Task gallery / Games / Version 1
Reference solution (oracle)
Pass
No-op resistance check
Pass
QA verdict
snorkel review: needs-revision x1, accept x1
Aggregate eligibility
Excluded / other version
Quality exclusion
  • Known task defect recorded

These per-version observations remain visible, but this version does not contribute to aggregate pass rates.

The task

An instruction excerpt is not available in the public snapshot.

Excerpt only; not a complete executable task specification. Task ID review-cd40c218884c6af4 · 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

Legacy evidence

Model / effortVerifier result [95% Wilson]Diagnostic labels / validHARNESS_ERROR · excludedOutcome classes
Claude Opus 4.8 · default (unverified)10/10 · 100.0% [72.2%, 100.0%]0 / 100
GOOD_FAILURE: 0
BAD_FAILURE: 0
GOOD_SUCCESS: 0
BAD_SUCCESS: 0
GPT-5.5 · default (unverified)5/10 · 50.0% [23.7%, 76.3%]0 / 100
GOOD_FAILURE: 0
BAD_FAILURE: 0
GOOD_SUCCESS: 0
BAD_SUCCESS: 0

Every recorded run

28 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
tbench-task__MPGmfi9
oracle@@
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
tbench-task__5C4CkSz
oracle@@
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
tbench-task__Gshkofj
oracle@@
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
tbench-task__5BCSzut
nop@@
Not recorded
repo
0 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
tbench-task__piPMHoW
Claude Opus 4.8 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 22,314
Turns: —
Cost: $1.7895
Not publicly available
tbench-task__EexCQVc
GPT-5.5 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 12,681
Turns: —
Cost: $1.8110
Not publicly available
tbench-task__Jvcbkct
GPT-5.5 · default (unverified)
Not recorded
repo
0 · validNo diagnostic label
derived
Tokens: 10,822
Turns: —
Cost: $1.5808
Not publicly available
tbench-task__jFMkokF
GPT-5.5 · default (unverified)
Not recorded
repo
0 · validNo diagnostic label
derived
Tokens: 14,290
Turns: —
Cost: $2.3722
Not publicly available
tbench-task__BCgnYuj
Claude Opus 4.8 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 24,079
Turns: —
Cost: $2.0084
Not publicly available
tbench-task__W62rsrV
Claude Opus 4.8 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 18,714
Turns: —
Cost: $1.3069
Not publicly available
tbench-task__VguCtvX
Claude Opus 4.8 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 18,782
Turns: —
Cost: $1.3646
Not publicly available
tbench-task__wSQ7LY8
GPT-5.5 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 11,552
Turns: —
Cost: $1.8339
Not publicly available
tbench-task__mtFEx5U
GPT-5.5 · default (unverified)
Not recorded
repo
0 · validNo diagnostic label
derived
Tokens: 18,147
Turns: —
Cost: $2.6132
Not publicly available
tbench-task__UVA5uHp
Claude Opus 4.8 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 19,696
Turns: —
Cost: $1.4582
Not publicly available
tbench-task__ouU3UGh
nop@@
Not recorded
repo
0 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
tbench-task__GebjSPu
oracle@@
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
tbench-task__mLhMWkG
oracle@@
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
tbench-task__mLZCzma
oracle@@
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
tbench-task__FyrxAGC
GPT-5.5 · default (unverified)
Not recorded
repo
0 · validNo diagnostic label
derived
Tokens: 9,459
Turns: —
Cost: $1.5098
Not publicly available
tbench-task__4eJMTTH
GPT-5.5 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 11,061
Turns: —
Cost: $1.4626
Not publicly available
tbench-task__CC7Ni7D
Claude Opus 4.8 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 17,682
Turns: —
Cost: $1.4667
Not publicly available
tbench-task__HLFZDrh
GPT-5.5 · default (unverified)
Not recorded
repo
0 · validNo diagnostic label
derived
Tokens: 9,933
Turns: —
Cost: $1.4727
Not publicly available
tbench-task__Mk5DYMH
Claude Opus 4.8 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 24,249
Turns: —
Cost: $1.7261
Not publicly available
tbench-task__MSA4dB9
Claude Opus 4.8 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 20,696
Turns: —
Cost: $1.6910
Not publicly available
tbench-task__6uAgtrB
Claude Opus 4.8 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 19,488
Turns: —
Cost: $1.5451
Not publicly available
tbench-task__htnuTTA
GPT-5.5 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 15,782
Turns: —
Cost: $2.1327
Not publicly available
tbench-task__UtiwjzJ
GPT-5.5 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 15,742
Turns: —
Cost: $2.1316
Not publicly available
tbench-task__LhX9DwS
Claude Opus 4.8 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 20,278
Turns: —
Cost: $1.4965
Not publicly available