└┘
← mecheval. / model / claude-direct-claude-opus-4-7

claude-direct-claude-opus-4-7

25 run blobs across 5 tasks

All runs

taskrun statusscoretokenswall
a1-plate-01 20260428T153537Z-bc66 fail 0.83 1.5k 6.3s
a1-cube-01 20260428T153537Z-bb2f PASS 1.00 965 2.6s
a2-flanged-cap-01 20260428T153537Z-97a4 PASS 1.00 2.3k 11.5s
a2-l-bracket-01 20260428T153537Z-3a65 PASS 1.00 1.5k 5.9s
a1-stepped-shaft-01 20260428T153537Z-33d7 PASS 1.00 1.2k 3.4s
a2-l-bracket-01 20260428T153525Z-a46b PASS 1.00 1.6k 6.8s
a1-stepped-shaft-01 20260428T153525Z-8710 PASS 1.00 1.1k 5.0s
a2-flanged-cap-01 20260428T153525Z-72cb PASS 1.00 2.2k 11.7s
a1-plate-01 20260428T153525Z-5f47 fail 0.83 1.5k 6.8s
a1-cube-01 20260428T153525Z-1416 PASS 1.00 959 3.1s
a1-plate-01 20260428T153513Z-cbe8 fail 0.83 1.7k 7.8s
a2-l-bracket-01 20260428T153513Z-ac6b PASS 1.00 1.6k 6.7s
a1-stepped-shaft-01 20260428T153513Z-ab32 PASS 1.00 1.2k 3.4s
a1-cube-01 20260428T153513Z-a078 PASS 1.00 961 2.7s
a2-flanged-cap-01 20260428T153513Z-1961 PASS 1.00 2.3k 11.4s
a2-flanged-cap-01 20260428T142511Z-8f59 PASS 1.00 2.1k 10.4s
a2-l-bracket-01 20260428T142504Z-02a4 PASS 1.00 1.6k 7.2s
a1-stepped-shaft-01 20260428T142500Z-3bc3 PASS 1.00 1.2k 3.6s
a1-plate-01 20260428T142452Z-c85b fail 0.83 1.5k 7.9s
a1-cube-01 20260428T142449Z-9da6 PASS 1.00 959 2.4s
a2-flanged-cap-01 20260428T141650Z-bd80 PASS 1.00 2.0k 15.8s
a2-l-bracket-01 20260428T141643Z-2876 PASS 1.00 1.6k 6.8s
a1-stepped-shaft-01 20260428T141639Z-92f3 PASS 1.00 1.2k 3.9s
a1-plate-01 20260428T141632Z-d7d2 fail 0.83 1.5k 6.8s
a1-cube-01 20260428T141611Z-6a7b PASS 1.00 962 2.9s
mecheval. · an evaluation suite by Municipal Robotics
sibling project: vcad. · github
drawing
mecheval.		 sheet
MODEL · claude-direct-claude-opus-4-7		 scale
25 runs · 5 tasks
date
2026-04-28		 drawn by
muni		 project
mecheval

generated 2026-04-28T21:00:04.654Z · static site, regenerate with npm run build -w @mecheval/leaderboard