Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

EQ-Bench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Emotional IntelligencePolish EQ-Bench
Overall Score78.07
106
Long-form writingEQ-Bench Long-form writing (leaderboard)
Score0.798
23
Reverse Chain-of-Thought GenerationEQ-Bench 3
Score0.896
20
Emotional Intelligence evaluationEQ-Bench
Overall Score86.4
19
Creative WritingEQ-Bench Longform (Creative Writing) (32 prompts)
Elo Rating1,578
17
Instruction FollowingEQ-Bench Longform (ID prompts) (45 prompts)
Elo Score1,911
16
Creative Writing EvaluationEQ-Bench Creative (OOD)
Elo Rating1,911
14
Creative writing evaluationEQ-Bench Creative
S Score84.6
14
Emotional Intelligence EvaluationEQ-Bench3
Overall Score83.3
12
Creative Writing EvaluationEQ-Bench Creative Writing v3
EQ-Bench83.8
6
Long-form Emotional Intelligence EvaluationEQ-Bench Longform (Far OOD 8–12k)
EQ-Bench Score54.3
1
Long-form Emotional Intelligence EvaluationEQ-Bench Longform Near OOD 4–8k
EQ-Bench Score57.5
1
Long-form Emotional Intelligence EvaluationEQ-Bench Longform (ID 1–4k)
EQ-Bench Score63.1
1
Long-form Emotional Intelligence EvaluationEQ-Bench Longform Aggregate
EQ-Bench Score59.8
1
Empathetic response generationEQ-Bench 3
Metric-
0
Showing 15 of 15 rows