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%3Ahinduism Rawsurvey Indiv Individual - Run 25e67de...

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

DTEF [indiv]: Predict individual answers for Hinduism (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	3rd 53.1%	5th 51.7%	4th 52.6%	1st 54.3%	2nd 53.8%	6th 50.6%
86.5%	83%	87%	97%	91%	87%	74%
98.2%	99%	99%	100%	97%	97%	97%
1.2%	0%	0%	0%	0%	0%	7%
95.3%	92%	99%	100%	97%	97%	87%
93.2%	92%	99%	100%	97%	97%	74%
88.7%	88%	87%	97%	97%	86%	77%
37.0%	59%	0%	58%	73%	0%	32%
93.0%	98%	95%	100%	97%	91%	77%
30.7%	66%	0%	35%	15%	0%	68%
88.8%	88%	88%	97%	97%	86%	77%
53.7%	81%	7%	81%	0%	78%	75%
98.7%	99%	100%	100%	97%	97%	99%
60.7%	0%	87%	97%	97%	83%	0%
63.2%	90%	32%	81%	0%	89%	87%
69.3%	0%	78%	81%	97%	86%	74%
56.5%	83%	0%	81%	0%	88%	87%
30.7%	0%	54%	11%	68%	51%	0%
96.8%	97%	99%	100%	97%	91%	97%
27.2%	0%	79%	0%	84%	0%	0%
47.5%	35%	7%	81%	0%	88%	74%
44.8%	19%	88%	0%	0%	87%	75%
94.3%	93%	88%	100%	91%	97%	97%
0.7%	1%	0%	0%	3%	0%	0%
92.5%	90%	99%	97%	91%	91%	87%
28.0%	20%	0%	83%	65%	0%	0%
69.3%	77%	78%	0%	88%	86%	87%
20.0%	15%	8%	58%	0%	31%	8%
68.8%	69%	78%	0%	91%	88%	87%
9.2%	0%	0%	55%	0%	0%	0%
47.7%	19%	78%	0%	28%	83%	78%
35.2%	59%	0%	84%	0%	0%	68%
88.5%	88%	78%	100%	91%	97%	77%
21.8%	66%	0%	0%	0%	0%	65%
69.7%	77%	88%	0%	88%	88%	77%
79.8%	75%	78%	97%	91%	83%	55%
0.0%	0%	0%	0%	0%	0%	0%
0.0%	0%	0%	0%	0%	0%	0%
3.2%	12%	0%	0%	0%	0%	7%
52.5%	69%	54%	35%	73%	32%	52%
54.5%	73%	78%	0%	88%	88%	0%
4.7%	28%	0%	0%	0%	0%	0%
92.8%	88%	88%	100%	97%	97%	87%
81.8%	86%	88%	97%	91%	78%	51%
0.0%	0%	0%	0%	0%	0%	0%
88.7%	88%	87%	100%	97%	86%	74%
1.2%	0%	0%	0%	0%	0%	7%
39.3%	42%	54%	28%	60%	0%	52%
87.3%	77%	88%	97%	97%	88%	77%
41.2%	74%	89%	0%	84%	0%	0%
0.0%	0%	0%	0%	0%	0%	0%