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%3Asouth Africa Rawsurvey Indiv Individual - Run db15fdd...

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

DTEF [indiv]: Predict individual answers for South Africa (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	1st 51.0%	3rd 45.3%	6th 35.5%	4th 42.1%	5th 41.8%	2nd 49.9%
96.7%	99%	100%	100%	97%	97%	87%
92.2%	86%	99%	100%	97%	97%	74%
89.2%	83%	98%	97%	97%	86%	74%
45.8%	0%	78%	55%	75%	67%	0%
87.3%	83%	87%	97%	97%	86%	74%
22.2%	36%	7%	1%	0%	24%	65%
70.0%	77%	87%	81%	85%	90%	0%
5.2%	0%	0%	0%	0%	0%	31%
0.0%	0%	0%	0%	0%	0%	0%
60.2%	64%	78%	55%	87%	77%	0%
96.7%	99%	88%	100%	99%	97%	97%
0.0%	0%	0%	0%	0%	0%	0%
42.7%	91%	0%	0%	0%	78%	87%
34.8%	95%	14%	1%	20%	15%	64%
58.7%	91%	8%	0%	91%	88%	74%
24.3%	0%	0%	0%	78%	68%	0%
46.0%	88%	0%	1%	92%	0%	95%
11.5%	1%	67%	1%	0%	0%	0%
91.2%	97%	78%	100%	97%	88%	87%
68.0%	92%	78%	0%	92%	68%	78%
93.2%	88%	99%	100%	88%	97%	87%
84.0%	84%	78%	81%	87%	87%	87%
55.2%	77%	78%	0%	16%	86%	74%
43.8%	72%	0%	35%	73%	19%	64%
46.3%	11%	87%	0%	20%	86%	74%
48.8%	78%	52%	1%	73%	24%	65%
47.7%	78%	52%	1%	66%	0%	89%
40.7%	11%	78%	81%	0%	74%	0%
53.7%	19%	67%	55%	16%	88%	77%
13.8%	6%	0%	0%	9%	0%	68%
89.8%	88%	88%	97%	91%	97%	78%
2.0%	5%	0%	0%	0%	0%	7%
28.5%	59%	0%	84%	0%	0%	28%
33.0%	66%	31%	49%	0%	0%	52%
27.7%	59%	0%	84%	0%	16%	7%
36.0%	66%	54%	1%	7%	24%	64%
22.0%	66%	0%	1%	0%	0%	65%
2.8%	3%	14%	0%	0%	0%	0%
4.2%	0%	0%	0%	0%	0%	25%
17.8%	64%	0%	35%	0%	0%	8%
94.0%	93%	99%	100%	97%	97%	78%
71.0%	16%	78%	81%	87%	87%	77%
1.2%	0%	0%	0%	0%	0%	7%
3.7%	8%	14%	0%	0%	0%	0%
1.2%	0%	0%	0%	0%	0%	7%
24.8%	53%	68%	0%	3%	0%	25%
35.7%	73%	51%	1%	0%	0%	89%
46.2%	78%	54%	1%	66%	0%	78%
73.3%	38%	78%	97%	91%	78%	58%
28.3%	9%	78%	0%	10%	5%	68%