DTeval

Loading analysis results...

Please wait while we prepare the detailed comparison.

Loading blueprint versions...

Please wait while we gather all the unique runs for this blueprint.

Analysis: Gd4 Individual Raw Survey Dtef Global Dialogues Gd4 Religion%3Aother Religious Group Rawsurvey Indiv Individual - Run e0d7bc8...

Global Dialogues GD4 - Other religious group [indiv] (73 ctx) [raw-survey]

DTEF [indiv]: Predict individual answers for Other religious group (10 participants). Source: Global Dialogues GD4 (https://github.com/collect-intel/global-dialogues)

TAGS:

Select Prompt:

Average key point coverage extent for each model across all prompts.

Click on any result cell to open a detailed view.

Advanced view

Highlight best performers

Sort prompts by

Sort models by

Color Scale - Simplified View (Avg. Coverage)

Perfect

Excellent

Good

Fair

Poor

Bad

Not Met

	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	4th 54.8%	2nd 61.5%	6th 51.7%	1st 63.2%	3rd 55.1%	5th 52.9%
91.2%	92%	87%	100%	97%	97%	74%
96.0%	99%	88%	100%	97%	97%	95%
92.2%	87%	98%	100%	97%	97%	74%
0.0%	0%	0%	0%	0%	0%	0%
40.3%	0%	26%	55%	0%	74%	87%
96.2%	97%	99%	100%	97%	97%	87%
15.2%	1%	0%	1%	0%	0%	89%
85.0%	54%	88%	97%	97%	97%	77%
73.8%	84%	87%	97%	97%	78%	0%
91.8%	92%	88%	100%	97%	97%	77%
0.0%	0%	0%	0%	0%	0%	0%
96.7%	99%	88%	100%	97%	97%	99%
71.7%	97%	78%	81%	0%	87%	87%
35.5%	0%	78%	1%	87%	0%	47%
48.8%	99%	95%	0%	99%	0%	0%
96.5%	99%	89%	100%	97%	97%	97%
58.5%	95%	78%	1%	88%	0%	89%
94.7%	99%	78%	100%	97%	97%	97%
26.3%	0%	68%	1%	89%	0%	0%
94.7%	99%	88%	100%	97%	97%	87%
30.2%	0%	14%	81%	0%	86%	0%
94.3%	88%	87%	100%	97%	97%	97%
76.7%	92%	99%	0%	91%	91%	87%
4.7%	0%	0%	28%	0%	0%	0%
43.8%	84%	95%	0%	84%	0%	0%
56.2%	3%	78%	83%	4%	91%	78%
35.2%	2%	52%	35%	20%	24%	78%
47.5%	16%	78%	0%	16%	88%	87%
40.5%	79%	0%	0%	84%	0%	80%
62.3%	35%	78%	0%	87%	97%	77%
69.5%	15%	78%	97%	91%	86%	50%
90.3%	88%	88%	100%	91%	97%	78%
25.0%	59%	0%	84%	0%	0%	7%
4.8%	20%	2%	0%	7%	0%	0%
17.5%	66%	0%	39%	0%	0%	0%
87.0%	80%	88%	97%	91%	88%	78%
43.5%	73%	54%	35%	7%	27%	65%
0.0%	0%	0%	0%	0%	0%	0%
54.2%	16%	78%	55%	88%	88%	0%
52.8%	16%	67%	0%	88%	88%	58%
46.2%	0%	14%	81%	91%	91%	0%
91.2%	88%	88%	100%	97%	97%	77%
0.0%	0%	0%	0%	0%	0%	0%
48.3%	66%	52%	35%	78%	27%	32%
42.2%	74%	95%	0%	84%	0%	0%
90.5%	93%	78%	100%	97%	97%	78%
48.8%	66%	80%	1%	78%	0%	68%
89.7%	84%	88%	100%	97%	91%	78%
40.0%	66%	54%	1%	67%	0%	52%
89.3%	80%	88%	97%	97%	97%	77%