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 First Person Blueprints Individual First Person Dtef Global Dialogues Gd4 Country%3Amalaysia Firstperson Indiv Individual - Run 3c4cdae...

Global Dialogues GD4 - Malaysia [indiv] (73 ctx) [first-person]

DTEF [indiv]: Predict individual answers for Malaysia (10 participants). Source: Global Dialogues GD4 (https://github.com/collect-intel/global-dialogues)

TAGS:

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Reasoning

Efficiency & Succinctness

Knowledge, learning and memory

Best Models (Coverage)

1.GPT 4.1 Nano
39.9%
2.Gemma 3 12b It
36.2%
3.Gemini 2.5 Flash
30.3%
4.GPT 4o Mini
26.2%
5.GPT 4.1 Mini
24.5%

View Blueprint

Select Prompt:

Macro Coverage Overview

Average key point coverage extent for each model across all prompts.

Pro Tip

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	6th 22.6%	3rd 30.3%	2nd 36.2%	5th 24.5%	1st 39.9%	4th 26.2%
89.8%	97%	88%	97%	97%	86%	74%
12.3%	0%	0%	0%	0%	74%	0%
19.3%	7%	32%	0%	0%	77%	0%
11.5%	0%	0%	0%	7%	62%	0%
12.3%	0%	0%	0%	0%	74%	0%
0.0%	0%	0%	0%	0%	0%	0%
12.0%	0%	0%	0%	0%	72%	0%
15.3%	7%	8%	0%	0%	77%	0%
92.7%	99%	88%	97%	97%	88%	87%
29.3%	0%	0%	0%	24%	78%	74%
29.5%	31%	0%	0%	7%	88%	51%
3.8%	23%	0%	0%	0%	0%	0%
26.8%	23%	40%	0%	20%	78%	0%
31.5%	0%	0%	100%	0%	89%	0%
0.0%	0%	0%	0%	0%	0%	0%
12.8%	0%	0%	0%	0%	77%	0%
61.7%	73%	54%	84%	67%	14%	78%
41.8%	0%	0%	97%	0%	65%	89%
46.7%	0%	0%	97%	0%	95%	88%
46.8%	64%	52%	97%	3%	65%	0%
53.2%	16%	78%	0%	87%	78%	60%
7.7%	20%	14%	12%	0%	0%	0%
53.0%	70%	78%	0%	87%	77%	6%
0.0%	0%	0%	0%	0%	0%	0%
9.0%	0%	54%	0%	0%	0%	0%
11.3%	54%	14%	0%	0%	0%	0%
68.8%	88%	89%	84%	67%	7%	78%
12.0%	0%	23%	43%	0%	6%	0%
2.3%	0%	14%	0%	0%	0%	0%
27.5%	22%	78%	0%	0%	65%	0%
50.3%	0%	78%	0%	88%	78%	58%
31.2%	28%	32%	73%	0%	23%	31%
24.3%	0%	32%	84%	0%	0%	30%
19.7%	0%	14%	73%	0%	0%	31%
19.2%	0%	0%	84%	0%	0%	31%
31.2%	23%	54%	20%	7%	31%	52%
41.5%	66%	54%	84%	0%	14%	31%
20.0%	0%	0%	84%	0%	16%	20%
65.0%	86%	78%	0%	97%	78%	51%
16.5%	0%	0%	84%	0%	15%	0%
23.0%	2%	0%	84%	52%	0%	0%
30.0%	1%	95%	0%	84%	0%	0%
21.8%		0%	84%	0%	0%	25%
44.3%	79%	95%	0%	92%	0%	0%
27.3%	1%	79%	0%	84%	0%	0%
23.3%	0%	0%	73%	0%	15%	52%
56.2%	49%	45%	84%	67%	14%	78%
28.5%	21%	0%	0%	79%	65%	6%
39.0%	0%	0%	92%	0%	88%	54%
43.5%	56%	53%	0%	10%	65%	77%