Operator Performance — Scoring the Human, Not the Model
The model is held constant. The operator is the variable. SigRank scores the human driving the AI — because that is where the signal lives.
The operator is the variable
Two developers sit down with the same model — the same Claude, the same ChatGPT, the same Gemini — on the same platform, for the same session length. One walks away with a token cascade that compounds: small fresh input riding a large cached foundation into dense output. The other walks away with a cascade that burns: high input, low cache reuse, thin output. Same model. Same clock. Wildly different results.
The difference is not the model. The difference is the operator — how they structure their prompts, how they reuse context, how they manage the cascade across turns. The model is a constant. The operator is the variable. SigRank is built to measure that variable.
This is the inversion that makes SigRank a different category from model leaderboards. LMSYS Arena ranks which model humans prefer. SigRank ranks which human drives their model best. The question is not “which AI is smarter?” — it is “who is better at using the AI they have?”
How SigRank scores operators
Scoring starts with token telemetry — four counts captured on-device per session: input, output, cache-read, cache-write. From those four integers, the yield metric Υ = cache_read × output / input² is computed. Yield is the headline: it measures the architecture of the cascade in one number.
The composite SIGNA rate blends yield with signal-force and drift components to produce the final operator score. Proprietary weights (RS.xx) govern the composite and remain server-side — the scoring shape is public, the exact weights are not, to prevent gaming. Snapshots are ed25519-signed and verified server-side with replay and plausibility guards. Operators are ranked over 7-day, 30-day, 90-day, and all-time windows.
Class tiers explained
Every operator is assigned a class tier from the scoring ruleset. Tiers run from low to high — they describe where an operator is in the compounding journey, not a fixed label.
IGNITER
The entry tier. Operators here are lighting the first sparks - high input, low cache reuse, output still finding its footing. Everyone starts here.
BEARER
Quiet accumulation. Token flow is growing but the cascade hasn't compounded yet.
REFINER
Practicing with purpose. Cache reuse is growing, yield is rising but not yet compounding.
SEEKER
Active exploration. The operator is learning to reuse context and reduce fresh input.
BASE
The center of the field. Mid-tier operators with consistent, balanced token flow.
POWER
Above center. The cascade is taking shape - cache hit rate is healthy, output is dense, yield is climbing.
ARCH
System builders. Coherent operators with consistent output and deep context reuse.
ARCH+
The deepest field experience. Sustained high-volume cascade across all dimensions.
Explore the category
How to Compare AI Operators
A guide to head-to-head operator comparison — what to look at, what to ignore, and how to read the yield gap.
Yield (Υ) Cascade
The headline metric that ranks operators: cache_read × output / input². The architecture of the cascade, not raw spend.
AI Benchmarking Tools — Alternatives
How SigRank compares to LMSYS Arena, WakaTime, Cursor metrics, and other adjacent tools — and why operator scoring is a different category.
The SigRank Index — Methodology
The canonical methodology: how operator scores are computed, verified, and ranked across platforms and time windows.
AI Operator Scoring — The New Performance Layer
The companion hub: what operator scoring is, how it differs from model benchmarking and time tracking, and the privacy-preserving scoring system.
Velocity
Tokens produced per unit of wall-clock time. The throughput metric — useful for speed comparisons, but yield is the number the leaderboard ranks by.
FAQ
- What is operator performance in AI coding?
- It measures how efficiently the human driving the AI uses it — not how good the model is. SigRank scores the operator by the architecture of their token cascade. The model is held constant; the operator is the variable.
- Why score the operator, not the model?
- Because the model is not the variable. Two operators on the same model can produce wildly different cascades. Model leaderboards already exist — SigRank measures the layer no one else does: the human.
- What are the class tiers?
- 8 experience tiers: IGNITER (entry), BEARER, REFINER, SEEKER, BASE, POWER, ARCH, and ARCH+ (deepest field experience). Tiers are assigned from total tokens accumulated. TRANSMITTER is a separate peak badge, not a tier.
- How is operator performance scored?
- From four on-device token counts. Yield (Υ = cache_read × output / input²) is the headline. The composite SIGNA rate blends yield with signal-force and drift. Weights (RS.xx) are server-side. Snapshots are ed25519-signed and verified.
- Is operator scoring private?
- Yes. The scanner reads token counts only — never prompt content. Only ed25519-signed numeric scores leave your device. Your prompts, code, and conversation history never leave your machine.