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%3Aspain Rawsurvey Indiv Individual - Run 3d04d4a...

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

DTEF [indiv]: Predict individual answers for Spain (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 43.1%	2nd 49.3%	6th 35.9%	1st 53.6%	5th 38.8%	3rd 43.2%
43.2%	65%	0%	35%	88%	7%	64%
87.3%	80%	87%	100%	97%	86%	74%
88.3%	84%	87%	97%	97%	91%	74%
65.7%	74%	87%	55%	91%	87%	0%
54.5%	0%	78%	58%	92%	89%	10%
14.2%	11%	0%	0%	0%	74%	0%
81.5%	74%	88%	97%	91%	88%	51%
2.3%	0%	0%	0%	0%	0%	14%
78.8%	77%	77%	97%	87%	86%	49%
12.5%	1%	0%	35%	0%	0%	39%
58.7%	95%	78%	1%	89%	0%	89%
96.2%	97%	99%	100%	97%	87%	97%
91.5%	99%	78%	97%	97%	91%	87%
47.3%	0%	89%	0%	95%	0%	100%
31.7%	0%	95%	0%	95%	0%	0%
48.3%	95%	95%	0%	100%	0%	0%
40.7%	19%	78%	81%	0%	66%	0%
41.7%	20%	52%	1%	88%	0%	89%
54.5%	0%	78%	0%	97%	78%	74%
77.3%	80%	32%	81%	97%	87%	87%
39.8%	0%	54%	1%	74%	32%	78%
73.2%	88%	87%	0%	91%	86%	87%
34.3%	15%	26%	0%	0%	91%	74%
66.0%	0%	78%	55%	88%	88%	87%
25.0%	3%	0%	58%	0%	0%	89%
48.7%	98%	95%	0%	99%	0%	0%
50.5%	79%	78%	0%	0%	86%	60%
30.2%	0%	14%	81%	0%	86%	0%
24.3%	39%	0%	84%	23%	0%	0%
56.0%	0%	78%	81%	16%	87%	74%
2.5%	7%	0%	0%	0%	0%	8%
25.8%	65%	0%	83%	0%	0%	7%
23.2%	73%	0%	35%	0%	0%	31%
34.0%	68%	0%	84%	0%	0%	52%
0.0%	0%	0%	0%	0%	0%	0%
25.0%	67%	0%	83%	0%	0%	0%
24.2%	35%	0%	58%	0%	0%	52%
47.2%	16%	51%	55%	87%	74%	0%
16.5%	69%	0%	0%	0%	0%	30%
34.3%	66%	54%	1%	0%	7%	78%
46.0%	51%	54%	1%	88%	14%	68%
82.7%	62%	78%	97%	91%	91%	77%
58.2%	36%	78%	0%	88%	87%	60%
42.2%	74%	95%	0%	84%	0%	0%
31.2%	0%	95%	0%	92%	0%	0%
44.0%	77%	95%	0%	92%	0%	0%
1.3%	0%	0%	0%	0%	0%	8%
39.2%	78%	0%	1%	78%	0%	78%
54.5%	19%	78%	0%	91%	88%	51%
3.7%	0%	0%	0%	0%	7%	15%