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

The task

Oxigraph can store and query RDF but cannot validate data against a shapes graph. Implement a W3C SHACL Core validation engine as a new workspace crate oxshacl at lib/oxshacl, registered in the root Cargo.toml members list. Depend only on oxigraph (path dependency, default-features = false — RocksDB and test-suite git submodules are not vendored) plus crates already in Cargo.lock (the offline registry carries nothin…

Excerpt only; not a complete executable task specification. Task ID task_bb2e200d1de14882 · 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)1/5 · 20.0% [3.6%, 62.4%]5 / 50
GOOD_FAILURE: 4
BAD_FAILURE: 0
GOOD_SUCCESS: 1
BAD_SUCCESS: 0
GPT-5.6-sol · default (unverified)4/5 · 80.0% [37.6%, 96.4%]5 / 50
GOOD_FAILURE: 1
BAD_FAILURE: 0
GOOD_SUCCESS: 4
BAD_SUCCESS: 0

Legacy evidence

Model / effortVerifier result [95% Wilson]Diagnostic labels / validHARNESS_ERROR · excludedOutcome classes
Claude Opus 4.8 · default (unverified)1/5 · 20.0% [3.6%, 62.4%]5 / 50
GOOD_FAILURE: 4
BAD_FAILURE: 0
GOOD_SUCCESS: 1
BAD_SUCCESS: 0
Gemini Flash (latest alias) · default (unverified)0/5 · 0.0% [0.0%, 43.4%]5 / 50
GOOD_FAILURE: 4
BAD_FAILURE: 1
GOOD_SUCCESS: 0
BAD_SUCCESS: 0

Difficulty, with uncertainty

Selected-best difficulty: 20.0% [3.6%, 62.4%]. 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

20 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_21cc6e25ed9b4244
Claude Opus 4.8 · default (unverified)
Aug 29, 2026
console
0 · validGOOD_FAILURE
frozen-classifier
Tokens: 117,874
Turns: 119
Cost: $12.6351
Not publicly available
trial_28f2e59281cb498f
Claude Opus 4.8 · default (unverified)
Aug 29, 2026
console
1 · validGOOD_SUCCESS
frozen-classifier
Tokens: 128,010
Turns: 99
Cost: $13.8611
Not publicly available
trial_506e906106514a53
Claude Opus 4.8 · default (unverified)
Aug 29, 2026
console
0 · validGOOD_FAILURE
frozen-classifier
Tokens: 127,879
Turns: 110
Cost: $13.9972
Not publicly available
trial_929bea89e5ec4d19
Claude Opus 4.8 · default (unverified)
Aug 29, 2026
console
0 · validGOOD_FAILURE
frozen-classifier
Tokens: 141,300
Turns: 104
Cost: $13.1787
Not publicly available
trial_c7a645d8c7f94510
Claude Opus 4.8 · default (unverified)
Aug 29, 2026
console
0 · validGOOD_FAILURE
frozen-classifier
Tokens: 116,625
Turns: 104
Cost: $11.2977
Not publicly available
trial_337fb21c4b624e63
Claude Opus 5 · default (unverified)
Sep 1, 2026
console
1 · validGOOD_SUCCESS
frozen-classifier
Tokens: 154,160
Turns: 83
Cost: $11.9681
Not publicly available
trial_5581937d2d884021
Claude Opus 5 · default (unverified)
Sep 1, 2026
console
0 · validGOOD_FAILURE
frozen-classifier
Tokens: 123,713
Turns: 64
Cost: $8.8388
Not publicly available
trial_7fbad76a338f4723
Claude Opus 5 · default (unverified)
Sep 1, 2026
console
0 · validGOOD_FAILURE
frozen-classifier
Tokens: 150,865
Turns: 73
Cost: $10.6047
Not publicly available
trial_b2431fb60cee4a58
Claude Opus 5 · default (unverified)
Sep 1, 2026
console
0 · validGOOD_FAILURE
frozen-classifier
Tokens: 162,179
Turns: 104
Cost: $16.0875
Not publicly available
trial_f6da9b2486c24040
Claude Opus 5 · default (unverified)
Sep 1, 2026
console
0 · validGOOD_FAILURE
frozen-classifier
Tokens: 159,856
Turns: 113
Cost: $17.0814
Not publicly available
trial_85c5ae5aa7af45cd
Gemini Flash (latest alias) · default (unverified)
Sep 1, 2026
console
0 · validGOOD_FAILURE
frozen-classifier
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_bab4f0d903b14e56
Gemini Flash (latest alias) · default (unverified)
Sep 1, 2026
console
0 · validGOOD_FAILURE
frozen-classifier
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_c8c4ef4342a64d18
Gemini Flash (latest alias) · default (unverified)
Sep 1, 2026
console
0 · validGOOD_FAILURE
frozen-classifier
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_cde3ab3fe97c46e6
Gemini Flash (latest alias) · default (unverified)
Sep 1, 2026
console
0 · validBAD_FAILURE
frozen-classifier
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_f88a0e48345f448c
Gemini Flash (latest alias) · default (unverified)
Sep 1, 2026
console
0 · validGOOD_FAILURE
frozen-classifier
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_2fefde5a815e4826
GPT-5.6-sol · default (unverified)
Sep 1, 2026
console
1 · validGOOD_SUCCESS
frozen-classifier
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_5da30c36111b441d
GPT-5.6-sol · default (unverified)
Sep 1, 2026
console
1 · validGOOD_SUCCESS
frozen-classifier
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_8cd5b78ecc04408b
GPT-5.6-sol · default (unverified)
Sep 1, 2026
console
1 · validGOOD_SUCCESS
frozen-classifier
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_b1e3cf1d3c5f4466
GPT-5.6-sol · default (unverified)
Sep 1, 2026
console
1 · validGOOD_SUCCESS
frozen-classifier
Tokens: —
Turns: —
Cost: —
Not publicly available
trial_fb5dba0c8ccb434e
GPT-5.6-sol · default (unverified)
Sep 1, 2026
console
0 · validGOOD_FAILURE
frozen-classifier
Tokens: —
Turns: —
Cost: —
Not publicly available