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%3Aaustralia Rawsurvey Indiv Individual - Run a8511c7...

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

DTEF [indiv]: Predict individual answers for Australia (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 47.1%	2nd 58.1%	5th 45.2%	1st 66.1%	3rd 50.3%	6th 37.3%
20.5%	0%	14%	35%	0%	74%	0%
80.0%	80%	87%	81%	97%	86%	49%
92.3%	98%	88%	100%	97%	97%	74%
89.2%	92%	78%	97%	97%	97%	74%
0.0%	0%	0%	0%	0%	0%	0%
92.2%	92%	99%	97%	97%	94%	74%
6.5%	0%	0%	0%	0%	0%	39%
82.3%	84%	78%	97%	97%	88%	50%
90.0%	88%	87%	97%	97%	97%	74%
92.3%	98%	88%	100%	97%	97%	74%
48.8%	99%	95%	0%	99%	0%	0%
1.3%	0%	0%	0%	0%	0%	8%
59.2%	0%	89%	81%	97%	88%	0%
56.0%	0%	78%	81%	91%	86%	0%
91.0%	97%	78%	97%	97%	88%	89%
44.0%	0%	89%	0%	95%	0%	80%
77.8%	53%	78%	81%	97%	83%	75%
41.0%	0%	89%	0%	89%	0%	68%
26.8%	71%	0%	1%	0%	0%	89%
94.7%	99%	88%	100%	97%	97%	87%
45.0%	97%	89%	0%	84%	0%	0%
55.5%	0%	78%	81%	87%	87%	0%
14.0%	0%	0%	84%	0%	0%	0%
41.7%	73%	0%	35%	74%	0%	68%
37.8%	0%	78%	83%	0%	66%	0%
43.7%	0%	87%	0%	87%	88%	0%
40.5%	66%	32%	1%	66%	0%	78%
0.0%	0%	0%	0%	0%	0%	0%
48.2%	73%	52%	1%	74%	0%	89%
70.5%	84%	78%	0%	87%	97%	77%
17.7%	67%	0%	39%	0%	0%	0%
13.2%	13%	0%	35%	0%	0%	31%
78.2%	65%	78%	97%	91%	88%	50%
52.0%	0%	51%	35%	88%	87%	51%
18.3%	49%	0%	0%	2%	5%	54%
45.0%	16%	78%	0%	88%	88%	0%
31.5%	66%	54%	1%	0%	0%	68%
50.3%	0%	78%	58%	88%	78%	0%
63.3%	19%	78%	55%	91%	86%	51%
65.5%	73%	67%	0%	88%	88%	77%
26.3%	74%	0%	0%	84%	0%	0%
0.0%	0%	0%	0%	0%	0%	0%
89.3%	77%	88%	97%	97%	88%	89%
62.0%	64%	78%	55%	97%	78%	0%
70.0%	77%	88%	97%	92%	66%	0%
43.8%	73%	95%	0%	95%	0%	0%
60.3%	35%	78%	81%	91%	77%	0%
43.8%	79%	95%	0%	89%	0%	0%
34.3%	0%	14%	81%	25%	86%	0%
85.3%	62%	88%	97%	97%	91%	77%