refactor: token efficiency benchmark code

benchmarks/src/evaluate.ts

@@ -81,7 +81,8 @@ async function validateAnswer(
   }:
   { actual: string, expected: string, question: string },
 ): Promise<boolean> {
-  const prompt = `You are validating answers to questions about structured data.
+  const prompt = `
+You are validating answers to questions about structured data.
 
 Question: ${question}
 Expected answer: ${expected}
@@ -93,7 +94,8 @@ Is the actual answer correct? Consider:
 - Minor formatting differences are acceptable
 - Case-insensitive comparison for text
 
-Respond with only "YES" or "NO".`
+Respond with only "YES" or "NO".
+`.trim()
 
   try {
     const { text } = await generateText({

benchmarks/src/report.ts

@@ -204,7 +204,7 @@ ${modelPerformance}
 
 #### What's Being Measured
 
-This benchmark tests **LLM comprehension and data retrieval accuracy** when data is presented in different formats. Each LLM receives formatted data and must answer questions about it (this does NOT test LLM's ability to generate TOON output).
+This benchmark tests **LLM comprehension and data retrieval accuracy** across different input formats. Each LLM receives formatted data and must answer questions about it (this does **not** test model's ability to generate TOON output).
 
 #### Datasets Tested
 
@@ -233,18 +233,9 @@ Four datasets designed to test different structural patterns:
 
 #### Evaluation Process
 
-1. **Format conversion**: Each dataset is converted to all 5 formats (TOON, JSON, YAML, CSV, XML).
-2. **Query LLM**: Each model receives formatted data + question in a prompt.
-3. **LLM responds**: Model extracts the answer from the data.
-4. **Validate with LLM-as-judge**: GPT-5-nano validates if the answer is semantically correct.
-
-#### Semantic Validation
-
-Answers are validated by an LLM judge (\`gpt-5-nano\`) using semantic equivalence, not exact string matching:
-
-- **Numeric formats**: \`50000\` = \`$50,000\` = \`50000 dollars\` ✓
-- **Case insensitive**: \`Engineering\` = \`engineering\` = \`ENGINEERING\` ✓
-- **Minor formatting**: \`2025-01-01\` = \`January 1, 2025\` ✓
+1. **Format conversion:** Each dataset is converted to all 5 formats (TOON, JSON, YAML, CSV, XML).
+2. **Query LLM**: Each model receives formatted data + question in a prompt and extracts the answer.
+4. **Validate with LLM-as-judge**: \`gpt-5-nano\` validates if the answer is semantically correct (e.g., \`50000\` = \`$50,000\`, \`Engineering\` = \`engineering\`, \`2025-01-01\` = \`January 1, 2025\`).
 
 #### Models & Configuration