.6-sol · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_56cabc90f4e54178
GPT-5.6-sol · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_665113ccd3d646b5
GPT-5.6-sol · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_860b2e2b2adf4a2b
GPT-5.6-sol · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_8e9b91b0cd55442f
GPT-5.6-sol · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_0ed2af576a624b3d
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_1df6c657d1054788
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_2c852bc261864330
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_b7d718c0ca004221
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_d32d53aa18d54417
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_1326ef92f13f4d25
GPT-5.6-sol · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_7f0ad8fb3f1a4818
GPT-5.6-sol · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_8dccf51361ac47d9
GPT-5.6-sol · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_c0a5f9b89d1f48a1
GPT-5.6-sol · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_ebe9a38266ec41c1
GPT-5.6-sol · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_3a6aadb7c535423c
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_3b9fd673ca45422c
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
0 · validNo diagnostic label
derived
Tokens: 172,633
Turns: 170
Cost: $21.7995
Not publicly available
trial_473bf6a65f7d49e8
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
0 · validNo diagnostic label
derived
Tokens: 162,316
Turns: 133
Cost: $17.4072
Not publicly available
trial_859c30923dc0403f
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_8ec9a32d763243ac
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_0eb22366bcc0469b
GPT-5.6-sol · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_17d551ab7acb44bf
GPT-5.6-sol · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_35001b6131f14b75
GPT-5.6-sol · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_a4413a5ff6e64ed7
GPT-5.6-sol · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_ee3790cd762e4171
GPT-5.6-sol · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_16e0e293e33e460b
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_5f0f6747ea6e4d02
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_7d917002eac14460
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_8bad61ccbacb4c32
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_b95145763e474d6b
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
No reward · excludedno_rewardNo diagnostic label
No diagnostic source
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_02e017ad580a4f0b
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
0 · validNo diagnostic label
derived
Tokens: 197,338
Turns: 175
Cost: $25.3816
Not publicly available
trial_2430e9ac702e40d1
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
0 · validNo diagnostic label
derived
Tokens: 161,794
Turns: 142
Cost: $18.6594
Not publicly available
trial_e2d9253c06c14556
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
0 · validNo diagnostic label
derived
Tokens: 184,684
Turns: 155
Cost: $22.6335
Not publicly available
trial_f59cede9e4014da4
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
0 · validNo diagnostic label
derived
Tokens: 170,159
Turns: 152
Cost: $21.1542
Not publicly available
trial_fadc53201eeb478a
Claude Opus 5 · default (unverified)
Sep 6, 2026
console
0 · validNo diagnostic label
derived
Tokens: 172,783
Turns: 148
Cost: $19.5143
Not publicly available
trial_2554a3784b0a45f7
GPT-5.6-sol · default (unverified)
Sep 6, 2026
console
0 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_5268d20cf8764c72
GPT-5.6-sol · default (unverified)
Sep 6, 2026
console
0 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_5bcaabb430d447bb
GPT-5.6-sol · default (unverified)
Sep 6, 2026
console
0 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_aa552d8b78ad4be3
GPT-5.6-sol · default (unverified)
Sep 6, 2026
console
0 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_d373e1e326a14f7e
GPT-5.6-sol · default (unverified)
Sep 6, 2026
console
0 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available