Added 3.5 sonnet

website/_data/edit_leaderboard.yml

@@ -611,4 +611,51 @@
   date: 2024-06-08
   versions: 0.37.1-dev
   seconds_per_case: 280.6
-  total_cost: 0.0000
+  total_cost: 0.0000
+
+- dirname: 2024-06-20-15-09-26--claude-3.5-sonnet-whole
+  test_cases: 133
+  model: claude-3.5-sonnet (whole)
+  edit_format: whole
+  commit_hash: 068609e
+  pass_rate_1: 61.7
+  pass_rate_2: 78.2
+  percent_cases_well_formed: 100.0
+  error_outputs: 4
+  num_malformed_responses: 0
+  num_with_malformed_responses: 0
+  user_asks: 2
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 0
+  command: aider --model openrouter/anthropic/claude-3.5-sonnet
+  date: 2024-06-20
+  versions: 0.38.1-dev
+  seconds_per_case: 15.4
+  total_cost: 0.0000
+
+- dirname: 2024-06-20-15-16-41--claude-3.5-sonnet-diff
+  test_cases: 133
+  model: openrouter/anthropic/claude-3.5-sonnet
+  edit_format: diff
+  commit_hash: 068609e-dirty
+  pass_rate_1: 57.9
+  pass_rate_2: 74.4
+  percent_cases_well_formed: 97.0
+  error_outputs: 48
+  num_malformed_responses: 11
+  num_with_malformed_responses: 4
+  user_asks: 0
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 1
+  command: aider --model openrouter/anthropic/claude-3.5-sonnet
+  date: 2024-06-20
+  versions: 0.38.1-dev
+  seconds_per_case: 21.6
+  total_cost: 0.0000
+  

website/docs/leaderboards/index.md

@@ -16,22 +16,16 @@ While [aider can connect to almost any LLM](/docs/llms.html),
 it works best with models that score well on the benchmarks.
 
 
-## DeepSeek Coder V2 beats GPT-4o, Opus
+## Claude 3.5 Sonnet takes the top spot
 
-The new 
-[DeepSeek Coder V2](https://aider.chat/docs/llms/deepseek.html)
-model is now atop aider's code editing leaderboard!
-
-It's worth noting that DeepSeek Coder V2 is only capable of using aider's "whole" edit format.
-This means it returns a modified full copy of each file when it makes changes.
-Most other strong models are able to use aider's "diff" editing format,
-which allows them to return diffs of edits -- saving time and token costs.
-
-Models which use the "whole" edit format can only edit files
-which fit within their output token limits.
-These output limits are often as low as 4k tokens, even for models
-with very large context windows.
+Claude 3.5 Sonnet is now the top ranked model on aider's code editing leaderboard.
+DeepSeek Coder V2 previously took the #1 spot, only 4 days ago.
 
+Sonnet ranked #1 when using the "whole" editing format,
+but it also scored very well with
+aider's "diff" editing format.
+This format allows it to return code changes as diffs -- saving time and token costs,
+and making it practical to work with larger source files.
 
 ## Code editing leaderboard