2026-09-17__16-00-06

skills/bundesliga-fantasy-trader/evals/regression

sourishkrout/skillsIndexed 9/18/26, 12:41 AMOverview
Reward
1.00
Status
completed
Duration
5m 14s
Cost
$0.56
Tokens
482,890
Comparison
See how the candidate performs against the baseline.
Base
2026-09-17__14-20-31 (87c56d8)
Candidate
2026-09-17__16-00-06 (b696f93)
Reward delta
+0.00
Metadata
match
Rewards
Rewards below 1 appear first. Values are shown as raw decimals.
Reward
reward
1.00
Reward dimensions
artifact_written1.00

No verifier detail captured for this dimension.

budget_and_state_safety1.00

No verifier detail captured for this dimension.

decision_quality1.00

No verifier detail captured for this dimension.

evidence_quality1.00

No verifier detail captured for this dimension.

skill_activation_evidence1.00

No verifier detail captured for this dimension.

task_contract1.00

No verifier detail captured for this dimension.

temporal_integrity1.00

No verifier detail captured for this dimension.

Trials
Agent attempts at completing tasks in this job.

No trial details found.

Reward Reasoning
For rewards below 1.

No verifier explanations for rewards below 1.

Infra / Local Debug
Job path
https://github.com/sourishkrout/skills/commit/b696f931a4f43a8d0c046490c24011e7032e47ed
Eval keys
runme-codex__gpt-5.6-sol__regression
Agents
runme-codex
Models
-
Input tokens
257,910
Cache tokens
210,816
Output tokens
14,164