Task gallery / Science / STEM / Version 1
Task evidence / repo

Snorkel-reviewed task review-8d6a0ae6

legacy-onlyChosen benchmark version
Reference solution (oracle)
Pass
No-op resistance check
Pass
QA verdict
snorkel review: needs-revision x1
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 review-8d6a0ae6 · version 1. Selection status: not fully recorded.

repo ↗

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)2/5 · 40.0% [11.8%, 76.9%]0 / 50
GOOD_FAILURE: 0
BAD_FAILURE: 0
GOOD_SUCCESS: 0
BAD_SUCCESS: 0
GPT-5.5 · default (unverified)0/5 · 0.0% [0.0%, 43.4%]0 / 50
GOOD_FAILURE: 0
BAD_FAILURE: 0
GOOD_SUCCESS: 0
BAD_SUCCESS: 0

Every recorded run

14 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__7mKRbah
nop@@		Not recorded
repo		0 · validNo diagnostic label
derived		Tokens: —
Turns: —
Cost: —		Not publicly available
tbench-task__P9vmKkU
oracle@@		Not recorded
repo		1 · validNo diagnostic label
derived		Tokens: —
Turns: —
Cost: —		Not publicly available
tbench-task__ihaTpAZ
oracle@@		Not recorded
repo		1 · validNo diagnostic label
derived		Tokens: —
Turns: —
Cost: —		Not publicly available
tbench-task__V4vjMPG
oracle@@		Not recorded
repo		1 · validNo diagnostic label
derived		Tokens: —
Turns: —
Cost: —		Not publicly available
tbench-task__ZAoPYhV
Claude Opus 4.8 · default (unverified)		Not recorded
repo		0 · validNo diagnostic label
derived		Tokens: 8,301
Turns: —
Cost: $0.5720		Not publicly available
tbench-task__ZXjQ8PJ
Claude Opus 4.8 · default (unverified)		Not recorded
repo		1 · validNo diagnostic label
derived		Tokens: 13,707
Turns: —
Cost: $0.8617		Not publicly available
tbench-task__xJ5Nhs8
Claude Opus 4.8 · default (unverified)		Not recorded
repo		1 · validNo diagnostic label
derived		Tokens: 11,168
Turns: —
Cost: $0.7236		Not publicly available
tbench-task__HZS2qUj
Claude Opus 4.8 · default (unverified)		Not recorded
repo		0 · validNo diagnostic label
derived		Tokens: 8,973
Turns: —
Cost: $0.5898		Not publicly available
tbench-task__NL7EEkA
Claude Opus 4.8 · default (unverified)		Not recorded
repo		0 · validNo diagnostic label
derived		Tokens: 9,852
Turns: —
Cost: $0.6658		Not publicly available
tbench-task__Fk2CGXo
GPT-5.5 · default (unverified)		Not recorded
repo		0 · validNo diagnostic label
derived		Tokens: 3,430
Turns: —
Cost: $0.7653		Not publicly available
tbench-task__iZbQSdc
GPT-5.5 · default (unverified)		Not recorded
repo		0 · validNo diagnostic label
derived		Tokens: 6,327
Turns: —
Cost: $0.9724		Not publicly available
tbench-task__G4U5hLG
GPT-5.5 · default (unverified)		Not recorded
repo		0 · validNo diagnostic label
derived		Tokens: 3,982
Turns: —
Cost: $0.6739		Not publicly available
tbench-task__v355rEx
GPT-5.5 · default (unverified)		Not recorded
repo		0 · validNo diagnostic label
derived		Tokens: 4,178
Turns: —
Cost: $0.5915		Not publicly available
tbench-task__8TL5PRT
GPT-5.5 · default (unverified)		Not recorded
repo		0 · validNo diagnostic label
derived		Tokens: 4,672
Turns: —
Cost: $0.5647		Not publicly available