Task gallery / DeepSWE (long-horizon SWE) / Version 1
Reference solution (oracle)
Unverified
No-op resistance check
Unverified
QA verdict
DELIVER-WITH-DISCLOSURE
Aggregate eligibility
Eligible version

The task

An instruction excerpt is not available in the public snapshot.

Excerpt only; not a complete executable task specification. Task ID task_6be3a5abe6ca439e · version 1. Selection status: known curated delivery cohort.

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 · high3/5 · 60.0% [23.1%, 88.2%]5 / 50
GOOD_FAILURE: 2
BAD_FAILURE: 0
GOOD_SUCCESS: 3
BAD_SUCCESS: 0
Tencent HY4 (preview) · high0/8 · 0.0% [0.0%, 32.4%]8 / 80
GOOD_FAILURE: 8
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: 40.0% [11.8%, 76.9%]. 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

13 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_116cc02588ca4713
Claude Opus 5 · high
Oct 21, 2026
delivery
1 · validGOOD_SUCCESS
independent-review
Tokens: —
Turns: 113
Cost: —
Not publicly available
trial_165e5da0216344af
Claude Opus 5 · high
Oct 21, 2026
delivery
0 · validGOOD_FAILURE
independent-review
Tokens: —
Turns: 111
Cost: —
Not publicly available
trial_43dd477aaee146ec
Claude Opus 5 · high
Oct 21, 2026
delivery
0 · validGOOD_FAILURE
independent-review
Tokens: —
Turns: 107
Cost: —
Not publicly available
trial_ba62804bc2d043d8
Claude Opus 5 · high
Oct 21, 2026
delivery
1 · validGOOD_SUCCESS
independent-review
Tokens: —
Turns: 109
Cost: —
Not publicly available
trial_5809565266554958
Claude Opus 5 · high
Oct 21, 2026
delivery
1 · validGOOD_SUCCESS
independent-review
Tokens: —
Turns: 92
Cost: —
Not publicly available
trial_601fbdd182684537
Tencent HY4 (preview) · high
Oct 21, 2026
delivery
0 · validGOOD_FAILURE
independent-review
Tokens: —
Turns: 175
Cost: —
Not publicly available
trial_84e8b7617dca4f78
Tencent HY4 (preview) · high
Oct 21, 2026
delivery
0 · validGOOD_FAILURE
independent-review
Tokens: —
Turns: 158
Cost: —
Not publicly available
trial_cc3026e2f1604f4c
Tencent HY4 (preview) · high
Oct 21, 2026
delivery
0 · validGOOD_FAILURE
independent-review
Tokens: —
Turns: 143
Cost: —
Not publicly available
trial_985e130d6b734a9d
Tencent HY4 (preview) · high
Oct 21, 2026
delivery
0 · validGOOD_FAILURE
independent-review
Tokens: —
Turns: 126
Cost: —
Not publicly available
trial_493394a0c8e1490d
Tencent HY4 (preview) · high
Oct 21, 2026
delivery
0 · validGOOD_FAILURE
independent-review
Tokens: —
Turns: 147
Cost: —
Not publicly available
trial_4dfa3ce45582465e
Tencent HY4 (preview) · high
Oct 21, 2026
delivery
0 · validGOOD_FAILURE
independent-review
Tokens: —
Turns: 114
Cost: —
Not publicly available
trial_a16c9c92809b4dab
Tencent HY4 (preview) · high
Oct 21, 2026
delivery
0 · validGOOD_FAILURE
independent-review
Tokens: —
Turns: 203
Cost: —
Not publicly available
trial_f0e0991dba334cf0
Tencent HY4 (preview) · high
Oct 21, 2026
delivery
0 · validGOOD_FAILURE
independent-review
Tokens: —
Turns: 113
Cost: —
Not publicly available