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%3Amorocco Rawsurvey Indiv Individual - Run 72d6c81...

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

DTEF [indiv]: Predict individual answers for Morocco (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 49.0%	2nd 59.1%	3rd 55.4%	4th 53.5%	1st 61.4%	6th 46.5%
95.5%	93%	99%	100%	97%	97%	87%
88.8%	87%	87%	97%	91%	97%	74%
62.5%	19%	88%	92%	88%	88%	0%
41.8%	61%	78%	35%	0%	77%	0%
88.0%	86%	88%	97%	97%	83%	77%
84.5%	84%	88%	97%	91%	88%	59%
94.3%	98%	87%	100%	97%	97%	87%
94.0%	95%	88%	100%	97%	97%	87%
67.5%	81%	78%	81%	88%	77%	0%
92.5%	88%	99%	100%	97%	97%	74%
96.0%	99%	88%	100%	97%	97%	95%
93.2%	99%	88%	100%	97%	88%	87%
56.5%	0%	78%	97%	97%	67%	0%
61.0%	98%	52%	1%	88%	38%	89%
0.0%	0%	0%	0%	0%	0%	0%
0.0%	0%	0%	0%	0%	0%	0%
96.3%	99%	88%	100%	97%	97%	97%
94.8%	97%	89%	100%	97%	97%	89%
29.8%	32%	68%	1%	78%	0%	0%
44.3%	0%	0%	100%	0%	79%	87%
75.2%	82%	78%	97%	19%	97%	78%
40.7%	0%	78%	0%	0%	88%	78%
0.0%	0%	0%	0%	0%	0%	0%
48.8%	65%	32%	35%	73%	0%	88%
76.8%	62%	78%	81%	88%	78%	74%
37.5%	2%	52%	83%	0%	88%	0%
57.2%	74%	78%	0%	7%	97%	87%
43.5%	0%	78%	0%	0%	88%	95%
36.7%	0%	52%	81%	0%	87%	0%
76.3%	88%	99%	0%	97%	87%	87%
70.0%	19%	78%	97%	88%	88%	50%
34.7%	59%	0%	84%	0%	0%	65%
2.2%	5%	0%	0%	0%	0%	8%
0.0%	0%	0%	0%	0%	0%	0%
1.5%	9%	0%	0%	0%	0%	0%
2.0%	12%	0%	0%	0%	0%	0%
80.3%	52%	78%	97%	91%	87%	77%
73.5%	27%	78%	97%	91%	88%	60%
0.0%	0%	0%	0%	0%	0%	0%
6.3%	38%	0%	0%	0%	0%	0%
92.8%	86%	99%	100%	97%	97%	78%
66.7%	65%	78%	0%	91%	88%	78%
68.5%	88%	88%	55%	92%	88%	0%
48.7%	66%	68%	1%	79%	0%	78%
43.8%	0%	88%	81%	6%	88%	0%
30.8%	0%	14%	83%	0%	88%	0%
91.2%	88%	88%	100%	97%	97%	77%
89.0%	83%	88%	100%	97%	88%	78%
31.3%	66%	54%	1%	67%	0%	0%
0.0%	0%	0%	0%	0%	0%	0%