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	5th 44.5%	2nd 52.6%	6th 42.8%	1st 55.6%	4th 44.6%	3rd 45.3%
86.5%	88%	77%	97%	97%	86%	74%
96.3%	98%	99%	100%	97%	97%	87%
5.0%	0%	0%	0%	0%	0%	30%
19.8%	16%	0%	35%	0%	0%	68%
76.8%	77%	87%	81%	90%	77%	49%
29.8%	66%	0%	35%	0%	0%	78%
59.5%	16%	78%	81%	91%	91%	0%
93.7%	95%	87%	100%	97%	97%	86%
90.8%	95%	78%	100%	97%	97%	78%
90.0%	88%	87%	100%	97%	94%	74%
54.7%	89%	52%	0%	92%	0%	95%
98.2%	99%	99%	100%	97%	97%	97%
28.7%	16%	78%	0%	78%	0%	0%
0.0%	0%	0%	0%	0%	0%	0%
23.5%	0%	68%	1%	72%	0%	0%
26.0%	72%	68%	1%	0%	0%	15%
25.7%	7%	54%	1%	78%	0%	14%
95.7%	97%	88%	100%	97%	97%	95%
58.2%	0%	78%	83%	97%	91%	0%
54.8%	88%	54%	0%	92%	0%	95%
39.3%	65%	7%	1%	74%	0%	89%
71.0%	35%	78%	97%	31%	98%	87%
21.5%	11%	54%	1%	0%	31%	32%
13.2%	0%	0%	0%	79%	0%	0%
43.2%	7%	78%	81%	16%	77%	0%
34.5%	0%	52%	81%	0%	74%	0%
27.8%	0%	0%	81%	0%	86%	0%
69.5%	64%	88%	0%	91%	88%	86%
1.5%	9%	0%	0%	0%	0%	0%
22.0%	53%	0%	1%	64%	0%	14%
54.2%	16%	78%	55%	88%	88%	0%
76.7%	28%	78%	97%	91%	88%	78%
32.5%	0%	14%	55%	77%	49%	0%
26.7%	46%	10%	0%	6%	44%	54%
17.3%	66%	0%	1%	0%	7%	30%
0.0%	0%	0%	0%	0%	0%	0%
0.0%	0%	0%	0%	0%	0%	0%
79.8%	65%	88%	97%	91%	88%	50%
63.2%	19%	78%	55%	88%	88%	51%
58.2%	16%	78%	81%	88%	86%	0%
38.2%	59%	80%	1%	0%	0%	89%
91.3%	88%	88%	100%	97%	97%	78%
21.0%	20%	54%	0%	0%	0%	52%
18.0%	23%	14%	39%	7%	17%	8%
45.2%	73%	54%	1%	65%	0%	78%
51.8%	79%	54%	1%	84%	25%	68%
42.0%	66%	54%	1%	79%	0%	52%
89.8%	88%	88%	100%	97%	88%	78%
81.2%	64%	78%	97%	97%	86%	65%
33.0%	56%	52%	1%	0%	0%	89%