From b47c8499c764e86f27e0300a7d1f66731f78f77a Mon Sep 17 00:00:00 2001 From: multipleof4 Date: Mon, 13 Oct 2025 10:24:12 -0700 Subject: [PATCH] Feat: Run and display benchmark results in browser --- index.html | 87 +++++++++++++++++++++++++++++------------------------- 1 file changed, 46 insertions(+), 41 deletions(-) diff --git a/index.html b/index.html index c5451ef..bf5553b 100644 --- a/index.html +++ b/index.html @@ -16,52 +16,57 @@

Lynchmark

- Last updated + Last updated
-

Just another LLM benchmark.

+

An evolving benchmark for algorithmic code generation.

-
-
-
-

The only correct ranking of publicly available LLMs

-
-
-
    -
  • - 1. - Gemini 2.5 Pro - ~77tps -
  • -
  • - 2. - Claude Sonnet 4.5 - ~58tps -
  • -
  • - 3. - GPT-5 Codex - ~37tps -
  • -
-
-
- -
-
-

Non-coding

-
-
-
    -
  • - 1. - Kimi K2 -
  • -
-
-
+
+