diff --git a/apps/web-roo-code/src/app/evals/methodology/methodology-content.tsx b/apps/web-roo-code/src/app/evals/methodology/methodology-content.tsx index 18d9bcef3a..0285be5970 100644 --- a/apps/web-roo-code/src/app/evals/methodology/methodology-content.tsx +++ b/apps/web-roo-code/src/app/evals/methodology/methodology-content.tsx @@ -5,8 +5,6 @@ import { ArrowRight, FlaskConical, Code, - GitBranch, - Building2, AlertTriangle, BarChart3, Terminal, @@ -17,6 +15,7 @@ import { DollarSign, Zap, Trophy, + Scale, } from "lucide-react" import Link from "next/link" @@ -476,126 +475,112 @@ export function MethodologyContent() { Engineer Roles - - Not every task needs the same level of engineering. Three role tiers, each with different - exercise difficulty and scoring weights. - +

+ Each role represents a different engineering seniority level. We test models against + exercises matched to that role's complexity, then score using role-specific weights. +

+ - {/* Role cards */} - - {/* Junior */} + {/* How weights differ */} + -
-
-
- +

Different Roles, Different Weights

+

+ Each role has its own scoring weights. A model that's great for simple tasks might + not rank for architecture decisions. +

+ + +

Matched Exercises

+

+ Budget roles get simpler exercises. Complex roles get harder ones. The difficulty and + scoring shift together so recommendations stay relevant. +

+
+ + + {/* Budget vs Complex comparison */} + +

+ How Scoring Weights Shift +

+
+ {/* Budget roles */} +
+
+
-

Junior Engineer

-

- Easy + Medium exercises. Boilerplate, simple bug fixes, test generation. Scoring - emphasizes{" "} - cost efficiency. -

- {/* Weight breakdown */} -
-

- Scoring Weights +

+

Budget Roles

+

+ Cost and speed matter most. Simpler exercises where many models succeed, so + efficiency breaks the tie.

-
-
-
-
-
+
+
+
+
+
+
+
-
- Success 35% - Quality 15% - Cost 35% - Speed 15% +
+ Success + Quality + Cost ↑ + Speed
- - - {/* Senior */} - -
-
-
- + {/* Complex roles */} +
+
+
-

Senior Engineer

-

- Medium exercises. Feature development, debugging, code review. Balanced scoring with - emphasis on{" "} - success rate + quality - . -

- {/* Weight breakdown */} -
-

- Scoring Weights +

+

Complex Roles

+

+ Reasoning quality and success rate matter most. Harder exercises where only the + best models deliver.

-
-
-
-
-
+
+
+
+
+
+
+
-
- Success 40% - Quality 25% - Cost 20% - Speed 15% +
+ + Success ↑ + + + Quality ↑ + + Cost + Speed
- +
+ - {/* Staff */} - -
-
-
- -
-

Staff Engineer

-

- Hard exercises. Architecture, ambiguous requirements, system design. Scoring - prioritizes{" "} - - reasoning quality + correctness - - . -

- {/* Weight breakdown */} -
-

- Scoring Weights -

-
-
-
-
-
-
-
- Success 45% - Quality 30% - Cost 10% - Speed 15% -
-
-
- + {/* Link to roles page */} + + + Browse all engineer roles + +