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%3Akazakhstan Rawsurvey Indiv Individual - Run f54b95d...

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

DTEF [indiv]: Predict individual answers for Kazakhstan (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	3rd 53.4%	2nd 62.0%	6th 35.2%	1st 67.3%	5th 37.2%	4th 38.6%
91.3%	85%	98%	97%	97%	97%	74%
87.3%	81%	88%	97%	97%	87%	74%
24.0%	65%	25%	39%	7%	0%	8%
70.2%	87%	78%	81%	90%	85%	0%
96.3%	98%	99%	100%	97%	97%	87%
85.8%	88%	87%	97%	97%	91%	55%
48.5%	16%	88%	2%	97%	88%	0%
40.7%	84%	68%	0%	92%	0%	0%
53.5%	1%	78%	81%	87%	74%	0%
20.5%	1%	0%	0%	0%	68%	54%
97.2%	99%	99%	100%	97%	91%	97%
61.3%	98%	95%	0%	95%	0%	80%
39.3%	0%	68%	11%	78%	54%	25%
55.8%	99%	54%	1%	92%	0%	89%
97.8%	99%	99%	100%	97%	97%	95%
26.8%	0%	68%	1%	78%	0%	14%
61.5%	99%	95%	0%	95%	0%	80%
49.0%	100%	95%	0%	99%	0%	0%
29.3%	8%	54%	1%	88%	0%	25%
29.0%	0%	79%	0%	95%	0%	0%
57.5%	77%	78%	0%	16%	87%	87%
35.0%	89%	32%	0%	89%	0%	0%
28.3%	29%	14%	71%	0%	24%	32%
48.5%	79%	54%	1%	79%	0%	78%
87.2%	70%	78%	100%	91%	97%	87%
36.5%	16%	32%	81%	7%	83%	0%
58.3%	0%	78%	97%	87%	88%	0%
47.3%	96%	89%	0%	99%	0%	0%
5.7%	20%	14%	0%	0%	0%	0%
8.0%	0%	0%	20%	20%	0%	8%
16.0%	66%	0%	0%	0%	0%	30%
55.0%	0%	78%	83%	91%	78%	0%
27.0%	16%	14%	28%	3%	69%	32%
31.0%	73%	0%	35%	0%	0%	78%
70.2%	16%	78%	97%	91%	88%	51%
49.8%	0%	78%	55%	88%	78%	0%
0.0%	0%	0%	0%	0%	0%	0%
42.3%	67%	95%	0%	92%	0%	0%
31.2%	52%	0%	83%	0%	0%	52%
34.7%	42%	54%	0%	6%	54%	52%
85.2%	70%	88%	97%	91%	88%	77%
44.5%	88%	95%	0%	84%	0%	0%
33.2%	32%	54%	3%	58%	0%	52%
44.5%	56%	54%	1%	78%	0%	78%
83.0%	39%	88%	100%	97%	97%	77%
44.7%	66%	68%	1%	65%	0%	68%
45.5%	86%	95%	0%	92%	0%	0%
46.3%	84%	95%	0%	99%	0%	0%
35.2%	66%	0%	1%	79%	0%	65%
51.2%	66%	84%	0%	89%	0%	68%