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	2nd 61.7%	3rd 60.7%	5th 51.8%	1st 63.0%	4th 54.2%	6th 51.7%
91.2%	92%	87%	100%	97%	97%	74%
95.2%	96%	87%	100%	97%	97%	94%
90.5%	88%	98%	100%	97%	86%	74%
0.0%	0%	0%	0%	0%	0%	0%
22.5%	0%	26%	35%	0%	74%	0%
96.2%	98%	99%	100%	97%	97%	86%
19.5%	27%	0%	1%	0%	0%	89%
90.7%	88%	88%	97%	97%	97%	77%
75.3%	84%	87%	97%	97%	87%	0%
92.8%	98%	88%	100%	97%	97%	77%
0.0%	0%	0%	0%	0%	0%	0%
96.3%	99%	88%	100%	97%	97%	97%
70.8%	90%	78%	81%	0%	89%	87%
32.8%	0%	54%	1%	88%	22%	32%
48.8%	99%	95%	0%	99%	0%	0%
96.5%	99%	89%	100%	97%	97%	97%
59.2%	95%	68%	1%	88%	14%	89%
94.8%	99%	88%	100%	97%	88%	97%
26.2%	0%	67%	1%	89%	0%	0%
96.0%	97%	88%	100%	97%	97%	97%
30.2%	0%	14%	81%	0%	86%	0%
95.2%	93%	87%	100%	97%	97%	97%
75.2%	88%	99%	0%	91%	86%	87%
6.5%	0%	0%	39%	0%	0%	0%
46.0%	97%	95%	0%	84%	0%	0%
55.2%	0%	78%	83%	4%	88%	78%
38.5%	66%	52%	35%	0%	0%	78%
59.7%	88%	88%	0%	16%	88%	78%
38.2%	60%	0%	0%	89%	0%	80%
69.7%	79%	78%	0%	87%	97%	77%
72.2%	65%	78%	55%	91%	86%	58%
86.2%	73%	88%	97%	91%	91%	77%
25.0%	59%	0%	84%	0%	0%	7%
3.8%	15%	2%	0%	6%	0%	0%
24.0%	60%	0%	84%	0%	0%	0%
82.8%	55%	88%	97%	91%	88%	78%
52.0%	86%	54%	73%	7%	24%	68%
0.0%	0%	0%	0%	0%	0%	0%
61.3%	79%	78%	35%	88%	88%	0%
52.8%	19%	67%	0%	88%	88%	55%
48.3%	16%	14%	81%	91%	88%	0%
88.8%	84%	78%	100%	97%	97%	77%
2.0%	0%	0%	0%	0%	0%	12%
46.2%	66%	54%	35%	78%	12%	32%
44.5%	88%	95%	0%	84%	0%	0%
90.2%	91%	78%	100%	97%	97%	78%
50.5%	78%	67%	1%	79%	0%	78%
89.0%	83%	88%	100%	97%	88%	78%
42.7%	66%	54%	1%	67%	0%	68%
88.2%	84%	88%	97%	97%	86%	77%