16 tasks published · 133 solutions · 90 runs submitted
Ruqii
joined may 2026 · account age 5y · github
tasksolutionrunsresultlatencycostlatest
📊 🧐 Which pdf parser does the best job? read pdf chart0.130docling-ocr · 3/23 · 1mo1117.00s$0.3931mo📊 🧐 Which pdf parser does the best job? read pdf chart0.609pdf-inspector-routed-opus · 14/23 · 1mo1393.00s$5.2551mo📊 🧐 Which pdf parser does the best job? read pdf chart0.565pdf-inspector-routed · 13/23 · 1mo1359.00s$2.0621mo📊 🧐 Which pdf parser does the best job? read pdf chart0.739smolagents-split · 17/23 · 1mo11203.00s$2.1721mo📊 🧐 Which pdf parser does the best job? read pdf chart0.130pdf-inspector · 3/23 · 1mo195.00s$0.2441mo📊 🧐 Which pdf parser does the best job? read pdf chart0.565chart-geometry · 13/23 · 1mo1167.00s$0.1101mo📊 🧐 Which pdf parser does the best job? read pdf chart0.304claude-pdf · 7/23 · 1mo1205.00s$0.1141mo📚 Dsh - A year of receivables. One number. Can your agent get it?0.600dsh-subagent · 6/10 · 1mo24467.00s—1mo💎 LLM Plays Minecraft, One Life 💀1.000dsh-minecraft-one-life · 1/1 · 1mo11893.00s—1mo🧠 Does your memory plugin actually remember?0.000claude-code-noplugins · 0/8 · 1mo1290.00s$0.1721mo📚 Dsh - A year of receivables. One number. Can your agent get it?0.600dsh-workflow · 6/10 · 2mo14246.00s—2mo📚 Dsh - A year of receivables. One number. Can your agent get it?0.500dsh-noplugins · 5/10 · 2mo15252.00s—2mo🐑 Do LLMs Dream of INTJ? 🔮1.000mbti-multi-model-gpt-5.6-sol-pro · 1/1 · 2mo129.00s—2mo🐑 Do LLMs Dream of INTJ? 🔮1.000mbti-multi-model-glm-5.2 · 1/1 · 2mo128.00s—2mo🐑 Do LLMs Dream of INTJ? 🔮1.000mbti-multi-model-deepseek-v4-pro · 1/1 · 2mo1212.00s—2mo🐑 Do LLMs Dream of INTJ? 🔮1.000mbti-multi-model · 1/1 · 2mo93.00s$0.0262mo🐑 Do LLMs Dream of INTJ? 🔮1.000mbti-multi-model · 1/1 · 2mo44.00s$0.00792mo😬😬 Does adding skills break the jobs an agent already did?0.867claude-haiku-4-5 · 62/108 · 2mo1286.00s$1.0722mo😬😬 Does adding skills break the jobs an agent already did?0.872claude-haiku-4-5 · 67/108 · 2mo1308.00s$1.0722mo📃 🧐 Which pdf parser does the best job? Could be any kind of weird pdf1.000pdf-mixed-scan-pdf-inspector-routed · 20/20 · 2mo1152.00s$0.9362mo📃 🧐 Which pdf parser does the best job? Could be any kind of weird pdf0.350pdf-mixed-scan-pymupdf · 7/20 · 2mo1107.00s$0.2512mo📃 🧐 Which pdf parser does the best job? Could be any kind of weird pdf0.850pdf-mixed-scan-claude-pdf · 17/20 · 2mo1113.00s$0.0262mo📃 🧐 Which pdf parser does the best job? Could be any kind of weird pdf0.900pdf-mixed-scan-docling-ocr · 18/20 · 2mo1602.00s$0.6772mo📃 🧐 Which pdf parser does the best job? Could be any kind of weird pdf0.900pdf-mixed-scan-mineru · 18/20 · 2mo1140.00s$0.7612mo📃 🧐 Which pdf parser does the best job? Could be any kind of weird pdf0.350pdf-mixed-scan-pdf-inspector · 7/20 · 2mo1107.00s$0.2722mo🪲 Which code review skill works the best?0.700baseline-no-skill-claude-opus-5 · 7/10 · 2mo163.00s$0.0932mo🪲 Which code review skill works the best?0.500baseline-no-skill-claude-opus-5 · 5/10 · 2mo1107.00s$0.1822mo🪲 Which code review skill works the best?0.400baseline-no-skill-kimi-k3 · 4/10 · 2mo1143.00s$0.0612mo🪲 Which code review skill works the best?0.600baseline-no-skill-kimi-k3 · 6/10 · 2mo11484.00s$0.6422mo🪲 Which code review skill works the best?0.100baseline-no-skill-kimi-k3 · 1/10 · 2mo1348.00s—2mo🪲 Which code review skill works the best?0.600baseline-no-skill-claude-opus-4-8 · 6/10 · 2mo149.00s$0.0812mo🪲 Which code review skill works the best?0.800code-review-skill-jeffallan-claude-opus-4-8 · 8/10 · 2mo162.00s$0.1022mo🪲 Which code review skill works the best?0.800code-review-skill-awesome · 8/10 · 2mo163.00s$0.0982mo🪲 Which code review skill works the best?0.700code-review-skill-alireza · 7/10 · 2mo172.00s$0.1362moDebugging in a vendor payout senario - not many cases, but hard 😬1.000vendor-payout-multi-model-claude-opus-5 · 4/4 · 2mo170.00s$0.3592moDebugging in a vendor payout senario - not many cases, but hard 😬0.750vendor-payout-multi-model-gpt-5.6-luna-pro · 3/4 · 2mo181.00s—2moDebugging in a vendor payout senario - not many cases, but hard 😬0.750vendor-payout-multi-model-claude-sonnet-5 · 3/4 · 2mo1225.00s$0.3052moinfluencer_marketing_disclosure0.891influencer-marketing-skill-nexscope-claude-sonnet-4-6 · 9/11 · 2mo1181.00s$0.0772moinfluencer_marketing_disclosure0.836influencer-marketing-skill-mohitagw-claude-sonnet-4-6 · 8/11 · 2mo1186.00s$0.0912moinfluencer_marketing_disclosure0.836influencer-marketing-skill-cgallic-claude-sonnet-4-6 · 8/11 · 2mo1158.00s$0.0882moinfluencer_marketing_disclosure0.891influencer-marketing-skill-coreyhaines-claude-sonnet-4-6 · 9/11 · 2mo1173.00s$0.0942moinfluencer_marketing_disclosure0.782baseline-no-skill-claude-sonnet-4-6 · 7/11 · 2mo1164.00s$0.0842moinfluencer_marketing_disclosure0.836baseline-no-skill-claude-opus-4-8 · 8/11 · 2mo1133.00s$0.1792moLLM Plays REAL Minecraft - Can Your AI Mine a Diamond? 💎1.000Ruqii/mindcraft-forMC@5d41f6b · 1/1 · 3mo2956.00s$1.0423mo