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%3Akorea South Rawsurvey Indiv Individual - Run d0a0ee8...

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

DTEF [indiv]: Predict individual answers for Korea South (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	2nd 50.8%	5th 43.4%	4th 45.4%	3rd 47.1%	6th 42.3%	1st 51.8%
27.8%	77%	0%	1%	0%	0%	89%
59.8%	11%	87%	55%	91%	64%	51%
78.2%	62%	78%	97%	97%	86%	49%
65.3%	62%	78%	81%	85%	86%	0%
84.3%	88%	87%	97%	91%	88%	55%
71.8%	87%	87%	0%	97%	86%	74%
34.2%	71%	0%	55%	7%	7%	65%
93.2%	92%	99%	100%	97%	97%	74%
92.2%	93%	88%	100%	97%	97%	78%
83.7%	88%	88%	97%	91%	88%	50%
57.0%	97%	78%	1%	88%	0%	78%
24.0%	1%	54%	1%	88%	0%	0%
42.5%	12%	0%	81%	0%	87%	75%
46.2%	95%	0%	1%	92%	0%	89%
31.0%	0%	7%	91%	0%	88%	0%
53.3%	97%	39%	0%	24%	86%	74%
26.7%	92%	0%	0%	0%	0%	68%
29.7%	0%	99%	1%	78%	0%	0%
97.8%	99%	99%	100%	97%	97%	95%
56.3%	81%	14%	81%	0%	88%	74%
42.8%	34%	49%	55%	32%	9%	78%
41.7%	15%	78%	55%	24%	78%	0%
57.3%	81%	78%	0%	25%	86%	74%
29.5%	23%	54%	35%	0%	0%	65%
23.5%	20%	0%	55%	59%	0%	7%
67.7%	81%	78%	0%	87%	86%	74%
25.3%	70%	14%	0%	0%	0%	68%
83.2%	84%	87%	81%	87%	86%	74%
76.8%	63%	78%	97%	47%	88%	88%
33.2%	0%	53%	58%	0%	88%	0%
52.7%	69%	54%	55%	59%	14%	65%
5.7%	9%	0%	0%	0%	0%	25%
41.7%	59%	32%	84%	0%	7%	68%
35.3%	30%	7%	84%	0%	26%	65%
44.0%	19%	14%	55%	88%	88%	0%
25.8%	7%	0%	84%	0%	0%	64%
47.3%	63%	31%	55%	59%	24%	52%
63.0%	16%	78%	55%	88%	86%	55%
81.3%	77%	78%	97%	88%	88%	60%
1.7%	0%	0%	0%	0%	0%	10%
31.0%	78%	0%	1%	15%	14%	78%
45.3%	66%	54%	1%	79%	7%	65%
0.8%	5%	0%	0%	0%	0%	0%
47.3%	59%	68%	1%	78%	0%	78%
8.8%	21%	0%	1%	0%	0%	31%
19.8%	35%	0%	84%	0%	0%	0%
32.8%	17%	14%	35%	59%	7%	65%
24.0%	43%	0%	1%	65%	0%	35%
89.8%	88%	88%	100%	97%	88%	78%
5.8%	5%	0%	0%	0%	0%	30%