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%3Aisrael Rawsurvey Indiv Individual - Run 483eb45...

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

DTEF [indiv]: Predict individual answers for Israel (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 52.1%	3rd 52.2%	6th 41.0%	1st 62.3%	5th 41.5%	2nd 52.9%
93.8%	95%	87%	100%	97%	97%	87%
87.7%	80%	87%	97%	97%	91%	74%
51.7%	78%	78%	0%	88%	66%	0%
90.0%	92%	88%	97%	97%	88%	78%
89.0%	88%	87%	97%	97%	88%	77%
0.0%	0%	0%	0%	0%	0%	0%
83.7%	88%	87%	97%	91%	88%	51%
70.3%	74%	98%	81%	85%	84%	0%
15.5%	9%	0%	1%	15%	0%	68%
53.0%	11%	78%	55%	91%	83%	0%
98.2%	99%	99%	100%	97%	97%	97%
76.2%	20%	78%	100%	97%	88%	74%
0.0%	0%	0%	0%	0%	0%	0%
95.3%	99%	99%	100%	97%	88%	89%
92.0%	95%	88%	97%	97%	88%	87%
55.7%	95%	52%	1%	97%	0%	89%
57.3%	0%	78%	81%	97%	88%	0%
58.7%	98%	67%	1%	97%	0%	89%
60.8%	97%	89%	1%	89%	0%	89%
48.3%	0%	95%	0%	95%	0%	100%
71.5%	70%	87%	0%	91%	94%	87%
30.2%	32%	0%	83%	66%	0%	0%
16.5%	2%	39%	58%	0%	0%	0%
78.7%	65%	88%	58%	88%	95%	78%
43.8%	0%	78%	0%	20%	88%	77%
54.2%	80%	0%	83%	84%	0%	78%
16.3%	59%	0%	39%	0%	0%	0%
27.7%	11%	0%	1%	66%	0%	88%
28.5%	60%	32%	1%	0%	0%	78%
50.7%	0%	51%	58%	28%	78%	89%
69.8%	88%	78%	0%	91%	88%	74%
29.8%	59%	0%	84%	0%	16%	20%
7.0%	8%	2%	0%	0%	0%	32%
1.7%	0%	0%	0%	0%	0%	10%
1.7%	0%	0%	0%	0%	0%	10%
33.8%	0%	31%	58%	66%	16%	32%
1.7%	0%	0%	0%	0%	0%	10%
27.5%	59%	0%	35%	0%	7%	64%
45.5%	68%	54%	1%	73%	9%	68%
18.2%	60%	0%	35%	0%	0%	14%
87.8%	79%	88%	100%	97%	86%	77%
70.8%	81%	88%	0%	91%	88%	77%
0.0%	0%	0%	0%	0%	0%	0%
87.2%	80%	88%	97%	92%	88%	78%
88.7%	86%	88%	97%	92%	91%	78%
58.2%	73%	54%	55%	88%	11%	68%
60.0%	52%	78%	0%	91%	88%	51%
38.8%	66%	0%	1%	88%	0%	78%
49.2%	73%	54%	1%	89%	0%	78%
44.0%	77%	95%	0%	92%	0%	0%