ENH: Update models

README.md

@@ -18,6 +18,6 @@ These are shown in green 🟢 and are the best LLMs to use.
 Some LLMs are "pareto suboptimal", i.e. there is no LLM worse in both cost and quality.
 These are shown in red 🔴 and are the LLMs to avoid.
 
-**Last updated: 24 July 2024**
+**Last updated: 4 Aug 2024**
 
 Alternatives: [ArtificialAnalysis.ai](https://artificialanalysis.ai/)

elo.csv

@@ -1,16 +1,20 @@
 model,elo,cpmi,source
-gpt-4o-2024-05-13,1287,5,https://openai.com/api/pricing/
+gpt-4o-2024-05-13,1286,5,https://openai.com/api/pricing/
 gpt-4o-mini-2024-07-18,1280,0.15,https://openai.com/api/pricing/
 claude-3-5-sonnet-20240620,1271,3,
-gemini-advanced-0514,1267,,
-gemini-1.5-pro-api-0514,1263,3.5,https://ai.google.dev/pricing
-gemini-1.5-pro-api-0409-preview,1258,7,https://llmpricecheck.com/google/gemini-1.5-pro
-gpt-4-turbo-2024-04-09,1256,10,https://openai.com/api/pricing/
-gpt-4-1106-preview,1252,10,https://openai.com/api/pricing/
+gemini-advanced-0514,1266,,
+meta-llama-3.1-405b-instruct,1262,2,https://openrouter.ai/models/meta-llama/llama-3.1-405b
+gemini-1.5-pro-api-0514,1261,3.5,https://ai.google.dev/pricing
+gemini-1.5-pro-api-0409-preview,1257,7,https://llmpricecheck.com/google/gemini-1.5-pro
+gpt-4-turbo-2024-04-09,1257,10,https://openai.com/api/pricing/
+gpt-4-1106-preview,1251,10,https://openai.com/api/pricing/
 claude-3-opus-20240229,1248,15,
-gpt-4-0125-preview,1246,10,https://openai.com/api/pricing/
+athene-70b,1245,,
+meta-llama-3.1-70b-instruct,1242,0.52,https://openrouter.ai/models/meta-llama/llama-3.1-70b-instruct
+gpt-4-0125-preview,1245,10,https://openai.com/api/pricing/
 yi-large-preview,1239,3,https://openrouter.ai/models/01-ai/yi-large
-gemini-1.5-flash-api-0514,1232,0.35,https://ai.google.dev/pricing
+gemini-1.5-flash-api-0514,1227,0.35,https://ai.google.dev/pricing
+deepseek-v2-api-0628,1221,0.14,
 gemma-2-27b-it,1212,0.27,https://openrouter.ai/models/google/gemma-2-27b-it
 yi-large,1239,3,https://openrouter.ai/models/01-ai/yi-large
 bard-jan-24-gemini-pro,1208,7,https://ai.google.dev/pricing
@@ -25,11 +29,12 @@ gpt-4-0314,1186,30,https://platform.openai.com/docs/deprecations/
 gemma-2-9b-it,1186,0.2,https://openrouter.ai/models/google/gemma-2-9b-it
 glm-4-0116,1183,,
 qwen-max-0428,1183,,
-deepseek-coder-v2-instruct,1179,0.14,https://openrouter.ai/models/deepseek/deepseek-coder
+deepseek-coder-v2-instruct,1178,0.14,https://openrouter.ai/models/deepseek/deepseek-coder
 claude-3-haiku-20240307,1178,0.25,
+meta-llama-3.1-8b-instruct,1166,0.06,https://openrouter.ai/models/meta-llama/llama-3.1-8b-instruct
 qwen1.5-110b-chat,1164,1.62,https://openrouter.ai/models/qwen/qwen-110b-chat
 gpt-4-0613,1161,30,https://platform.openai.com/docs/deprecations/
-yi-1.5-34b-chat,1158,
+yi-1.5-34b-chat,1158,,
 mistral-large-2402,1156,8,
 llama-3-8b-instruct,1153,0.05,
 claude-1,1149,8,