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%3Apakistan Rawsurvey Indiv Individual - Run 8fe01ec...

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

DTEF [indiv]: Predict individual answers for Pakistan (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 56.2%	2nd 58.2%	6th 51.4%	5th 52.6%	1st 58.8%	3rd 56.4%
73.0%	86%	78%	97%	91%	86%	0%
89.8%	93%	87%	100%	97%	88%	74%
89.8%	83%	88%	97%	97%	97%	77%
66.0%	73%	78%	81%	85%	79%	0%
0.0%	0%	0%	0%	0%	0%	0%
90.0%	88%	87%	97%	97%	97%	74%
92.0%	93%	88%	100%	97%	97%	77%
89.2%	88%	78%	97%	97%	97%	78%
90.8%	87%	99%	97%	97%	91%	74%
27.7%	71%	7%	1%	0%	9%	78%
29.5%	99%	0%	0%	0%	78%	0%
0.0%	0%	0%	0%	0%	0%	0%
92.3%	95%	88%	100%	97%	88%	86%
57.8%	97%	68%	1%	92%	0%	89%
93.0%	99%	88%	100%	97%	87%	87%
95.8%	97%	99%	100%	97%	87%	95%
95.8%	98%	88%	100%	97%	97%	95%
94.2%	97%	88%	100%	97%	86%	97%
92.8%	88%	99%	100%	97%	78%	95%
32.2%	93%	0%	7%	7%	0%	86%
27.7%	0%	78%	0%	0%	88%	0%
39.5%	0%	78%	81%	0%	78%	0%
50.3%	0%	78%	58%	0%	88%	78%
37.5%	71%	0%	1%	64%	0%	89%
62.5%	16%	88%	81%	16%	97%	77%
43.3%	12%	78%	0%	7%	86%	77%
42.2%	0%	78%	0%	0%	97%	78%
60.7%	15%	78%	81%	24%	88%	78%
56.0%	11%	78%	0%	87%	86%	74%
48.0%	65%	49%	1%	78%	7%	88%
40.3%	59%	32%	83%	0%	0%	68%
53.0%	19%	78%	0%	88%	83%	50%
20.8%	59%	23%	35%	0%	0%	8%
29.7%	65%	0%	35%	0%	0%	78%
58.5%	19%	78%	81%	87%	86%	0%
15.0%	59%	0%	0%	0%	0%	31%
72.3%	52%	88%	55%	91%	88%	60%
0.0%	0%	0%	0%	0%	0%	0%
14.8%	59%	0%	0%	0%	0%	30%
32.8%	66%	31%	35%	0%	0%	65%
6.3%	7%	0%	0%	0%	0%	31%
32.5%	0%	14%	81%	12%	88%	0%
67.8%	80%	88%	0%	91%	88%	60%
45.0%	59%	54%	1%	78%	0%	78%
86.8%	77%	88%	97%	91%	91%	77%
82.8%	84%	88%	97%	91%	86%	51%
90.7%	86%	89%	97%	97%	97%	78%
88.7%	81%	88%	100%	97%	88%	78%
82.5%	64%	78%	97%	91%	88%	77%
0.0%	0%	0%	0%	0%	0%	0%