As-wandb's workspace
Runs
149
Name
149 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
api
benchmarks.heron.artifact_path
benchmarks.heron.context_file
benchmarks.heron.context_key
benchmarks.heron.image_key
benchmarks.heron.leaderboard_csv
benchmarks.heron.name
benchmarks.heron.question_key
benchmarks.heron.questions_file
benchmarks.heron.reference_file
benchmarks.heron.reference_path
benchmarks.heron.table_columns
benchmarks.llava.artifact_path
benchmarks.llava.context_file
benchmarks.llava.context_key
benchmarks.llava.image_key
benchmarks.llava.leaderboard_csv
benchmarks.llava.name
benchmarks.llava.question_key
benchmarks.llava.questions_file
benchmarks.llava.reference_file
benchmarks.llava.reference_path
benchmarks.llava.table_columns
datasets.japanese_heron_bench_artifact_path
datasets.japanese_heron_bench_reference_path
datasets.llava_bench_in_the_wild_artifact_path
datasets.llava_bench_in_the_wild_reference_path
device_id
device_map
generation.args.device_map
generation.args.do_sample
generation.args.eos_token_id_list
generation.args.max_length
generation.args.max_new_tokens
generation.args.no_repeat_ngram_size
generation.args.num_beams
generation.args.temperature
generation.args.top_p
generation.args.use_flash_attn
model._attn_implementation
model._target_
model.api_type
model.automatic_adapter_generation
model.device_map
Finished
-
yuya-yamamoto
leaderboard
leaderboard_new
4h 20m 48s
-
-
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
context_ja.jsonl
caption
image
-
heron
text
questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
["benchmark","question_id","category","image_category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
ja/context_ja.jsonl
caption_jp
image
-
llava
jp
ja/questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
["benchmark","question_id","category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
0
-
-
true
-
512
-
3
-
0.7
-
-
-
-
-
-
-
Killed
-
yuya-yamamoto
5m 6s
-
-
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
context_ja.jsonl
caption
image
-
heron
text
questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
["benchmark","question_id","category","image_category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
ja/context_ja.jsonl
caption_jp
image
-
llava
jp
ja/questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
["benchmark","question_id","category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
0
-
-
true
-
512
-
3
-
0.7
-
-
-
-
-
-
-
Finished
-
yuya-yamamoto
leaderboard
leaderboard_new
2h 18m 17s
-
-
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
context_ja.jsonl
caption
image
-
heron
text
questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
["benchmark","question_id","category","image_category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
ja/context_ja.jsonl
caption_jp
image
-
llava
jp
ja/questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
["benchmark","question_id","category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
0
-
-
true
-
512
-
3
-
0.7
-
-
-
-
-
-
-
Killed
-
yuya-yamamoto
2m 29s
-
-
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
context_ja.jsonl
caption
image
-
heron
text
questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
["benchmark","question_id","category","image_category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
ja/context_ja.jsonl
caption_jp
image
-
llava
jp
ja/questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
["benchmark","question_id","category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
0
-
-
true
-
512
-
3
-
0.7
-
-
-
-
-
-
-
Killed
-
yuya-yamamoto
3m 14s
-
-
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
context_ja.jsonl
caption
image
-
heron
text
questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
["benchmark","question_id","category","image_category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
ja/context_ja.jsonl
caption_jp
image
-
llava
jp
ja/questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
["benchmark","question_id","category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
0
-
-
true
-
512
-
3
-
0.7
-
-
-
-
-
-
-
Killed
-
yuya-yamamoto
1m 10s
-
-
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
context_ja.jsonl
caption
image
-
heron
text
questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
["benchmark","question_id","category","image_category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
ja/context_ja.jsonl
caption_jp
image
-
llava
jp
ja/questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
["benchmark","question_id","category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
0
-
-
true
-
512
-
3
-
0.7
-
-
-
-
-
-
-
Failed
-
yuya-yamamoto
4s
-
-
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
context_ja.jsonl
caption
image
-
heron
text
questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
["benchmark","question_id","category","image_category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
ja/context_ja.jsonl
caption_jp
image
-
llava
jp
ja/questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
["benchmark","question_id","category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
0
-
-
true
-
512
-
3
-
0.7
-
-
-
-
-
-
-
Failed
-
yuya-yamamoto
5s
-
-
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
context_ja.jsonl
caption
image
-
heron
text
questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
["benchmark","question_id","category","image_category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
ja/context_ja.jsonl
caption_jp
image
-
llava
jp
ja/questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
["benchmark","question_id","category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
0
-
-
true
-
512
-
3
-
0.7
-
-
-
-
-
-
-
Failed
-
yuya-yamamoto
9s
-
-
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
context_ja.jsonl
caption
image
-
heron
text
questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
["benchmark","question_id","category","image_category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
ja/context_ja.jsonl
caption_jp
image
-
llava
jp
ja/questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
["benchmark","question_id","category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
0
-
-
true
-
512
-
3
-
0.7
-
-
-
-
-
-
-
Failed
-
yuya-yamamoto
5s
-
-
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
context_ja.jsonl
caption
image
-
heron
text
questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
["benchmark","question_id","category","image_category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
ja/context_ja.jsonl
caption_jp
image
-
llava
jp
ja/questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
["benchmark","question_id","category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
0
-
-
true
-
512
-
3
-
0.7
-
-
-
-
-
-
-
Killed
-
yuya-yamamoto
1m 35s
-
-
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
context_ja.jsonl
caption
image
-
heron
text
questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
["benchmark","question_id","category","image_category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
ja/context_ja.jsonl
caption_jp
image
-
llava
jp
ja/questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
["benchmark","question_id","category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
0
-
-
true
-
512
-
3
-
0.7
-
-
-
-
-
-
-
Crashed
-
yuya-yamamoto
3m 46s
-
-
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
context_ja.jsonl
caption
image
-
heron
text
questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
["benchmark","question_id","category","image_category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
ja/context_ja.jsonl
caption_jp
image
-
llava
jp
ja/questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
["benchmark","question_id","category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
0
-
-
true
-
512
-
3
-
0.7
-
-
-
-
-
-
-
Failed
-
yuya-yamamoto
5s
-
-
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
context_ja.jsonl
caption
image
-
heron
text
questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
["benchmark","question_id","category","image_category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
ja/context_ja.jsonl
caption_jp
image
-
llava
jp
ja/questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
["benchmark","question_id","category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
0
-
-
true
-
512
-
3
-
0.7
-
-
-
-
-
-
-
Failed
-
yuya-yamamoto
1m 11s
-
-
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
context_ja.jsonl
caption
image
-
heron
text
questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
["benchmark","question_id","category","image_category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
ja/context_ja.jsonl
caption_jp
image
-
llava
jp
ja/questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
["benchmark","question_id","category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
0
-
-
true
-
512
-
3
-
0.7
-
-
-
-
-
-
-
Failed
-
yuya-yamamoto
1m 8s
-
-
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
context_ja.jsonl
caption
image
-
heron
text
questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
["benchmark","question_id","category","image_category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
ja/context_ja.jsonl
caption_jp
image
-
llava
jp
ja/questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
["benchmark","question_id","category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
0
-
-
true
-
512
-
3
-
0.7
-
-
-
-
-
-
-
Failed
-
yuya-yamamoto
44s
-
-
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
context_ja.jsonl
caption
image
-
heron
text
questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
["benchmark","question_id","category","image_category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
ja/context_ja.jsonl
caption_jp
image
-
llava
jp
ja/questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
["benchmark","question_id","category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
0
-
-
true
-
512
-
3
-
0.7
-
-
-
-
-
-
-
Failed
-
yuya-yamamoto
1m 1s
-
-
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
context_ja.jsonl
caption
image
-
heron
text
questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
["benchmark","question_id","category","image_category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
ja/context_ja.jsonl
caption_jp
image
-
llava
jp
ja/questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
["benchmark","question_id","category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
0
-
-
true
-
512
-
3
-
0.7
-
-
-
-
-
-
-
Failed
-
yuya-yamamoto
1m 5s
-
-
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
context_ja.jsonl
caption
image
-
heron
text
questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
["benchmark","question_id","category","image_category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
ja/context_ja.jsonl
caption_jp
image
-
llava
jp
ja/questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
["benchmark","question_id","category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
0
-
-
true
-
512
-
3
-
0.7
-
-
-
-
-
-
-
Failed
-
yuya-yamamoto
1m 1s
-
-
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
context_ja.jsonl
caption
image
-
heron
text
questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
["benchmark","question_id","category","image_category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
ja/context_ja.jsonl
caption_jp
image
-
llava
jp
ja/questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
["benchmark","question_id","category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
0
-
-
true
-
512
-
3
-
0.7
-
-
-
-
-
-
-
Failed
-
yuya-yamamoto
1m 12s
-
-
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
context_ja.jsonl
caption
image
-
heron
text
questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
["benchmark","question_id","category","image_category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
ja/context_ja.jsonl
caption_jp
image
-
llava
jp
ja/questions_ja.jsonl
gpt-4-turbo-2024-04-09_answers.jsonl
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
["benchmark","question_id","category","image_file","image","question","answer"]
vision-language-leaderboard/heron-leaderboard/japanese-heron-bench:v0
vision-language-leaderboard/heron-leaderboard/heron-bench-reference:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild:v0
vision-language-leaderboard/heron-leaderboard/llava-bench-in-the-wild-reference:v0
0
-
-
true
-
512
-
3
-
0.7
-
-
-
-
-
-
-
1-20
of 149