From f8fa5d80c3a58e2960d96ce217cc957f59fb5d1e Mon Sep 17 00:00:00 2001 From: wangcunxiang Date: Mon, 17 Jun 2024 13:30:40 +0800 Subject: [PATCH] Update index.html --- index.html | 204 ++++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 202 insertions(+), 2 deletions(-) diff --git a/index.html b/index.html index 97bdcfe..b21bfb4 100644 --- a/index.html +++ b/index.html @@ -225,7 +225,7 @@

Citation

- Leaderboard - Generative Question + Leaderboard - Generative Setting (All novels)
@@ -337,7 +337,7 @@

Citation

- Leaderboard - MultiChoice Question + Leaderboard - MultiChoice Setting (All novels)
@@ -444,6 +444,206 @@

Citation

+
+ Leaderboard - Generative Setting (Public domain novels) +
+
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
ModelAccContext WindowText Input byTeam

+ 		Human Performance
+ 		90.00---
🏆1
+ 		claude-3-sonnet-20240229-v1:0
+ 		46.96200KLong-contextClaude
🥈2
+ 		gpt-4-0125-preview
+ 		45.76128KLong-contextOpenAI
🥉3
+ 		claude-v2:1
+ 		44.32200KLong-contextClaude
4
+ 		InternLM-20b
+ 		30.04200KLong-contextInternLM
5
+ 		InternLM-7b
+ 		28.07200KLong-contextInternLM
6
+ 		-
+ 		----
7
+ 		-
+ 		----
+
+
+ + +
+
+ Leaderboard - MultiChoice Setting (Public domain novels) +
+
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
ModelAccContext WindowText Input byTeam

+ 		Human Performance
+ 		97.00---
🏆1
+ 		gpt-4-0125-preview
+ 		70.44128KLong-contextOpenAI
🥈2
+ 		claude-3-sonnet-20240229-v1:0
+ 		67.15200KLong-contextClaude
🥉3
+ 		claude-v2:1
+ 		65.92200KLong-contextClaude
4
+ 		InternLM-20b
+ 		45.87200KLong-contextInternLM
7
+ 		InternLM-7b
+ 		40.89200KLong-contextInternLM
+