Loading rankings…
Loading rankings…
Yield (Υ) vs raw token count — efficiency vs volume
| Feature | SigRank | ccusage |
|---|---|---|
| What it measures | Token-cascade efficiency (Yield, Leverage, SNR, Velocity) | Raw token counts (input, output, cache read/write) |
| Headline metric | Yield (Υ) = (cache_read × output) / input² | Total tokens consumed |
| What it tells you | How efficiently you use AI — are tokens compounding? | How much you spent — volume only |
| Leaderboard | Yes — ranked by Yield, class tiers, weekly drops | No — local CLI output only |
| API | Public REST API + MCP tools | None — CLI only |
| Comparison | Head-to-head operator comparison | None |
| Privacy | Token counts only — never prompt content | Token counts only — local CLI |
ccusage is a great tool for seeing how many tokens you've consumed. It reads your Claude session logs and shows you the raw numbers. That's useful for cost tracking.
But raw token count doesn't tell you if you're good at using AI. An operator who burns 10M tokens to produce 1K output has a high token count — but low efficiency. An operator who uses 100K tokens to produce the same 1K output has a lower token count but 10x higher Yield.
SigRank's Yield (Υ) metric measures the architecture of your token cascade — is signal compounding, or are tokens burned? ccusage tells you how much you spent. SigRank tells you whether it was worth it.
Note: SigRank actually bundles ccusage as a dependency for the raw token counting layer. They're complementary — ccusage counts, SigRank measures.
ccusage counts raw tokens from your Claude session logs — input, output, cache read/write. SigRank measures token-cascade efficiency with Yield — whether those tokens are compounding signal or burning. ccusage tells you how much you spent; SigRank tells a coder whether it was worth it.
No — they're complementary. SigRank actually bundles ccusage as a dependency for the raw token-counting layer. ccusage counts, SigRank measures. A developer using AI can run both: ccusage for cost tracking, SigRank for efficiency ranking.
Yield (Υ) = (cache_read × output) / input² — token-cascade efficiency from real sessions. Works across Claude, GPT, Gemini, Cursor, Copilot, and any AI coding tool.
Visit signalaf.com/score to enroll and submit your token telemetry. SigRank will compute your Yield, your rank, and your operator class. Token counts only — never prompt content, never code.
Stop counting. Start measuring.
Check my Yield