Inference Fleet Leaderboard

Render cross-model fleet leaderboards from the local perf-report campaigns in ONE command (`perftunereport fleet_leaderboard`): a latency tier (aa-1k/10k/100k tok/s/user + TTFT + cost at c=1/c=10), a throughput tier (peak tok/s/GPU per (model,quant,TP) with latency + $/1M-tok), and a decision capstone (the perf Pareto frontier across decode-latency x first-token x throughput, with the perf-dominated set and a hard PERF != quality caveat). Auto-discovers every model's AA + roofline cells in campaigns/*/atlas.jsonl, so re-running refreshes as new campaigns publish. Use to answer "which model do I pick" / "rank the fleet on latency/throughput/cost" / "is model X perf-dominated". Triggers on "fleet leaderboard", "which model should I use", "cross-model comparison", "rank the fleet", "model selection guide", "pareto frontier of models", "perftunereport fleet_leaderboard", or any combination of "fleet / cross-model / which-model / leaderboard / pareto" with "latency / throughput / cost / pick / rank / compare".

mkdir -p ~/.claude/skills/inference-fleet-leaderboard
curl -L https://claudskills.com/skills/inference-fleet-leaderboard/SKILL.md \
  -o ~/.claude/skills/inference-fleet-leaderboard/SKILL.md

@misc{inference-fleet-leaderboard-2026,
  author    = {cfregly},
  title     = {Inference Fleet Leaderboard [Claude Code skill]},
  year      = {2026},
  publisher = {ClaudSkills},
  url       = {https://claudskills.com/skills/inference-fleet-leaderboard/}
}