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%3Aislam Rawsurvey Indiv Individual - Run 9ce2119...

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

DTEF [indiv]: Predict individual answers for Islam (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 44.6%	2nd 52.9%	6th 42.8%	1st 54.1%	5th 44.0%	3rd 46.7%
87.2%	84%	77%	97%	97%	94%	74%
95.8%	95%	99%	100%	97%	97%	87%
5.2%	0%	0%	0%	0%	0%	31%
19.8%	16%	0%	35%	0%	0%	68%
77.0%	67%	87%	81%	97%	81%	49%
18.8%	0%	0%	35%	0%	0%	78%
67.5%	81%	78%	81%	88%	77%	0%
94.2%	98%	87%	100%	97%	97%	86%
92.3%	95%	78%	100%	97%	97%	87%
90.5%	88%	87%	100%	97%	97%	74%
55.3%	93%	52%	0%	92%	0%	95%
96.3%	99%	88%	100%	97%	97%	97%
26.0%	0%	78%	0%	78%	0%	0%
0.0%	0%	0%	0%	0%	0%	0%
27.0%	0%	68%	1%	78%	0%	15%
23.3%	72%	52%	1%	0%	0%	15%
29.8%	32%	68%	1%	78%	0%	0%
96.0%	97%	88%	100%	97%	97%	97%
55.2%	0%	78%	83%	92%	78%	0%
45.8%	91%	0%	0%	89%	0%	95%
38.3%	66%	7%	1%	67%	0%	89%
66.7%	19%	78%	97%	31%	97%	78%
20.7%	2%	54%	1%	20%	15%	32%
14.0%	0%	0%	0%	84%	0%	0%
46.7%	32%	78%	81%	12%	77%	0%
32.3%	0%	39%	81%	0%	74%	0%
36.7%	0%	52%	81%	0%	87%	0%
72.5%	84%	88%	0%	88%	88%	87%
4.2%	25%	0%	0%	0%	0%	0%
27.8%	77%	0%	1%	0%	0%	89%
54.3%	19%	78%	55%	88%	86%	0%
72.0%	0%	78%	97%	91%	88%	78%
35.0%	0%	14%	55%	77%	64%	0%
33.2%	42%	45%	0%	9%	35%	68%
17.5%	67%	0%	1%	0%	7%	30%
0.0%	0%	0%	0%	0%	0%	0%
0.0%	0%	0%	0%	0%	0%	0%
76.7%	19%	88%	97%	91%	88%	77%
63.8%	21%	78%	55%	91%	88%	50%
58.7%	19%	78%	81%	88%	86%	0%
37.5%	79%	67%	1%	0%	0%	78%
88.3%	70%	88%	100%	97%	97%	78%
17.7%	16%	38%	0%	0%	0%	52%
14.5%	26%	14%	39%	0%	0%	8%
45.2%	66%	54%	1%	72%	0%	78%
50.5%	60%	80%	1%	67%	27%	68%
31.3%	66%	54%	1%	67%	0%	0%
91.8%	91%	88%	100%	97%	97%	78%
89.5%	88%	89%	97%	97%	88%	78%
34.7%	66%	52%	1%	0%	0%	89%