RLTasks by ulam.ai

Models / Reported model

Reported model / MODEL EVIDENCE

roberta-large-race

1 benchmarks · 62 observations · 1 sources

Scores at a glance

1 benchmarks · large dot: roberta-large-race; small dots: closest models where reported

BBQ: Bias Benchmark for QA ↗68.0963%

roberta-large-race · BBQ · Overall answer accuracy ↗

71 more reported results

49.0458% · roberta-large-race · BBQ · All released categories · ambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

87.1469% · roberta-large-race · BBQ · All released categories · disambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

68.8043% · roberta-large-race · BBQ · Age · answer accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

66.9666% · roberta-large-race · BBQ · Disability status · answer accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

73.4756% · roberta-large-race · BBQ · Gender identity · answer accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

66.9481% · roberta-large-race · BBQ · Nationality · answer accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

60.9772% · roberta-large-race · BBQ · Physical appearance · answer accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

64.6809% · roberta-large-race · BBQ · Race ethnicity · answer accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

67.9167% · roberta-large-race · BBQ · Religion · answer accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

82.1096% · roberta-large-race · BBQ · SES · answer accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

66.4352% · roberta-large-race · BBQ · Sexual orientation · answer accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

46.8478% · roberta-large-race · BBQ · Age · ambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

11.8478 bias points · roberta-large-race · BBQ · Age · ambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

90.7609% · roberta-large-race · BBQ · Age · disambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

2.6775 bias points · roberta-large-race · BBQ · Age · disambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

47.4293% · roberta-large-race · BBQ · Disability status · ambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

17.3522 bias points · roberta-large-race · BBQ · Disability status · ambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

86.5039% · roberta-large-race · BBQ · Disability status · disambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

5.7269 bias points · roberta-large-race · BBQ · Disability status · disambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

64.0244% · roberta-large-race · BBQ · Gender identity · ambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

1.8293 bias points · roberta-large-race · BBQ · Gender identity · ambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

82.9268% · roberta-large-race · BBQ · Gender identity · disambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

1.0989 bias points · roberta-large-race · BBQ · Gender identity · disambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

56.88% · roberta-large-race · BBQ · Gender identity (names) · ambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

12.72 bias points · roberta-large-race · BBQ · Gender identity (names) · ambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

84.12% · roberta-large-race · BBQ · Gender identity (names) · disambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

2.9885 bias points · roberta-large-race · BBQ · Gender identity (names) · disambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

44.2857% · roberta-large-race · BBQ · Nationality · ambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

5.0649 bias points · roberta-large-race · BBQ · Nationality · ambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

89.6104% · roberta-large-race · BBQ · Nationality · disambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

0.7123 bias points · roberta-large-race · BBQ · Nationality · disambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

42.5127% · roberta-large-race · BBQ · Physical appearance · ambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

41.2437 bias points · roberta-large-race · BBQ · Physical appearance · ambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

79.4416% · roberta-large-race · BBQ · Physical appearance · disambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

-0.9845 bias points · roberta-large-race · BBQ · Physical appearance · disambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

38.4043% · roberta-large-race · BBQ · Race ethnicity · ambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

0.1064 bias points · roberta-large-race · BBQ · Race ethnicity · ambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

90.9574% · roberta-large-race · BBQ · Race ethnicity · disambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

-0.9281 bias points · roberta-large-race · BBQ · Race ethnicity · disambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

37.96% · roberta-large-race · BBQ · Race ethnicity (names) · ambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

1.08 bias points · roberta-large-race · BBQ · Race ethnicity (names) · ambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

87.84% · roberta-large-race · BBQ · Race ethnicity (names) · disambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

-0.1812 bias points · roberta-large-race · BBQ · Race ethnicity (names) · disambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

56.9048% · roberta-large-race · BBQ · Race x SES · ambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

0.4762 bias points · roberta-large-race · BBQ · Race x SES · ambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

80.119% · roberta-large-race · BBQ · Race x SES · disambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

-1.2621 bias points · roberta-large-race · BBQ · Race x SES · disambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

49.8718% · roberta-large-race · BBQ · Race x SES (names) · ambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

-0.1795 bias points · roberta-large-race · BBQ · Race x SES (names) · ambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

90.1282% · roberta-large-race · BBQ · Race x SES (names) · disambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

-0.196 bias points · roberta-large-race · BBQ · Race x SES (names) · disambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

45.7456% · roberta-large-race · BBQ · Race x gender · ambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

-2.3246 bias points · roberta-large-race · BBQ · Race x gender · ambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

86.6667% · roberta-large-race · BBQ · Race x gender · disambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

0.0476 bias points · roberta-large-race · BBQ · Race x gender · disambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

40.2281% · roberta-large-race · BBQ · Race x gender (names) · ambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

-0.9298 bias points · roberta-large-race · BBQ · Race x gender (names) · ambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

83.4386% · roberta-large-race · BBQ · Race x gender (names) · disambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

1.9717 bias points · roberta-large-race · BBQ · Race x gender (names) · disambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

55.8333% · roberta-large-race · BBQ · Religion · ambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

9.1667 bias points · roberta-large-race · BBQ · Religion · ambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

80% · roberta-large-race · BBQ · Religion · disambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

3.3582 bias points · roberta-large-race · BBQ · Religion · disambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

70.1923% · roberta-large-race · BBQ · SES · ambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

3.4091 bias points · roberta-large-race · BBQ · SES · ambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

94.0268% · roberta-large-race · BBQ · SES · disambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

3.5055 bias points · roberta-large-race · BBQ · SES · disambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

39.1204% · roberta-large-race · BBQ · Sexual orientation · ambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

-3.0093 bias points · roberta-large-race · BBQ · Sexual orientation · ambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

93.75% · roberta-large-race · BBQ · Sexual orientation · disambig · Accuracy · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

-3.1026 bias points · roberta-large-race · BBQ · Sexual orientation · disambig · Signed bias score · BBQ: A Hand-Built Bias Benchmark for Question Answering — released prediction aggregation ↗

Closest models by score

Similar positions on shared benchmark leaderboards. Smaller gaps are closer.

deberta-v3-base-race →

33.3 percentile-point gap

1 of 1 shared benchmark comparisons

deberta-v3-large-race →

66.7 percentile-point gap

1 of 1 shared benchmark comparisons

roberta-base-race →

100.0 percentile-point gap

1 of 1 shared benchmark comparisons

How similarity is measured

Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.

Filter comparisons to this model →

Sources

Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.

BBQ: A Hand-Built Bias Benchmark for Question Answering — released RoBERTa and DeBERTa predictions ↗
Parrish, Alicia, Chen, Angelica, Nangia, Nikita, Padmakumar, Vishakh, Phang, Jason, Thompson, Jana et al. · 2021
All 8 authors
Parrish, Alicia, Chen, Angelica, Nangia, Nikita, Padmakumar, Vishakh, Phang, Jason, Thompson, Jana, Htut, Phu Mon, Bowman, Samuel R.

Names used in source tables

roberta-large-race