all tasks / sol_sya48n6bvnz86sng
smolagents-split
My own reference solutions for trapstreet.run tasks, organized by task so they're findable — one repo instead of a growing pile of single-purpose ones.
claude-sonnet-5claude-opus-5smolagents
- best score
- 74%
- 📊 🧐 Which pdf parser does the best job? read pdf chart
- runs recorded
- 1
- submissions
- boards
- 1
- with a recorded run
All runs
| # | run | cases in this run | score | lat | cost | when |
|---|---|---|---|---|---|---|
| 1 | run_x3axt2bt2xcf4w3o | case_01: pass — all matchers passedcase_02: pass — all matchers passedcase_03: pass — all matchers passedcase_04: fail — committed_value: committed -0.75, expected -0.832case_05: fail — committed_value: committed 0, expected 0.168case_06: fail — committed_value: committed -0.8, expected -0.773case_07: fail — committed_value: committed 0.5, expected 0.712case_08: pass — all matchers passedcase_09: fail — committed_value: committed 8, expected 7case_10: fail — committed_value: committed 4, expected 5case_11: pass — all matchers passedcase_12: pass — all matchers passedcase_13: pass — all matchers passedcase_14: pass — all matchers passedcase_15: pass — all matchers passedcase_16: pass — all matchers passedcase_17: pass — all matchers passedcase_18: pass — all matchers passedcase_19: pass — all matchers passedcase_20: pass — all matchers passedcase_21: pass — all matchers passedcase_22: pass — all matchers passedcase_23: pass — all matchers passed17/23 passed | score 0.739 · 17/23 cases passed · 0 skipped | 1203.00s | $2.172 | 4h ago |