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%3Ajapan Rawsurvey Indiv Individual - Run 5f3e33a...

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

DTEF [indiv]: Predict individual answers for Japan (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 57.9%	2nd 62.2%	5th 55.9%	1st 63.8%	3rd 59.6%	6th 52.2%
98.2%	99%	99%	100%	97%	97%	97%
48.3%	0%	77%	55%	87%	71%	0%
34.7%	75%	78%	55%	0%	0%	0%
98.0%	98%	99%	100%	97%	97%	97%
56.8%	71%	78%	83%	31%	78%	0%
60.0%	86%	0%	97%	91%	86%	0%
59.8%	15%	78%	91%	87%	88%	0%
89.3%	88%	88%	97%	97%	88%	78%
94.2%	95%	99%	100%	97%	97%	77%
98.2%	99%	99%	100%	97%	97%	97%
98.2%	99%	99%	100%	97%	97%	97%
54.7%	89%	52%	1%	97%	0%	89%
62.8%	98%	80%	1%	95%	14%	89%
74.8%	75%	99%	0%	97%	91%	87%
13.3%	0%	0%	0%	0%	0%	80%
43.7%	0%	88%	0%	87%	87%	0%
59.0%	0%	88%	81%	97%	88%	0%
96.0%	97%	99%	100%	97%	88%	95%
94.7%	99%	88%	100%	97%	97%	87%
96.8%	100%	88%	100%	99%	97%	97%
94.2%	92%	88%	100%	91%	97%	97%
28.5%	58%	0%	35%	0%	0%	78%
28.5%	0%	54%	35%	0%	16%	66%
0.0%	0%	0%	0%	0%	0%	0%
47.5%	79%	68%	0%	84%	0%	54%
30.3%	66%	32%	84%	0%	0%	0%
11.8%	20%	0%	28%	23%	0%	0%
43.8%	19%	78%	0%	0%	88%	78%
56.7%	0%	78%	0%	88%	97%	77%
93.7%	93%	88%	100%	97%	97%	87%
88.0%	93%	78%	100%	91%	88%	78%
4.3%	1%	0%	0%	0%	0%	25%
3.3%	12%	0%	0%	0%	0%	8%
86.7%	79%	88%	97%	91%	88%	77%
2.7%	12%	0%	0%	0%	0%	4%
32.5%	59%	0%	84%	0%	0%	52%
28.0%	52%	0%	84%	0%	0%	32%
1.7%	0%	0%	0%	0%	0%	10%
59.8%	16%	78%	91%	88%	86%	0%
91.3%	88%	88%	100%	97%	97%	78%
92.3%	93%	89%	100%	97%	97%	78%
43.8%	66%	52%	1%	66%	0%	78%
50.2%	65%	54%	1%	79%	34%	68%
91.2%	88%	88%	100%	97%	97%	77%
20.2%	0%	0%	0%	0%	84%	37%
52.5%	56%	78%	0%	88%	87%	6%
55.2%	77%	78%	0%	88%	88%	0%
84.0%	77%	99%	97%	92%	88%	51%
81.3%	65%	78%	97%	91%	97%	60%
94.7%	88%	99%	100%	97%	97%	87%