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%3Asingapore Rawsurvey Indiv Individual - Run 1aafc1a...

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

DTEF [indiv]: Predict individual answers for Singapore (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 51.8%	4th 43.8%	5th 33.0%	2nd 51.1%	6th 28.3%	3rd 44.5%
90.5%	88%	87%	100%	97%	97%	74%
53.0%	12%	78%	55%	87%	86%	0%
0.0%	0%	0%	0%	0%	0%	0%
42.7%	20%	0%	83%	88%	0%	65%
62.8%	77%	77%	55%	91%	77%	0%
14.7%	0%	0%	1%	0%	9%	78%
88.8%	90%	78%	97%	97%	97%	74%
60.2%	16%	87%	81%	91%	86%	0%
82.3%	84%	87%	91%	91%	86%	55%
27.8%	77%	0%	1%	0%	0%	89%
79.3%	97%	32%	81%	91%	88%	87%
16.5%	99%	0%	0%	0%	0%	0%
47.8%	99%	89%	0%	99%	0%	0%
62.5%	99%	78%	1%	88%	14%	95%
3.8%	0%	14%	1%	0%	0%	8%
54.3%	93%	49%	1%	88%	0%	95%
94.0%	97%	88%	100%	97%	87%	95%
41.8%	0%	67%	91%	78%	0%	15%
82.8%	70%	87%	81%	97%	88%	74%
57.7%	95%	67%	0%	89%	0%	95%
72.2%	84%	95%	0%	91%	86%	77%
45.5%	68%	52%	1%	74%	0%	78%
43.3%	95%	68%	0%	97%	0%	0%
30.0%	9%	54%	35%	0%	14%	68%
38.8%	15%	78%	55%	7%	78%	0%
37.5%	78%	0%	1%	59%	9%	78%
70.5%	77%	87%	0%	87%	91%	81%
71.0%	93%	78%	81%	88%	86%	0%
30.2%	59%	0%	55%	60%	0%	7%
3.8%	0%	0%	1%	0%	22%	0%
17.2%	0%	0%	83%	0%	0%	20%
28.8%	66%	0%	55%	0%	0%	52%
0.0%	0%	0%	0%	0%	0%	0%
4.2%	3%	14%	0%	0%	0%	8%
34.8%	59%	25%	73%	0%	0%	52%
40.2%	66%	54%	35%	7%	14%	65%
19.3%	1%	0%	84%	0%	0%	31%
20.7%	21%	0%	35%	0%	0%	68%
1.7%	0%	0%	0%	0%	0%	10%
32.7%	69%	32%	1%	7%	9%	78%
2.0%	5%	0%	0%	0%	0%	7%
0.0%	0%	0%	0%	0%	0%	0%
39.3%	79%	68%	0%	89%	0%	0%
55.0%	66%	68%	35%	79%	14%	68%
2.8%	3%	14%	0%	0%	0%	0%
51.7%	66%	66%	1%	88%	0%	89%
68.2%	84%	88%	0%	91%	88%	58%
46.0%	66%	53%	1%	78%	0%	78%
83.7%	77%	78%	97%	97%	88%	65%
49.7%	66%	54%	1%	88%	0%	89%