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 Country%3Aitaly Rawsurvey Indiv Individual - Run c2c8646...

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

DTEF [indiv]: Predict individual answers for Italy (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 41.8%	1st 45.4%	5th 27.2%	3rd 40.5%	6th 25.9%	4th 39.8%
5.7%	20%	0%	0%	7%	0%	7%
14.8%	0%	0%	1%	0%	0%	88%
30.8%	15%	14%	81%	0%	75%	0%
33.8%	71%	0%	55%	0%	9%	68%
18.2%	35%	0%	49%	0%	0%	25%
53.3%	0%	78%	81%	75%	86%	0%
88.8%	87%	87%	97%	91%	97%	74%
65.2%	77%	78%	83%	88%	65%	0%
84.3%	84%	87%	97%	97%	91%	50%
6.8%	27%	0%	0%	0%	0%	14%
43.3%	79%	78%	0%	89%	14%	0%
58.8%	88%	78%	0%	92%	0%	95%
41.5%	0%	89%	0%	92%	0%	68%
28.8%	0%	89%	0%	84%	0%	0%
48.2%	0%	78%	0%	78%	68%	65%
16.2%	16%	14%	1%	0%	14%	52%
96.3%	99%	88%	100%	97%	97%	97%
30.7%	0%	89%	0%	95%	0%	0%
55.3%	98%	56%	0%	89%	0%	89%
49.2%	83%	0%	83%	0%	55%	74%
8.6%	12%	14%	0%	7%		10%
50.2%	65%	54%	1%	78%	14%	89%
1.2%	0%	7%	0%	0%	0%	0%
35.3%	0%	54%	84%	74%	0%	0%
15.8%	0%	0%	71%	0%	24%	0%
13.2%	23%	0%	1%	0%	23%	32%
40.3%	0%	78%	0%	0%	86%	78%
50.5%	0%	52%	83%	0%	79%	89%
0.2%	0%	0%	1%	0%	0%	0%
73.8%	70%	78%	55%	88%	78%	74%
26.2%	27%	54%	0%	0%	46%	30%
37.8%	73%	67%	1%	7%	1%	78%
19.3%	67%	0%	35%	0%	0%	14%
47.2%	73%	54%	83%	7%	14%	52%
28.2%	23%	32%	28%	0%	54%	32%
17.3%	52%	0%	0%	0%	0%	52%
7.8%	16%	0%	0%	0%	0%	31%
14.0%	16%	14%	0%	0%	0%	54%
52.5%	16%	78%	55%	88%	78%	0%
35.5%	66%	31%	35%	0%	16%	65%
45.5%	77%	67%	0%	79%	0%	50%
39.3%	88%	54%	1%	15%	0%	78%
43.3%	79%	89%	0%	92%	0%	0%
41.0%	73%	89%	0%	84%	0%	0%
38.8%	60%	54%	0%	67%	0%	52%
3.7%	0%	14%	0%	0%	0%	8%
88.7%	85%	88%	97%	97%	87%	78%
44.7%	84%	95%	0%	89%	0%	0%
44.2%	66%	52%	1%	78%	0%	68%
1.7%	0%	0%	0%	0%	0%	10%