SyncValsverifier → artifact → classifier → verdict
SyncVals · Task

fewlabel-ssl-fixmatch

Post Training10/10 resolved↑ All tasks
pass@1100.0%
pass@k100.0% @10
resolved10/10
dominantGOOD_SUCCESS
During each run the agent saw only the starter workspace; tests/ and solution/ were withheld and restored only for grading. The reference solution/ is shown below for transparency.
Runs (10) , every recorded attempt at this task
AgentModelRewardToolsClassification
claude-codeclaude-opus-4-8✓ resolved147GOOD_SUCCESSview →
claude-codeclaude-opus-4-8✓ resolved241GOOD_SUCCESSview →
claude-codeclaude-opus-4-8✓ resolved164GOOD_SUCCESSview →
claude-codeclaude-opus-4-8✓ resolved248BAD_SUCCESSview →
claude-codeclaude-opus-4-8✓ resolved248GOOD_SUCCESSview →
claude-codeclaude-opus-4-8✓ resolved243GOOD_SUCCESSview →
claude-codeclaude-opus-4-8✓ resolved33GOOD_SUCCESSview →
claude-codeclaude-opus-4-8✓ resolved243BAD_SUCCESSview →
claude-codeclaude-opus-4-8✓ resolved245GOOD_SUCCESSview →
claude-codeclaude-opus-4-8✓ resolved256GOOD_SUCCESSview →
Task files , workspace, grader & reference answer
Select a file
Select a file from the tree to view it.

The task as the agent saw it and the verifier graded it. The reference solution/ is included below for transparency.