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%3Amalaysia Rawsurvey Indiv Individual - Run 3c4cdae...

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

DTEF [indiv]: Predict individual answers for Malaysia (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	1st 52.9%	5th 40.4%	2nd 45.2%	3rd 44.2%	4th 42.6%	6th 37.4%
91.2%	92%	87%	100%	97%	97%	74%
53.2%	16%	87%	55%	87%	74%	0%
72.3%	67%	87%	97%	91%	86%	6%
62.7%	70%	87%	55%	87%	77%	0%
70.0%	74%	99%	81%	87%	79%	0%
0.0%	0%	0%	0%	0%	0%	0%
69.7%	75%	87%	81%	85%	90%	0%
80.5%	80%	78%	97%	91%	88%	49%
91.0%	88%	87%	100%	97%	97%	77%
91.2%	92%	78%	97%	97%	97%	86%
58.5%	84%	14%	91%	0%	88%	74%
0.0%	0%	0%	0%	0%	0%	0%
54.0%	81%	0%	81%	0%	87%	75%
28.3%	0%	0%	92%	0%	78%	0%
17.7%	97%	0%	1%	0%	0%	8%
16.0%	0%	6%	35%	0%	55%	0%
59.0%	97%	78%	1%	89%	0%	89%
73.0%	11%	87%	81%	97%	88%	74%
57.3%	0%	78%	81%	97%	88%	0%
95.2%	97%	89%	100%	97%	91%	97%
68.0%	81%	78%	0%	88%	87%	74%
11.5%	48%	0%	0%	0%	13%	8%
57.5%	74%	87%	0%	24%	86%	74%
32.5%	59%	0%	84%	52%	0%	0%
47.5%	73%	54%	1%	79%	0%	78%
4.0%	16%	0%	0%	3%	5%	0%
48.2%	72%	54%	1%	66%	7%	89%
36.8%	65%	0%	83%	73%	0%	0%
35.2%	60%	0%	84%	67%	0%	0%
51.7%	35%	78%	0%	19%	91%	87%
50.5%	0%	78%	0%	88%	86%	51%
19.7%	66%	0%	0%	0%	0%	52%
35.2%	59%	0%	84%	0%	0%	68%
33.7%	66%	0%	84%	0%	0%	52%
29.0%	67%	0%	55%	0%	0%	52%
37.5%	32%	54%	84%	7%	16%	32%
26.8%	66%	0%	1%	0%	16%	78%
16.2%	66%	0%	0%	0%	0%	31%
67.3%	64%	78%	91%	88%	83%	0%
13.3%	72%	0%	1%	0%	0%	7%
5.2%	24%	0%	0%	0%	0%	7%
0.0%	0%	0%	0%	0%	0%	0%
11.2%	36%	0%	0%	0%	0%	31%
0.0%	0%	0%	0%	0%	0%	0%
0.0%	0%	0%	0%	0%	0%	0%
23.0%	31%	0%	84%	0%	0%	23%
53.2%	71%	67%	1%	84%	7%	89%
67.2%	88%	88%	0%	91%	86%	50%
80.2%	56%	88%	97%	91%	97%	52%
87.3%	79%	88%	97%	91%	91%	78%