From 72bcb0ec4cb6bdaa03a91ea38f3ca70ade2bf26f Mon Sep 17 00:00:00 2001 From: mrT23 Date: Wed, 14 May 2025 07:35:09 +0300 Subject: [PATCH] docs: add Gemini-2.5-flash-preview benchmark comparisons to PR benchmark table --- docs/docs/pr_benchmark/index.md | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/docs/docs/pr_benchmark/index.md b/docs/docs/pr_benchmark/index.md index 53851e36..b26fd850 100644 --- a/docs/docs/pr_benchmark/index.md +++ b/docs/docs/pr_benchmark/index.md @@ -47,6 +47,18 @@ Here's a summary of the win rates based on the benchmark: Gemini-2.5-pro-preview-05-06 Sonnet 3.7 78.1% 21.9% + + Gemini-2.5-pro-preview-05-06 + Gemini-2.5-flash-preview-04-17 + 73.0% 27.0% + + Gemini-2.5-flash-preview-04-17 + GPT-4.1 + 54.6% 45.4% + + Gemini-2.5-flash-preview-04-17 + Sonnet 3.7 + 60.6% 39.4% GPT-4.1 Sonnet 3.7 @@ -54,6 +66,7 @@ Here's a summary of the win rates based on the benchmark: + ## Gemini-2.5-pro-preview-05-06 - Model Card ### Comparison against GPT-4.1