Hugging Face's logo

Spaces:
FSMBench
/
Leaderboard
Sleeping

App Files Community
4
taesiri commited on
Commit
ed1f48a
·
1 Parent(s): 669afad

update

Browse files
Files changed (35) hide show
  1. .gitattributes +20 -0
  2. results-cot/claude-3-sonnet-20240229.csv +2 -2
  3. results-cot/claude-3-sonnet-20240229.jpg +2 -2
  4. results-cot/claude-3-sonnet-20240229.pkl +2 -2
  5. results-cot/claude-3-sonnet-20240229.png +2 -2
  6. results-cot/gemini-pro.csv +3 -0
  7. results-cot/gemini-pro.jpg +3 -0
  8. results-cot/gemini-pro.pkl +3 -0
  9. results-cot/gemini-pro.png +3 -0
  10. results-cot/gpt-3.5-turbo-0125.csv +2 -2
  11. results-cot/gpt-3.5-turbo-0125.pkl +2 -2
  12. results-cot/gpt-4-turbo-2024-04-09.csv +3 -0
  13. results-cot/gpt-4-turbo-2024-04-09.jpg +3 -0
  14. results-cot/gpt-4-turbo-2024-04-09.pkl +3 -0
  15. results-cot/gpt-4-turbo-2024-04-09.png +3 -0
  16. results-vision/claude-3-opus-20240229.csv +3 -0
  17. results-vision/claude-3-opus-20240229.jpg +3 -0
  18. results-vision/claude-3-opus-20240229.pkl +3 -0
  19. results-vision/claude-3-opus-20240229.png +3 -0
  20. results/claude-3-haiku-20240307.csv +2 -2
  21. results/claude-3-haiku-20240307.jpg +2 -2
  22. results/claude-3-haiku-20240307.pkl +2 -2
  23. results/claude-3-haiku-20240307.png +2 -2
  24. results/claude-3-opus-20240229.csv +2 -2
  25. results/claude-3-opus-20240229.jpg +2 -2
  26. results/claude-3-opus-20240229.pkl +2 -2
  27. results/claude-3-opus-20240229.png +2 -2
  28. results/claude-3-sonnet-20240229.csv +3 -0
  29. results/claude-3-sonnet-20240229.jpg +3 -0
  30. results/claude-3-sonnet-20240229.pkl +3 -0
  31. results/claude-3-sonnet-20240229.png +3 -0
  32. results/deepseek-llm-67b-chat.csv +3 -0
  33. results/deepseek-llm-67b-chat.jpg +3 -0
  34. results/deepseek-llm-67b-chat.pkl +3 -0
  35. results/deepseek-llm-67b-chat.png +3 -0
.gitattributes CHANGED
@@ -175,3 +175,23 @@ results/gpt-4-turbo-2024-04-09.csv filter=lfs diff=lfs merge=lfs -text
175
  results/gpt-4-turbo-2024-04-09.jpg filter=lfs diff=lfs merge=lfs -text
176
  results/gpt-4-turbo-2024-04-09.pkl filter=lfs diff=lfs merge=lfs -text
177
  results/gpt-4-turbo-2024-04-09.png filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
175
  results/gpt-4-turbo-2024-04-09.jpg filter=lfs diff=lfs merge=lfs -text
176
  results/gpt-4-turbo-2024-04-09.pkl filter=lfs diff=lfs merge=lfs -text
177
  results/gpt-4-turbo-2024-04-09.png filter=lfs diff=lfs merge=lfs -text
178
+ results-cot/gemini-pro.pkl filter=lfs diff=lfs merge=lfs -text
179
+ results-cot/gpt-4-turbo-2024-04-09.pkl filter=lfs diff=lfs merge=lfs -text
180
+ results-cot/gemini-pro.png filter=lfs diff=lfs merge=lfs -text
181
+ results-cot/gpt-4-turbo-2024-04-09.png filter=lfs diff=lfs merge=lfs -text
182
+ results-cot/gemini-pro.jpg filter=lfs diff=lfs merge=lfs -text
183
+ results-cot/gpt-4-turbo-2024-04-09.jpg filter=lfs diff=lfs merge=lfs -text
184
+ results-cot/gemini-pro.csv filter=lfs diff=lfs merge=lfs -text
185
+ results-cot/gpt-4-turbo-2024-04-09.csv filter=lfs diff=lfs merge=lfs -text
186
+ results-vision/claude-3-opus-20240229.jpg filter=lfs diff=lfs merge=lfs -text
187
+ results/claude-3-sonnet-20240229.png filter=lfs diff=lfs merge=lfs -text
188
+ results/deepseek-llm-67b-chat.csv filter=lfs diff=lfs merge=lfs -text
189
+ results/deepseek-llm-67b-chat.png filter=lfs diff=lfs merge=lfs -text
190
+ results/deepseek-llm-67b-chat.pkl filter=lfs diff=lfs merge=lfs -text
191
+ results-vision/claude-3-opus-20240229.pkl filter=lfs diff=lfs merge=lfs -text
192
+ results-vision/claude-3-opus-20240229.png filter=lfs diff=lfs merge=lfs -text
193
+ results/claude-3-sonnet-20240229.csv filter=lfs diff=lfs merge=lfs -text
194
+ results/claude-3-sonnet-20240229.jpg filter=lfs diff=lfs merge=lfs -text
195
+ results/claude-3-sonnet-20240229.pkl filter=lfs diff=lfs merge=lfs -text
196
+ results/deepseek-llm-67b-chat.jpg filter=lfs diff=lfs merge=lfs -text
197
+ results-vision/claude-3-opus-20240229.csv filter=lfs diff=lfs merge=lfs -text
results-cot/claude-3-sonnet-20240229.csv CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf2b75b85af059eb5415b1bf58015eb0d7e0c0d9474d949562e66ebd6bb53412
3
- size 28117841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77c47e8698b8aa86de42bda82cb27c1efc0174c18b3ba306ff263cbd260de20e
3
+ size 13144187
results-cot/claude-3-sonnet-20240229.jpg CHANGED

Git LFS Details

  • SHA256: b47efc12fc779b56153d959400c99de0d5f52a3ac66fe22a2becd0e4c0e66000
  • Pointer size: 132 Bytes
  • Size of remote file: 1.28 MB

Git LFS Details

  • SHA256: f24cb016fbc657a82dbeb33a256608f26512beab44e613179e50d01f90cb9420
  • Pointer size: 132 Bytes
  • Size of remote file: 1.33 MB
results-cot/claude-3-sonnet-20240229.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b21e8f9c04cda7995d0326e58d0b4a14f6fef22b3ad9a3c6e183dc90ad32fbbd
3
- size 28099043
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e5a528d8fa3491adbc4e2e5a982e65a8a9c2fb5a96d321c864935dbe506453e
3
+ size 13047413
results-cot/claude-3-sonnet-20240229.png CHANGED

Git LFS Details

  • SHA256: 742dc668b70d0c03237074a8b49de92383ccb7df2b1f5cfcdb9ded8ebc878809
  • Pointer size: 132 Bytes
  • Size of remote file: 1.01 MB

Git LFS Details

  • SHA256: d5ede53fb575b73f93df09a94f8b66e2bafe6276a81d02b2d51944d956717a46
  • Pointer size: 132 Bytes
  • Size of remote file: 1.01 MB
results-cot/gemini-pro.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd52b8cfe861dd9fc106dafbe11569f9f2bf5848482e9b42c0ad3e88ffc83035
3
+ size 14773471
results-cot/gemini-pro.jpg ADDED

Git LFS Details

  • SHA256: d52c5a061dd3107ff0c970821247db3289e297a08626ec1062130cb3e6bd9c6c
  • Pointer size: 132 Bytes
  • Size of remote file: 1.33 MB
results-cot/gemini-pro.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72caa2e3c4ef872b3d6065f55179aa85d3eaa7978f9abb6fc1e3f58db19d8a69
3
+ size 14759970
results-cot/gemini-pro.png ADDED

Git LFS Details

  • SHA256: ab3de80d31f3903d88328e24731c44cd7e938e81224f9e8e5d3349a5664264d1
  • Pointer size: 132 Bytes
  • Size of remote file: 1.02 MB
results-cot/gpt-3.5-turbo-0125.csv CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25400229561733404647fa6aa2ab0372a8507f8c32a17339e9566a57c2618c93
3
- size 14472393
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9ea8fd5fd1e335397c14e3b312f60111614de4c20e50e5f3bc9d4fb6f049d70
3
+ size 14471960
results-cot/gpt-3.5-turbo-0125.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a5429ee7014934ba056f77e642157cb5ed3305246b6bfb6a335dc6cd874b4fd
3
- size 14487910
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:702c5dd6ffb22938a59815c65759ca5a201369b59633ee6c80c7030151e53634
3
+ size 14487477
results-cot/gpt-4-turbo-2024-04-09.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:011eeea335d67be1a859d51ca2accfd6bc56a2222394db52e68c9f444fec1c9b
3
+ size 20522713
results-cot/gpt-4-turbo-2024-04-09.jpg ADDED

Git LFS Details

  • SHA256: e10f603e693e6142bdac19f094b4b40782edc6da98ddd261ed402cae67dbec72
  • Pointer size: 132 Bytes
  • Size of remote file: 1.22 MB
results-cot/gpt-4-turbo-2024-04-09.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1383c823ccc8e09830dd4b96742c19fdf7515b56a715edd6ce131ff07fa029c
3
+ size 20513069
results-cot/gpt-4-turbo-2024-04-09.png ADDED

Git LFS Details

  • SHA256: c8cf146ef1e4456578ccc5c5fcd077e75aa0724146dbaed512cec70c5f7b8f31
  • Pointer size: 132 Bytes
  • Size of remote file: 1.01 MB
results-vision/claude-3-opus-20240229.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74ed9f652dc23c7408b307cb477e91692b561739bf23b33ba93319d9d073f294
3
+ size 10855333
results-vision/claude-3-opus-20240229.jpg ADDED

Git LFS Details

  • SHA256: 9938c9e622c49c715bbf459478f40f6c270dabf08a74a928ee9dfc66d26e34e4
  • Pointer size: 132 Bytes
  • Size of remote file: 1.34 MB
results-vision/claude-3-opus-20240229.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db495f6b9f264c3d9978c7d479b8206fbf8e67843c302c42416e0c6ee1aaa0a4
3
+ size 10789555
results-vision/claude-3-opus-20240229.png ADDED

Git LFS Details

  • SHA256: 3a8c1627064dfd947f682a877cf1bdd158b5a507a45690818941dd98a55b1090
  • Pointer size: 132 Bytes
  • Size of remote file: 1.01 MB
results/claude-3-haiku-20240307.csv CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45623535997485afdee5b0312f2b5fdcc26cf531fbb56b6c3af6e126dfbe7b0f
3
- size 19570166
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c11f91f84b50db9a3046bc1cf9445c46c6547d3f5828d9273ee5674e165477c6
3
+ size 19915152
results/claude-3-haiku-20240307.jpg CHANGED

Git LFS Details

  • SHA256: 3f2625de740c2c44bd3b55235ee44760467616e7ea7623a14d859899e5b2bb5d
  • Pointer size: 132 Bytes
  • Size of remote file: 1.32 MB

Git LFS Details

  • SHA256: c11ecd24a19d0acf8487beea975cddc2ce586298f6e8d4a9865cb8c49ffb20b0
  • Pointer size: 132 Bytes
  • Size of remote file: 1.3 MB
results/claude-3-haiku-20240307.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06b6c5cf244b982fcc45365fbeff804642130b80ec6f6f9b0cafcf69cb13e9fc
3
- size 19540844
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:281c6a1b1be9ef8d73978088e49dd4070ee21dcf326d8f6638b83abb394e1860
3
+ size 19884865
results/claude-3-haiku-20240307.png CHANGED

Git LFS Details

  • SHA256: 97c960ea8a02705da84250215ddd96eb6d5f981454fbee4b6f8803013fe298dc
  • Pointer size: 132 Bytes
  • Size of remote file: 1.01 MB

Git LFS Details

  • SHA256: 839090006279a0de9d90de9d11c86803e5bf035fce577408dcb4628b1d611b5e
  • Pointer size: 132 Bytes
  • Size of remote file: 1.01 MB
results/claude-3-opus-20240229.csv CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d902999bcee4798b81644b2ff0ea78280dd46bc310909154c1ef089adf82789
3
- size 20131397
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4513028095ff497d9594f87af6fdb2f75238c3444bdece4af1b22469c874f7e2
3
+ size 20347963
results/claude-3-opus-20240229.jpg CHANGED

Git LFS Details

  • SHA256: c4947b4ddae7034c9c22c6e4c89638f77d646578503ab4819badfaec686b07e3
  • Pointer size: 132 Bytes
  • Size of remote file: 1.22 MB

Git LFS Details

  • SHA256: 6e85e8e7ad91700f1da3f4697f01e1438993c9b0e5ba4707afc535fed47fd1ab
  • Pointer size: 132 Bytes
  • Size of remote file: 1.21 MB
results/claude-3-opus-20240229.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:424425308bdce6ebf2b59825b1b8b2796421792c44dafae8f74df06a07f3ef19
3
- size 20115450
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a7c21c7fbad602b1e517dbcca4753b566f940480ce56b2403d31fe3d230ead4
3
+ size 20331492
results/claude-3-opus-20240229.png CHANGED

Git LFS Details

  • SHA256: 3dccc43996953dd093472f31ad08e8607a0708f266b9301005a60b0541f8d6a5
  • Pointer size: 132 Bytes
  • Size of remote file: 1.01 MB

Git LFS Details

  • SHA256: 2ffda254a2d55eef6b4868bd5471c10a88abacf214c7876be637f9852e32a0f0
  • Pointer size: 132 Bytes
  • Size of remote file: 1.01 MB
results/claude-3-sonnet-20240229.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24f28e804daecb522f6f29ca4774a5178bbf18738ac9a433a2c9f98652de6f2f
3
+ size 23432638
results/claude-3-sonnet-20240229.jpg ADDED

Git LFS Details

  • SHA256: 58a9d375bc0cc391cd3c849f60e1323864670a7ca295647a27f64357a80f7927
  • Pointer size: 132 Bytes
  • Size of remote file: 1.29 MB
results/claude-3-sonnet-20240229.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea6e079352f2c37842cc53fc626d3aa51a462c486119d1b7b425b1209d654320
3
+ size 23403073
results/claude-3-sonnet-20240229.png ADDED

Git LFS Details

  • SHA256: d570a6a80f9c88e21bcce2c55b09c91efcbd8748261576ccbed3f1b806756b8f
  • Pointer size: 132 Bytes
  • Size of remote file: 1.01 MB
results/deepseek-llm-67b-chat.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e25ee66a4db8dcc610cb835ddb05cbca2b6249c279d50b92043a6f27182653e8
3
+ size 14589480
results/deepseek-llm-67b-chat.jpg ADDED

Git LFS Details

  • SHA256: 7d87ad7c1562889be8d76e441efefc5785d9ee803c68be1f32c5050ded893c7f
  • Pointer size: 132 Bytes
  • Size of remote file: 1.33 MB
results/deepseek-llm-67b-chat.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1601f6ca2972ccae7d173d7aafa41ecd2ef25ab7b088b8cdd1e60dca4b2831fc
3
+ size 14572334
results/deepseek-llm-67b-chat.png ADDED

Git LFS Details

  • SHA256: 8711f5a00452406a8a53d688ce263c8cedfd52138e688e41d030744c85da06f6
  • Pointer size: 132 Bytes
  • Size of remote file: 1.01 MB