Timmli commited on
Commit
e41e179
·
1 Parent(s): 56c7614

add v2 judgment

Browse files
data/arena-hard-v2.0/model_judgment/gemini-2.5/claude-3-7-sonnet-20250219-thinking-16k.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb5b4e3d8b921704a449db8acfe3b9225fd240cf8d3292def63d79188421aa3f
3
+ size 27579454
data/arena-hard-v2.0/model_judgment/gemini-2.5/deepseek-r1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eacb9d14c8b273c192953d1dde90abe404e0c6cfe8d45491dbff720f6e60719
3
+ size 25654391
data/arena-hard-v2.0/model_judgment/gemini-2.5/llama4-maverick-instruct-basic.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e944ff211c606854f26ff9cfc37c51403357aeca07d172d7206ed3ec9d771f0
3
+ size 26107532
data/arena-hard-v2.0/model_judgment/gemini-2.5/o1-2024-12-17-high.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d9215f2baa69473fc721e87c953531734d1157077eb6a51fe33f7ea5895d8da
3
+ size 28018662
data/arena-hard-v2.0/model_judgment/gemini-2.5/o3-2025-04-16.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:081da52d32596235c02eac8bee1d9e801beb891db79f2347a60a80b086127e68
3
+ size 26871562
data/arena-hard-v2.0/model_judgment/gemini-2.5/qwq-32b.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c88add3b2d1f236deff8809d4ccec1160df36bb4eb5b6aea72bb0974cb4b36e8
3
+ size 26818921
data/arena-hard-v2.0/model_judgment/gemini-2.5/s1.1-32B.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aed4af0af3d47f735763495b339d4a18c77a17fd0e27786cb4b7469f2ee65f9
3
+ size 28710704