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%3Abangladesh Rawsurvey Indiv Individual - Run c7dd203...

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

DTEF [indiv]: Predict individual answers for Bangladesh (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 50.7%	2nd 52.9%	6th 46.1%	1st 54.2%	3rd 50.7%	5th 48.2%
7.8%	39%	0%	0%	0%	0%	8%
95.8%	95%	99%	100%	97%	97%	87%
72.8%	15%	87%	97%	97%	91%	50%
89.5%	83%	99%	97%	97%	86%	75%
67.3%	15%	87%	97%	91%	64%	50%
49.7%	52%	78%	81%	87%	0%	0%
86.3%	90%	87%	97%	97%	97%	50%
95.8%	95%	99%	100%	97%	97%	87%
83.8%	85%	99%	91%	91%	86%	51%
90.5%	83%	95%	97%	97%	97%	74%
29.5%	77%	0%	0%	0%	0%	100%
98.2%	99%	99%	100%	97%	97%	97%
56.8%	91%	0%	83%	1%	88%	78%
95.8%	97%	99%	100%	97%	88%	94%
15.0%	11%	0%	1%	78%	0%	0%
38.8%	65%	54%	1%	88%	0%	25%
93.2%	99%	88%	100%	97%	88%	87%
96.7%	96%	99%	100%	97%	91%	97%
3.3%	20%	0%	0%	0%	0%	0%
95.3%	97%	95%	100%	97%	86%	97%
42.7%	92%	0%	0%	84%	0%	80%
74.2%	83%	87%	0%	91%	97%	87%
72.2%	19%	78%	83%	88%	88%	77%
59.0%	7%	78%	0%	91%	91%	87%
23.8%	0%	65%	0%	0%	78%	0%
2.5%	9%	0%	0%	6%	0%	0%
27.5%	0%	78%	0%	0%	87%	0%
73.8%	88%	87%	0%	91%	86%	91%
57.7%	58%	78%	55%	77%	78%	0%
58.8%	77%	78%	0%	25%	86%	87%
23.3%	13%	14%	28%	6%	54%	25%
74.3%	15%	78%	97%	91%	88%	77%
3.2%	9%	0%	0%	0%	0%	10%
6.7%	5%	0%	0%	0%	0%	35%
2.7%	16%	0%	0%	0%	0%	0%
5.8%	0%	10%	0%	0%	0%	25%
14.8%	59%	0%	0%	0%	0%	30%
15.8%	5%	0%	83%	0%	0%	7%
8.3%	19%	0%	0%	0%	0%	31%
15.2%	71%	0%	0%	0%	0%	20%
4.8%	1%	0%	28%	0%	0%	0%
90.5%	84%	88%	100%	97%	97%	77%
0.0%	0%	0%	0%	0%	0%	0%
84.5%	62%	88%	97%	97%	86%	77%
24.0%	66%	52%	1%	0%	0%	25%
41.7%	66%	54%	1%	79%	0%	50%
83.8%	86%	88%	97%	91%	89%	52%
86.2%	64%	95%	97%	97%	86%	78%
0.0%	0%	0%	0%	0%	0%	0%
84.2%	56%	87%	97%	97%	91%	77%