From e757746351018df9610386181c9e1638f7ef2eb1 Mon Sep 17 00:00:00 2001
From: Johann Schopplich <mail@johannschopplich.com>
Date: Tue, 28 Oct 2025 23:08:47 +0100
Subject: [PATCH] docs(accuracy): highlight toon in perf table

---
 benchmarks/results/retrieval-accuracy.md | 8 ++++----
 benchmarks/src/report.ts                 | 9 ++++++---
 2 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/benchmarks/results/retrieval-accuracy.md b/benchmarks/results/retrieval-accuracy.md
index 49e5bb5..2e1cb37 100644
--- a/benchmarks/results/retrieval-accuracy.md
+++ b/benchmarks/results/retrieval-accuracy.md
@@ -4,7 +4,7 @@ Accuracy across **4 LLMs** on 154 data retrieval questions:
 
 ```
 gpt-5-nano
-  toon         ███████████████████░  96.1% (148/154)
+→ toon         ███████████████████░  96.1% (148/154)
   csv          ██████████████████░░  90.3% (139/154)
   yaml         ██████████████████░░  89.0% (137/154)
   json         ██████████████████░░  87.7% (135/154)
@@ -12,7 +12,7 @@ gpt-5-nano
 
 claude-haiku-4-5-20251001
   yaml         ██████████░░░░░░░░░░  49.4% (76/154)
-  toon         ██████████░░░░░░░░░░  48.1% (74/154)
+→ toon         ██████████░░░░░░░░░░  48.1% (74/154)
   csv          ██████████░░░░░░░░░░  48.1% (74/154)
   json         █████████░░░░░░░░░░░  47.4% (73/154)
   xml          █████████░░░░░░░░░░░  46.8% (72/154)
@@ -20,12 +20,12 @@ claude-haiku-4-5-20251001
 gemini-2.5-flash
   csv          ██████████████████░░  87.7% (135/154)
   xml          █████████████████░░░  85.1% (131/154)
-  toon         █████████████████░░░  83.8% (129/154)
+→ toon         █████████████████░░░  83.8% (129/154)
   json         ████████████████░░░░  78.6% (121/154)
   yaml         ███████████████░░░░░  76.6% (118/154)
 
 grok-4-fast-non-reasoning
-  toon         ██████████░░░░░░░░░░  48.7% (75/154)
+→ toon         ██████████░░░░░░░░░░  48.7% (75/154)
   json         ██████████░░░░░░░░░░  48.1% (74/154)
   xml          █████████░░░░░░░░░░░  47.4% (73/154)
   yaml         █████████░░░░░░░░░░░  46.8% (72/154)
diff --git a/benchmarks/src/report.ts b/benchmarks/src/report.ts
index 90f85a1..df12691 100644
--- a/benchmarks/src/report.ts
+++ b/benchmarks/src/report.ts
@@ -73,7 +73,8 @@ export function generateMarkdownReport(
       const bar = createProgressBar(result.accuracy, 1, 20)
       const accuracyStr = `${(result.accuracy * 100).toFixed(1)}%`.padStart(6)
       const countStr = `(${result.correctCount}/${result.totalCount})`
-      return `  ${result.format.padEnd(12)} ${bar} ${accuracyStr} ${countStr}`
+      const prefix = result.format === 'toon' ? '→ ' : '  '
+      return `${prefix}${result.format.padEnd(12)} ${bar} ${accuracyStr} ${countStr}`
     }).join('\n')
 
     // Add blank line before model name, except for first model
@@ -134,7 +135,7 @@ export function generateMarkdownReport(
 | ------ | -------- | ------ | ------------- |
 ${tableRows}
 `.trimStart()
-  }).filter(Boolean).join('\n')
+  }).filter(Boolean).join('\n').trim()
 
   // Build performance by model
   const modelPerformance = modelNames.map((modelName) => {
@@ -163,7 +164,7 @@ ${tableRows}
 | ------ | -------- | ------------- |
 ${tableRows}
 `.trimStart()
-  }).join('\n')
+  }).join('\n').trim()
 
   // Calculate total unique questions
   const totalQuestions = [...new Set(results.map(r => r.questionId))].length
@@ -204,9 +205,11 @@ ${summaryComparison}
 #### Performance by Dataset
 
 ${datasetBreakdown}
+
 #### Performance by Model
 
 ${modelPerformance}
+
 </details>
 
 <details>