SaylorTwift/benchflow-dummy-test / readme-feature-verify
13.4 MB
78 files
Updated about 1 month ago
Name
Size
citation-check__7bee89dc
README.md491 Bytes
xet
adp.jsonl53.6 kB
xet
results.jsonl705 kB
xet
summary.json2.31 kB
xet
verifiers.jsonl52.7 kB
xet
README.md

BenchFlow run summary

  • Agent: opencode
  • Model: vllm/deepseek-ai/DeepSeek-V3.1
  • Tasks: 1
  • Scored: 0 / Unscored: 1
  • Mean reward: n/a
  • Rows with tool calls: 1

Tasks

Task Reward Tool calls Issue
citation-check — 14 verifier crashed: No reward file found at /tmp/bf-real-run4/2026-08-19__17-06-29/citation-check__7bee89dc/verifier/reward.txt or /tmp/bf-real-run4/2026-08-19__17-06-29/citation-check__7bee89dc/verifier/reward.json
Total size
13.4 MB
Files
78
Last updated
Aug 24
Pre-warmed CDN
US EU US EU

Contributors