Task gallery / Games / Version 1
Reference solution (oracle)
Pass
No-op resistance check
Pass
QA verdict
snorkel review: needs-revision x2
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-92aaeaf79aff8acb · 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
GPT-5.5 · default (unverified)4/10 · 40.0% [16.8%, 68.7%]0 / 100
GOOD_FAILURE: 0
BAD_FAILURE: 0
GOOD_SUCCESS: 0
BAD_SUCCESS: 0
Claude Opus 4.8 · default (unverified)8/10 · 80.0% [49.0%, 94.3%]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__MtfmRF7
oracle@@
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
tbench-task__JuSYQSr
oracle@@
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
tbench-task__YLwJjFz
nop@@
Not recorded
repo
0 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
tbench-task__vrHEn9g
oracle@@
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
tbench-task__GRdUdp4
GPT-5.5 · default (unverified)
Not recorded
repo
0 · validNo diagnostic label
derived
Tokens: 23,403
Turns: —
Cost: $2.7377
Not publicly available
tbench-task__7BXZDz2
Claude Opus 4.8 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 25,981
Turns: —
Cost: $1.6512
Not publicly available
tbench-task__8jAALrx
GPT-5.5 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 35,805
Turns: —
Cost: $3.7038
Not publicly available
tbench-task__MRd93zk
Claude Opus 4.8 · default (unverified)
Not recorded
repo
0 · validNo diagnostic label
derived
Tokens: 32,611
Turns: —
Cost: $2.1382
Not publicly available
tbench-task__Z2pSUmY
Claude Opus 4.8 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 35,117
Turns: —
Cost: $2.0893
Not publicly available
tbench-task__urmCDAp
Claude Opus 4.8 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 35,420
Turns: —
Cost: $2.4180
Not publicly available
tbench-task__Fiujeii
GPT-5.5 · default (unverified)
Not recorded
repo
0 · validNo diagnostic label
derived
Tokens: 31,509
Turns: —
Cost: $3.6698
Not publicly available
tbench-task__q3a3nDn
GPT-5.5 · default (unverified)
Not recorded
repo
0 · validNo diagnostic label
derived
Tokens: 17,013
Turns: —
Cost: $2.8733
Not publicly available
tbench-task__R3CAqHX
Claude Opus 4.8 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 27,001
Turns: —
Cost: $1.6793
Not publicly available
tbench-task__iAqkHQ8
GPT-5.5 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 28,876
Turns: —
Cost: $2.9645
Not publicly available
tbench-task__LsRerav
oracle@@
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
tbench-task__uC4NjDD
oracle@@
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
tbench-task__MsVqS7N
nop@@
Not recorded
repo
0 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
tbench-task__nzdsJJP
oracle@@
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
tbench-task__Gzy6GLd
Claude Opus 4.8 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 25,329
Turns: —
Cost: $1.5254
Not publicly available
tbench-task__u5y3mCv
Claude Opus 4.8 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 24,467
Turns: —
Cost: $1.5671
Not publicly available
tbench-task__UrjqPiz
Claude Opus 4.8 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 26,073
Turns: —
Cost: $1.6600
Not publicly available
tbench-task__tDWwLw6
Claude Opus 4.8 · default (unverified)
Not recorded
repo
0 · validNo diagnostic label
derived
Tokens: 29,056
Turns: —
Cost: $1.7235
Not publicly available
tbench-task__PJvzWM9
Claude Opus 4.8 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 31,759
Turns: —
Cost: $2.0494
Not publicly available
tbench-task__7RAUGTh
GPT-5.5 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 37,534
Turns: —
Cost: $3.7294
Not publicly available
tbench-task__GbB4aYA
GPT-5.5 · default (unverified)
Not recorded
repo
0 · validNo diagnostic label
derived
Tokens: 37,169
Turns: —
Cost: $4.1234
Not publicly available
tbench-task__AmxHpXD
GPT-5.5 · default (unverified)
Not recorded
repo
1 · validNo diagnostic label
derived
Tokens: 17,536
Turns: —
Cost: $2.4435
Not publicly available
tbench-task__vLk7R3C
GPT-5.5 · default (unverified)
Not recorded
repo
0 · validNo diagnostic label
derived
Tokens: 22,270
Turns: —
Cost: $2.6452
Not publicly available
tbench-task__5oLKfu4
GPT-5.5 · default (unverified)
Not recorded
repo
0 · validNo diagnostic label
derived
Tokens: 20,977
Turns: —
Cost: $2.2240
Not publicly available