-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
- Loading branch information
There are no files selected for viewing
Large diffs are not rendered by default.
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1 @@ | ||
cache['Claude 3 Opus'] = {} |
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,6 @@ | ||
{ | ||
"Method": "LMM 🖼️", | ||
"Source": "https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf", | ||
"Date": "2024-03-04", | ||
"Comment": "" | ||
} |
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,6 +1,6 @@ | ||
{ | ||
"average": { | ||
"accuracy": "52.8" | ||
"accuracy": "50.5" | ||
}, | ||
"task": { | ||
"figure question answering": { | ||
|
Large diffs are not rendered by default.
This file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.
Large diffs are not rendered by default.
Large diffs are not rendered by default.
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,6 +1,6 @@ | ||
{ | ||
"Method": "LMM 🖼️", | ||
"Source": "https://arxiv.org/abs/2310.02255", | ||
"Date": "2023-10-03", | ||
"Date": "2023-10-15", | ||
"Comment": "" | ||
} |
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,45 +1,45 @@ | ||
{ | ||
"average": { | ||
"accuracy": "53.0" | ||
"accuracy": "49.9" | ||
}, | ||
"task": { | ||
"figure question answering": { | ||
"accuracy": "49.07" | ||
"accuracy": "43.12" | ||
}, | ||
"geometry problem solving": { | ||
"accuracy": "56.25" | ||
"accuracy": "50.48" | ||
}, | ||
"math word problem": { | ||
"accuracy": "53.76" | ||
"accuracy": "57.53" | ||
}, | ||
"textbook question answering": { | ||
"accuracy": "68.99" | ||
"accuracy": "65.19" | ||
}, | ||
"visual question answering": { | ||
"accuracy": "40.22" | ||
"accuracy": "37.99" | ||
} | ||
}, | ||
"skills": { | ||
"algebraic reasoning": { | ||
"accuracy": "58.36" | ||
"accuracy": "53.02" | ||
}, | ||
"arithmetic reasoning": { | ||
"accuracy": "45.89" | ||
"accuracy": "49.01" | ||
}, | ||
"geometry reasoning": { | ||
"accuracy": "55.65" | ||
"accuracy": "51.05" | ||
}, | ||
"logical reasoning": { | ||
"accuracy": "21.62" | ||
}, | ||
"numeric commonsense": { | ||
"accuracy": "38.89" | ||
"accuracy": "20.14" | ||
}, | ||
"scientific reasoning": { | ||
"accuracy": "62.30" | ||
"accuracy": "63.11" | ||
}, | ||
"statistical reasoning": { | ||
"accuracy": "59.47" | ||
"accuracy": "55.81" | ||
} | ||
} | ||
} |
This file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.