{"_id":"@artale/pi-arena","_rev":"10-604e0a92e8262805a62582c89ea0ab60","name":"@artale/pi-arena","dist-tags":{"latest":"1.5.3"},"versions":{"1.0.0":{"name":"@artale/pi-arena","version":"1.0.0","keywords":["pi-package","pi-extension","benchmark","arena","evaluation","hallucination","model-comparison"],"author":{"name":"artale"},"license":"MIT","_id":"@artale/pi-arena@1.0.0","maintainers":[{"name":"artale","email":"arosstale1@gmail.com"}],"homepage":"https://github.com/arosstale/pi-arena#readme","bugs":{"url":"https://github.com/arosstale/pi-arena/issues"},"dist":{"shasum":"ad0bac0613ecab9154e0afde0c3c845ed596e439","tarball":"https://registry.npmjs.org/@artale/pi-arena/-/pi-arena-1.0.0.tgz","fileCount":4,"integrity":"sha512-zMy19T0MgBWaxQKWUqgUqMSsLpFZuBVwPSULWQKG4ekWu9zJ15RXfasHz6p+E/9K5EgVuVrFIAxoV8PSAvkWfQ==","signatures":[{"sig":"MEUCIQCLHqB1IB++B8npZ0l04fTZ57PNeNw5xPDPL8M8o8t9CgIgXr+EsnGYrEcXQiwOiIrk80SXNCJqFiKdxeqvelMchfc=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":17913},"_npmUser":{"name":"artale","email":"arosstale1@gmail.com"},"extensions":["extensions/pi-arena.ts"],"repository":{"url":"git+https://github.com/arosstale/pi-arena.git","type":"git"},"_npmVersion":"10.9.4","description":"Model benchmarking with domain-aware hallucination tracking, per-model leaderboards, and task templates. Track speed, quality, and pass rate across coding, reasoning, and general knowledge.","directories":{},"_nodeVersion":"22.22.0","_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/pi-arena_1.0.0_1772981264201_0.7607294601101253","host":"s3://npm-registry-packages-npm-production"}},"1.1.0":{"name":"@artale/pi-arena","version":"1.1.0","keywords":["pi-package","pi-extension","benchmark","arena","evaluation","hallucination","model-comparison"],"author":{"name":"artale"},"license":"MIT","_id":"@artale/pi-arena@1.1.0","maintainers":[{"name":"artale","email":"arosstale1@gmail.com"}],"homepage":"https://github.com/arosstale/pi-arena#readme","bugs":{"url":"https://github.com/arosstale/pi-arena/issues"},"dist":{"shasum":"5a07c6c195f11225a55fdfc574987716f90efd18","tarball":"https://registry.npmjs.org/@artale/pi-arena/-/pi-arena-1.1.0.tgz","fileCount":4,"integrity":"sha512-OrXsb93k/Gb784sDSVvrgNHk/xwuSYUpVWQbXOePVqE1RvuQuz61sn5wYHZ6LxYyuVg5voz1y/nVTmCW765m3A==","signatures":[{"sig":"MEUCIQDlIqQSbntExzH0B6v0rhIe+d4wYhNouisEKvUjZZNGZwIgfwkm4DJdN97O5R7hg2bV/iNF5BofCWhpBpBxGvwfXdk=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":21885},"_npmUser":{"name":"artale","email":"arosstale1@gmail.com"},"extensions":["extensions/pi-arena.ts"],"repository":{"url":"git+https://github.com/arosstale/pi-arena.git","type":"git"},"_npmVersion":"10.9.4","description":"Model benchmarking with domain-aware hallucination tracking, per-model leaderboards, and task templates. Track speed, quality, and pass rate across coding, reasoning, and general knowledge.","directories":{},"_nodeVersion":"22.22.0","_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/pi-arena_1.1.0_1772981802453_0.5393875945026352","host":"s3://npm-registry-packages-npm-production"}},"1.1.1":{"name":"@artale/pi-arena","version":"1.1.1","keywords":["pi-package","pi-extension","benchmark","arena","evaluation","hallucination","model-comparison"],"author":{"name":"artale"},"license":"MIT","_id":"@artale/pi-arena@1.1.1","maintainers":[{"name":"artale","email":"arosstale1@gmail.com"}],"homepage":"https://github.com/arosstale/pi-arena#readme","bugs":{"url":"https://github.com/arosstale/pi-arena/issues"},"dist":{"shasum":"d022aa2b05457a00b33fdcd71e9c3e36c2b1e9d4","tarball":"https://registry.npmjs.org/@artale/pi-arena/-/pi-arena-1.1.1.tgz","fileCount":4,"integrity":"sha512-pc+CGpr7I3kLuufjGOCNTW47TASHidMvgxfVZoV2PO+FkDR4b5iFcfxFjSDIjskPkKXoek8naL0IXoX0skKoWg==","signatures":[{"sig":"MEYCIQCDpCC2S+BS5gtuDIyegqXEsjpz/jltypvD5tWJWvnNgQIhALgHimKqbBl9a7fRz8zgFPqsUXsT6uWbRffmdmSHg8z7","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":21663},"gitHead":"629ad4691829c9be4518589bba0a79b51556dfe2","_npmUser":{"name":"artale","email":"arosstale1@gmail.com"},"extensions":["extensions/pi-arena.ts"],"repository":{"url":"git+https://github.com/arosstale/pi-arena.git","type":"git"},"_npmVersion":"10.9.4","description":"Model benchmarking with domain-aware hallucination tracking, per-model leaderboards, and task templates. Track speed, quality, and pass rate across coding, reasoning, and general knowledge.","directories":{},"_nodeVersion":"22.22.0","_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/pi-arena_1.1.1_1772982791074_0.6978392934921362","host":"s3://npm-registry-packages-npm-production"}},"1.2.0":{"name":"@artale/pi-arena","version":"1.2.0","keywords":["pi-package","pi-extension","benchmark","arena","evaluation","hallucination","model-comparison"],"author":{"name":"artale"},"license":"MIT","_id":"@artale/pi-arena@1.2.0","maintainers":[{"name":"artale","email":"arosstale1@gmail.com"}],"homepage":"https://github.com/arosstale/pi-arena#readme","bugs":{"url":"https://github.com/arosstale/pi-arena/issues"},"dist":{"shasum":"acc9fc84dd673d8d4f2dc7c72a412811c3f5a982","tarball":"https://registry.npmjs.org/@artale/pi-arena/-/pi-arena-1.2.0.tgz","fileCount":5,"integrity":"sha512-W4c8dmb8I+8aBRtpg8R4DrT04WTwiXr1Rauqb29GZt/7XsxH8MN+X9En2cg0EgwYunPdnnrq1UzgeS4i9zx2KQ==","signatures":[{"sig":"MEUCIQD8+x2k1Bx9gJpEB27tVxpoazQ/kz7Qiu3dXEdGwupjfQIgD8hNGKmvkCL5cK9dbnqm4zaw3HQezosi12aqUFINMuo=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":26712},"gitHead":"e7215743281278cef2bcbf971791be5513eafd09","_npmUser":{"name":"artale","email":"arosstale1@gmail.com"},"extensions":["extensions/pi-arena.ts"],"repository":{"url":"git+https://github.com/arosstale/pi-arena.git","type":"git"},"_npmVersion":"10.9.4","description":"Model benchmarking with domain-aware hallucination tracking, per-model leaderboards, and task templates. Track speed, quality, and pass rate across coding, reasoning, and general knowledge.","directories":{},"_nodeVersion":"22.22.0","_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/pi-arena_1.2.0_1773005270784_0.45719645534453046","host":"s3://npm-registry-packages-npm-production"}},"1.3.0":{"name":"@artale/pi-arena","version":"1.3.0","keywords":["pi-package","pi-extension","benchmark","arena","evaluation","hallucination","model-comparison"],"author":{"name":"artale"},"license":"MIT","_id":"@artale/pi-arena@1.3.0","maintainers":[{"name":"artale","email":"arosstale1@gmail.com"}],"homepage":"https://github.com/arosstale/pi-arena#readme","bugs":{"url":"https://github.com/arosstale/pi-arena/issues"},"dist":{"shasum":"a8f58fc6b91e99e43dcdffca59c16eb45d272651","tarball":"https://registry.npmjs.org/@artale/pi-arena/-/pi-arena-1.3.0.tgz","fileCount":6,"integrity":"sha512-AiwAA8RwWkXEKu2JlzPGcecYvFOKAbnKiGv5FSuBNOW4g/XuYwQvfKnrhtVrt8R0lDX+iVedczEcAUAyW/sOAg==","signatures":[{"sig":"MEUCIQCWa+OMwpsUFiemtgEASL+X8Z4YT9CC5h6mp/kyTYUSYAIgKEzAihLfkwW8fi1dSKKaeGwD57noalHyiE9rBcO3K7I=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":50187},"gitHead":"74d5182f6adf7327ce9336413c2a075b6d10223a","_npmUser":{"name":"artale","email":"arosstale1@gmail.com"},"extensions":["extensions/pi-arena.ts"],"repository":{"url":"git+https://github.com/arosstale/pi-arena.git","type":"git"},"_npmVersion":"10.9.4","description":"Model benchmarking with domain-aware hallucination tracking, per-model leaderboards, and task templates. Track speed, quality, and pass rate across coding, reasoning, and general knowledge.","directories":{},"_nodeVersion":"22.22.0","_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/pi-arena_1.3.0_1773011617813_0.7567835191883923","host":"s3://npm-registry-packages-npm-production"}},"1.3.1":{"name":"@artale/pi-arena","version":"1.3.1","keywords":["pi-package","pi-extension","benchmark","arena","evaluation","hallucination","model-comparison"],"author":{"name":"artale"},"license":"MIT","_id":"@artale/pi-arena@1.3.1","maintainers":[{"name":"artale","email":"arosstale1@gmail.com"}],"homepage":"https://github.com/arosstale/pi-arena#readme","bugs":{"url":"https://github.com/arosstale/pi-arena/issues"},"dist":{"shasum":"8dc0c29392d4965c0e48729f1d8ad4d54b52b0b5","tarball":"https://registry.npmjs.org/@artale/pi-arena/-/pi-arena-1.3.1.tgz","fileCount":8,"integrity":"sha512-x8a997W90Apt/PMVeEY6HKhh2Cl8GH4Vbck/E19QX4YtkhZQ2H6y0h53kqOisuPUdDOqButcING9WuxSLI85tQ==","signatures":[{"sig":"MEUCIDXnxx29v9N1vtOJvVVN8jCtOX0P/aIuD5C6yDCYLFJ7AiEA1428/QBIQ71xTZ3uTNxFjydKKJXNWQFkEmcvvnlj1ZY=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":91365},"gitHead":"9d7edefa29be37a451dc08d8a6d6d957c4ab8e80","_npmUser":{"name":"artale","email":"arosstale1@gmail.com"},"extensions":["extensions/pi-arena.ts"],"repository":{"url":"git+https://github.com/arosstale/pi-arena.git","type":"git"},"_npmVersion":"10.9.4","description":"Model benchmarking with domain-aware hallucination tracking, per-model leaderboards, and task templates. Track speed, quality, and pass rate across coding, reasoning, and general knowledge.","directories":{},"_nodeVersion":"22.22.0","_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/pi-arena_1.3.1_1773050014105_0.2669714534206773","host":"s3://npm-registry-packages-npm-production"}},"1.4.0":{"name":"@artale/pi-arena","version":"1.4.0","keywords":["pi-package","pi-extension","benchmark","arena","evaluation","hallucination","model-comparison"],"author":{"name":"artale"},"license":"MIT","_id":"@artale/pi-arena@1.4.0","maintainers":[{"name":"artale","email":"arosstale1@gmail.com"}],"homepage":"https://github.com/arosstale/pi-arena#readme","bugs":{"url":"https://github.com/arosstale/pi-arena/issues"},"dist":{"shasum":"878e5035043d1a17b7f4e83be3c1e1d5f60c3dd6","tarball":"https://registry.npmjs.org/@artale/pi-arena/-/pi-arena-1.4.0.tgz","fileCount":8,"integrity":"sha512-8vw0Z5PZfqlfJKcU0hMVpz9E2uVqFiqWY6i/9Xm70DRx0di/OojoxFfAetXQEt+KO/wfLFkvmi/n1u+Il6bi7g==","signatures":[{"sig":"MEUCIQDl7ow3vVwlpJBieLMj74nRILozf++bHUNlSpWNn/+cIgIgPGbU9lzT4Mk++3W0uSfwvg28Yqwek3HCnP62v6vQktM=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":95245},"gitHead":"9d7edefa29be37a451dc08d8a6d6d957c4ab8e80","_npmUser":{"name":"artale","email":"arosstale1@gmail.com"},"extensions":["extensions/pi-arena.ts"],"repository":{"url":"git+https://github.com/arosstale/pi-arena.git","type":"git"},"_npmVersion":"10.9.4","description":"Model benchmarking with domain-aware hallucination tracking, per-model leaderboards, and task templates. Track speed, quality, and pass rate across coding, reasoning, and general knowledge.","directories":{},"_nodeVersion":"22.22.0","_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/pi-arena_1.4.0_1773071106718_0.27273828162886815","host":"s3://npm-registry-packages-npm-production"}},"1.5.0":{"name":"@artale/pi-arena","version":"1.5.0","keywords":["pi-package","pi-extension","benchmark","arena","evaluation","hallucination","model-comparison"],"author":{"name":"artale"},"license":"MIT","_id":"@artale/pi-arena@1.5.0","maintainers":[{"name":"artale","email":"arosstale1@gmail.com"}],"homepage":"https://github.com/arosstale/pi-arena#readme","bugs":{"url":"https://github.com/arosstale/pi-arena/issues"},"dist":{"shasum":"4cf0da2939d7fc99e34a3b30cbc8f07bd4fc1f4e","tarball":"https://registry.npmjs.org/@artale/pi-arena/-/pi-arena-1.5.0.tgz","fileCount":8,"integrity":"sha512-KoyjWHOBgI88VyAGzSwrBGf7jmhcQoDQrpYSCQFzuxtg0Y21R4CfbWyiQUVumnpgzWaxMf4nAm+MBlN+oG7xQw==","signatures":[{"sig":"MEUCICahl0K1AjxqmKDXkpPzO7ZF3b2Y+6wCDFlc3ICkyMwNAiEA+tULqxRR01Ps2Z357P+cK5/SU6gEiJv3le3eNKCjmlY=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":95246},"gitHead":"faffd52a447fb586ee9dd042947f6b1d28ae3b65","_npmUser":{"name":"artale","email":"arosstale1@gmail.com"},"extensions":["extensions/pi-arena.ts"],"repository":{"url":"git+https://github.com/arosstale/pi-arena.git","type":"git"},"_npmVersion":"10.9.4","description":"Model benchmarking with domain-aware hallucination tracking, per-model leaderboards, and task templates. Track speed, quality, and pass rate across coding, reasoning, and general knowledge.","directories":{},"_nodeVersion":"22.22.0","_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/pi-arena_1.5.0_1773083957685_0.32430688974074573","host":"s3://npm-registry-packages-npm-production"}},"1.5.2":{"name":"@artale/pi-arena","version":"1.5.2","keywords":["pi-package","pi-extension","benchmark","arena","evaluation","hallucination","model-comparison"],"author":{"name":"artale"},"license":"MIT","_id":"@artale/pi-arena@1.5.2","maintainers":[{"name":"artale","email":"arosstale1@gmail.com"}],"homepage":"https://github.com/artale93/pi-arena#readme","bugs":{"url":"https://github.com/artale93/pi-arena/issues"},"dist":{"shasum":"d127f564c05baccad253b351c4235579c90b226c","tarball":"https://registry.npmjs.org/@artale/pi-arena/-/pi-arena-1.5.2.tgz","fileCount":8,"integrity":"sha512-c9LMxkXavEFs4v7tXTaB6DVlNFNSrHabaPxgIu13U+EKdsW+8PHWbKl983kzX3kocc/hevhNVmgocz/WU0SSAA==","signatures":[{"sig":"MEUCIHZSriIV/J5Oqnp7ttnkvXP9nmhQzQyR+VsBOc/c37fFAiEAqaDhFTvhzNyqkuXsk4xrrOfcCmN9yLi8VI43p4gT5H8=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":95245},"gitHead":"5f59ef5e226df430f92d50da8119125b20eaa6c3","_npmUser":{"name":"artale","email":"arosstale1@gmail.com"},"extensions":["extensions/pi-arena.ts"],"repository":{"url":"git+https://github.com/artale93/pi-arena.git","type":"git"},"_npmVersion":"11.12.1","description":"Model benchmarking with domain-aware hallucination tracking, per-model leaderboards, and task templates. Track speed, quality, and pass rate across coding, reasoning, and general knowledge.","directories":{},"_nodeVersion":"22.22.0","_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/pi-arena_1.5.2_1776776822247_0.37462037304194484","host":"s3://npm-registry-packages-npm-production"}},"1.5.3":{"name":"@artale/pi-arena","version":"1.5.3","description":"Model benchmarking with domain-aware hallucination tracking, per-model leaderboards, and task templates. Track speed, quality, and pass rate across coding, reasoning, and general knowledge.","keywords":["pi-package","pi-extension","benchmark","arena","evaluation","hallucination","model-comparison"],"license":"MIT","author":{"name":"artale"},"repository":{"type":"git","url":"git+https://github.com/artale93/pi-arena.git"},"pi":{"extensions":["extensions/pi-arena.ts"],"image":"https://raw.githubusercontent.com/artale93/pi-arena/main/preview.png"},"_id":"@artale/pi-arena@1.5.3","gitHead":"6ac7de08d119bec363b12c196fc29f1339a6dad7","bugs":{"url":"https://github.com/artale93/pi-arena/issues"},"homepage":"https://github.com/artale93/pi-arena#readme","_nodeVersion":"22.22.0","_npmVersion":"10.9.4","dist":{"integrity":"sha512-zS1ny1bV/iZxALasnztH+YQ3kQPTm/DqUVu7l9XB49CPUcfKw5kEr13iArCxZPdD9YwUE7Ap65NRONOVQP1QMg==","shasum":"ffc28971d0217a37fc62fed8fb70fd9707ee39ad","tarball":"https://registry.npmjs.org/@artale/pi-arena/-/pi-arena-1.5.3.tgz","fileCount":9,"unpackedSize":164328,"signatures":[{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEQCIDdODdHkxr4YEXT+smDD6ZwYYdmxHogvDD4qS5mKkRYlAiBAnCTWrJdwHWnjoPYwFoMvNong3XN1VLpZJGiarhLnnw=="}]},"_npmUser":{"name":"artale","email":"arosstale1@gmail.com"},"directories":{},"maintainers":[{"name":"artale","email":"arosstale1@gmail.com"}],"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/pi-arena_1.5.3_1777725772724_0.0626823940255512"},"_hasShrinkwrap":false}},"time":{"created":"2026-03-08T14:47:44.144Z","modified":"2026-05-02T12:42:53.012Z","1.0.0":"2026-03-08T14:47:44.354Z","1.1.0":"2026-03-08T14:56:42.597Z","1.1.1":"2026-03-08T15:13:11.221Z","1.2.0":"2026-03-08T21:27:50.937Z","1.3.0":"2026-03-08T23:13:37.963Z","1.3.1":"2026-03-09T09:53:34.288Z","1.4.0":"2026-03-09T15:45:06.865Z","1.5.0":"2026-03-09T19:19:17.923Z","1.5.2":"2026-04-21T13:07:02.379Z","1.5.3":"2026-05-02T12:42:52.905Z"},"bugs":{"url":"https://github.com/artale93/pi-arena/issues"},"author":{"name":"artale"},"license":"MIT","homepage":"https://github.com/artale93/pi-arena#readme","keywords":["pi-package","pi-extension","benchmark","arena","evaluation","hallucination","model-comparison"],"repository":{"type":"git","url":"git+https://github.com/artale93/pi-arena.git"},"description":"Model benchmarking with domain-aware hallucination tracking, per-model leaderboards, and task templates. Track speed, quality, and pass rate across coding, reasoning, and general knowledge.","maintainers":[{"name":"artale","email":"arosstale1@gmail.com"}],"readme":"# @artale/pi-arena\n\nModel benchmarking and performance tracking for pi. Run tasks against models, track results, detect regressions.\n\n## Install\n```bash\nnpm install -g @artale/pi-arena\n```\n\n## Features (v1.1)\n- **Benchmark tracking** — Record task/model/duration/score/pass runs\n- **Vectara baselines** — 28 models from HHEM-2.3 hallucination leaderboard (March 2026)\n- **Auto-compare** — Flag models scoring below their Vectara baseline\n- **Verbosity penalty** — Detect when verbose output correlates with hallucination\n- **Domain tracking** — coding, reasoning, general-knowledge, legal, medical, financial\n- **Thread type tracking** — Base, P-Thread, C-Thread, F-Thread, B-Thread, L-Thread, Z-Thread\n\n## Tools\n- **arena_run** — Record a benchmark run\n- **arena_history** — Query benchmark history (filter by model/domain)\n- **arena_compare** — Side-by-side model comparison with Vectara baselines\n\n## Commands\n- `/arena stats` — Aggregate statistics\n- `/arena baselines` — Vectara hallucination leaderboard\n- `/arena leaderboard` — Model rankings by score\n- `/arena history [n]` — Recent benchmark runs\n- `/arena compare <A> <B>` — Head-to-head comparison\n- `/arena templates` — Task templates\n- `/arena export` — Export all data\n","readmeFilename":"README.md"}