Evaluations
Filter
inputs
output
compute_bleu
compute_diff
Trace
Feedback
Status
model
self
mean
mean
N/A
N/A
N/A
N/A
1-50 of 7490
Per page:
50
Charts
3
Score summary
14
General
Cost
$0.00
↗+ $0.00
Tokens
0
↗+ 0
Latency
1m40s
↗+ 1m27s
compute_hit_rate
mean
0.58
↗+ 0.2
compute_mrr
mean
0.26
↗+ 0.06
compute_ndcg
mean
0.33
↗+ 0.11
compute_map
mean
0.67
↗+ 0.23
compute_precision
mean
0.52
↗+ 0.17
compute_recall
mean
0.42
↗+ 0.05
compute_f1_score
mean
0.44
↗+ 0.09
llm_retrieval_scorer
relevance.mean
0.5
↗+ 0.07
relevance_rank_score.mean
0.28
↗+ 0.04
model_latency
mean
62.29
↗+ 62.12
compute_diff
mean
0.03
↗+ 0.01
compute_levenshtein
mean
0.45
↗+ 0.09
compute_rouge
mean
0.22
↗+ 0.02
compute_bleu
mean
0.09
↗+ 0.07
llm_response_scorer
score.mean
0.85
↗+ 0.1
correct.true_count
4
↗+ 4
correct.true_fraction
0.2
↗+ 0.2