OptimismBench / app /src /content /assets /data /valence.json
seonglae's picture
article: interactive research piece for OptimismBench
1df44e8
Raw
History Blame Contribute Delete
642 Bytes
{
"note":"Valence decomposition (OptimismBench Fig 2). good=P(good)-50, bad=P(bad)-50. B_en_003 valence-label corrected.",
"models":[
{"name":"GPT-5.4-mini","provider":"OpenAI","good":7.3,"bad":5.8},
{"name":"GPT-5.4","provider":"OpenAI","good":4.2,"bad":5.5},
{"name":"Haiku 4.5","provider":"Anthropic","good":-0.2,"bad":6.4},
{"name":"Flash 3","provider":"Google","good":3.8,"bad":1.2},
{"name":"Pro 3.1","provider":"Google","good":-1.9,"bad":5.6},
{"name":"Sonnet 4.6","provider":"Anthropic","good":-6.6,"bad":-1.1}
],
"pairs":[["GPT-5.4-mini","GPT-5.4"],["Haiku 4.5","Sonnet 4.6"],["Flash 3","Pro 3.1"]]
}