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%3Ajudaism Rawsurvey Indiv Individual - Run 21c7e67...

Global Dialogues GD4 - Judaism [indiv] (73 ctx) [raw-survey]

DTEF [indiv]: Predict individual answers for Judaism (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	5th 42.5%	2nd 48.7%	4th 44.5%	1st 52.7%	6th 39.1%	3rd 45.7%
83.0%	88%	78%	97%	97%	87%	51%
88.5%	90%	87%	97%	97%	86%	74%
63.7%	75%	78%	55%	91%	83%	0%
70.5%	15%	87%	91%	91%	88%	51%
88.3%	84%	87%	97%	97%	88%	77%
95.8%	96%	98%	100%	97%	97%	87%
0.0%	0%	0%	0%	0%	0%	0%
87.7%	90%	87%	97%	91%	86%	75%
28.5%	77%	0%	1%	15%	0%	78%
65.7%	82%	78%	55%	91%	88%	0%
14.7%	88%	0%	0%	0%	0%	0%
72.3%	0%	78%	97%	97%	88%	74%
44.0%	0%	89%	0%	95%	0%	80%
31.0%	11%	8%	81%	0%	86%	0%
94.7%	98%	88%	97%	97%	91%	97%
57.3%	0%	87%	0%	97%	86%	74%
56.8%	95%	52%	1%	97%	7%	89%
29.3%	0%	8%	81%	0%	87%	0%
61.7%	95%	89%	0%	97%	0%	89%
47.3%	0%	89%	0%	95%	0%	100%
38.7%	42%	32%	1%	79%	0%	78%
28.5%	27%	0%	84%	60%	0%	0%
45.0%	0%	32%	55%	0%	88%	95%
40.8%	0%	78%	58%	20%	83%	6%
56.0%	15%	78%	58%	20%	88%	77%
13.2%	14%	0%	0%	65%	0%	0%
50.2%	66%	0%	84%	84%	2%	65%
14.2%	0%	0%	84%	0%	0%	1%
27.0%	51%	32%	1%	0%	0%	78%
48.7%	0%	67%	58%	0%	78%	89%
40.7%	0%	78%	0%	88%	78%	0%
28.2%	65%	0%	84%	0%	0%	20%
31.0%	51%	0%	83%	0%	0%	52%
1.3%	0%	0%	0%	0%	0%	8%
0.0%	0%	0%	0%	0%	0%	0%
81.0%	77%	78%	97%	91%	88%	55%
29.8%	0%	54%	58%	7%	8%	52%
35.0%	59%	32%	84%	0%	0%	35%
46.8%	68%	54%	1%	66%	14%	78%
18.0%	59%	0%	35%	0%	0%	14%
0.0%	0%	0%	0%	0%	0%	0%
65.0%	56%	78%	0%	91%	88%	77%
28.0%	0%	84%	0%	84%	0%	0%
7.7%	16%	0%	0%	0%	0%	30%
85.2%	86%	88%	97%	92%	97%	51%
90.7%	88%	88%	100%	97%	97%	74%
57.3%	66%	67%	55%	88%	0%	68%
1.2%	0%	0%	0%	0%	0%	7%
46.3%	66%	54%	1%	79%	0%	78%
41.0%	67%	95%	0%	84%	0%	0%