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	6th 49.4%	4th 50.6%	3rd 52.0%	1st 55.9%	2nd 52.9%	5th 50.6%
80.7%	67%	87%	97%	91%	87%	55%
97.5%	93%	99%	100%	99%	97%	97%
1.2%	0%	0%	0%	0%	0%	7%
94.5%	98%	88%	100%	97%	97%	87%
91.2%	92%	87%	100%	97%	97%	74%
87.5%	84%	87%	97%	97%	86%	74%
33.3%	31%	7%	49%	73%	8%	32%
91.7%	86%	95%	100%	97%	91%	81%
45.2%	66%	0%	35%	88%	14%	68%
90.0%	95%	88%	97%	97%	86%	77%
59.7%	98%	7%	81%	0%	97%	75%
98.5%	99%	99%	100%	99%	97%	97%
57.5%	0%	87%	97%	97%	64%	0%
65.7%	97%	32%	81%	0%	97%	87%
72.8%	7%	78%	81%	97%	87%	87%
57.3%	90%	0%	81%	0%	86%	87%
28.0%	2%	38%	11%	92%	0%	25%
96.8%	97%	99%	100%	97%	91%	97%
38.5%	0%	79%	0%	84%	0%	68%
31.3%	12%	7%	81%	0%	88%	0%
41.8%	1%	88%	0%	0%	87%	75%
92.0%	88%	88%	100%	92%	97%	87%
0.2%	1%	0%	0%	0%	0%	0%
76.8%	93%	99%	0%	91%	91%	87%
41.7%	86%	0%	84%	66%	0%	14%
65.3%	67%	78%	0%	87%	86%	74%
17.2%	5%	8%	58%	0%	24%	8%
87.0%	84%	78%	97%	88%	88%	87%
5.8%	0%	0%	35%	0%	0%	0%
45.7%	0%	88%	0%	20%	88%	78%
28.0%	16%	0%	84%	0%	0%	68%
88.0%	88%	78%	100%	97%	88%	77%
21.0%	73%	0%	1%	0%	0%	52%
67.8%	65%	88%	0%	91%	86%	77%
78.0%	64%	78%	97%	88%	86%	55%
0.0%	0%	0%	0%	0%	0%	0%
0.0%	0%	0%	0%	0%	0%	0%
1.2%	7%	0%	0%	0%	0%	0%
50.2%	64%	54%	35%	66%	14%	68%
51.8%	16%	78%	0%	88%	78%	51%
0.0%	0%	0%	0%	0%	0%	0%
94.2%	96%	88%	100%	97%	97%	87%
73.0%	84%	78%	97%	91%	88%	0%
0.0%	0%	0%	0%	0%	0%	0%
82.7%	63%	78%	97%	97%	86%	75%
4.7%	21%	0%	0%	0%	0%	7%
36.3%	25%	54%	28%	54%	5%	52%
85.8%	77%	78%	97%	97%	88%	78%
41.2%	74%	89%	0%	84%	0%	0%
0.0%	0%	0%	0%	0%	0%	0%