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%3Aphilippines Rawsurvey Indiv Individual - Run bb1047c...

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

DTEF [indiv]: Predict individual answers for Philippines (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 49.6%	4th 39.8%	6th 34.6%	2nd 45.6%	5th 39.2%	3rd 42.0%
62.7%	84%	86%	0%	91%	64%	51%
14.3%	55%	0%	0%	0%	0%	31%
91.2%	88%	87%	100%	97%	97%	78%
69.8%	84%	78%	91%	88%	78%	0%
63.5%	79%	78%	55%	75%	94%	0%
72.2%	88%	78%	91%	88%	88%	0%
84.7%	62%	87%	97%	91%	97%	74%
27.2%	83%	0%	1%	0%	14%	65%
83.7%	84%	87%	97%	91%	88%	55%
56.8%	19%	78%	92%	88%	64%	0%
25.8%	0%	52%	1%	88%	0%	14%
57.5%	95%	67%	0%	88%	0%	95%
57.3%	0%	78%	81%	97%	88%	0%
7.8%	39%	0%	0%	0%	0%	8%
46.0%	97%	0%	1%	89%	0%	89%
8.3%	42%	0%	0%	0%	0%	8%
96.2%	97%	99%	100%	97%	97%	87%
38.2%	94%	0%	0%	0%	67%	68%
58.5%	96%	78%	0%	88%	0%	89%
0.0%	0%	0%	0%	0%	0%	0%
35.5%	0%	78%	58%	0%	77%	0%
44.3%	72%	31%	1%	73%	0%	89%
25.0%	65%	0%	39%	46%	0%	0%
11.2%	65%	2%	0%	0%	0%	0%
41.8%	73%	54%	35%	0%	0%	89%
9.7%	50%	0%	0%	0%	0%	8%
55.5%	19%	78%	55%	16%	88%	77%
45.3%	71%	54%	0%	0%	79%	68%
36.2%	72%	0%	1%	66%	0%	78%
27.3%	0%	0%	0%	84%	0%	80%
8.3%	16%	10%	0%	0%	0%	24%
31.3%	0%	14%	81%	19%	74%	0%
74.5%	52%	78%	91%	88%	78%	60%
20.2%	0%	0%	0%	0%	69%	52%
35.3%	67%	32%	35%	0%	0%	78%
12.3%	42%	0%	0%	0%	0%	32%
22.8%	59%	0%	58%	0%	0%	20%
46.7%	59%	54%	35%	66%	14%	52%
49.8%	0%	78%	55%	88%	78%	0%
1.8%	9%	2%	0%	0%	0%	0%
31.8%	59%	0%	1%	66%	0%	65%
46.2%	66%	54%	1%	78%	0%	78%
87.0%	89%	88%	97%	97%	91%	60%
30.5%	0%	14%	81%	0%	88%	0%
51.8%	66%	54%	35%	67%	0%	89%
34.3%	23%	14%	81%	0%	88%	0%
63.3%	35%	88%	0%	91%	88%	78%
11.8%	0%	14%	1%	0%	24%	32%
45.2%	60%	54%	1%	78%	0%	78%
31.5%	6%	14%	81%	0%	88%	0%