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%3Abrazil Rawsurvey Indiv Individual - Run 74103e4...

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

DTEF [indiv]: Predict individual answers for Brazil (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	3rd 54.2%	2nd 58.0%	6th 49.5%	1st 61.4%	4th 53.3%	5th 51.8%
46.8%	0%	78%	35%	87%	81%	0%
69.7%	81%	87%	81%	91%	78%	0%
95.8%	95%	99%	100%	97%	97%	87%
83.3%	83%	78%	100%	91%	97%	51%
95.2%	92%	98%	100%	97%	97%	87%
85.3%	83%	98%	97%	97%	86%	51%
91.2%	88%	99%	97%	97%	88%	78%
62.8%	73%	54%	83%	88%	14%	65%
97.0%	96%	95%	100%	97%	97%	97%
22.8%	71%	0%	1%	0%	0%	65%
16.3%	98%	0%	0%	0%	0%	0%
5.7%	20%	14%	0%	0%	0%	0%
96.0%	99%	88%	100%	97%	97%	95%
93.5%	93%	88%	100%	97%	88%	95%
98.2%	99%	99%	100%	97%	97%	97%
23.8%	0%	54%	1%	88%	0%	0%
94.5%	97%	88%	100%	97%	88%	97%
38.8%	0%	68%	0%	97%	0%	68%
96.0%	97%	88%	100%	97%	97%	97%
33.0%	0%	49%	1%	88%	35%	25%
46.5%	73%	49%	1%	78%	0%	78%
28.8%	0%	14%	81%	0%	78%	0%
46.2%	0%	78%	0%	24%	97%	78%
29.3%	0%	0%	0%	0%	87%	89%
64.0%	32%	77%	0%	91%	97%	87%
41.2%	15%	78%	55%	16%	83%	0%
58.2%	15%	78%	58%	32%	88%	78%
0.0%	0%	0%	0%	0%	0%	0%
75.8%	93%	87%	0%	97%	91%	87%
27.0%	78%	32%	0%	52%	0%	0%
27.0%	38%	0%	58%	0%	14%	52%
25.5%	66%	0%	35%	0%	0%	52%
70.0%	16%	78%	97%	91%	88%	50%
22.3%	66%	0%	0%	0%	0%	68%
75.0%	16%	78%	97%	91%	91%	77%
29.0%	59%	0%	84%	0%	0%	31%
4.3%	16%	0%	0%	0%	0%	10%
42.5%	22%	49%	83%	78%	23%	0%
57.8%	16%	78%	0%	91%	88%	74%
42.7%	73%	52%	35%	7%	24%	65%
0.0%	0%	0%	0%	0%	0%	0%
2.8%	3%	14%	0%	0%	0%	0%
91.7%	90%	88%	100%	97%	97%	78%
74.7%	84%	88%	97%	91%	88%	0%
92.0%	84%	99%	100%	97%	97%	75%
45.7%	59%	52%	1%	84%	0%	78%
87.7%	83%	88%	97%	92%	88%	78%
41.2%	84%	79%	0%	84%	0%	0%
92.2%	84%	88%	100%	97%	97%	87%
48.3%	78%	54%	1%	78%	14%	65%