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 Environment%3Aurban Firstperson Indiv Individual - Run d840478...

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

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

TAGS:

Instruction Following & Prompt Adherence

Reasoning

Factual Accuracy & Hallucination

Efficiency & Succinctness

General Knowledge

Best Models (Coverage)

1.GPT 4.1 Nano
48.3%
2.GPT 4.1 Mini
42.3%
3.GPT 4o Mini
39.0%
4.Claude Haiku 4.5
37.1%
5.Gemini 2.5 Flash
35.6%

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	4th 37.1%	5th 35.6%	6th 30.5%	2nd 42.3%	1st 48.3%	3rd 39.0%
12.3%	0%	0%	0%	0%	74%	0%
77.3%	99%	0%	97%	97%	97%	74%
0.0%	0%	0%	0%	0%	0%	0%
39.8%	7%	78%	0%	87%	67%	0%
93.0%	99%	88%	100%	97%	88%	86%
41.8%	67%	0%	0%	24%	86%	74%
96.5%	99%	99%	100%	97%	97%	87%
32.0%		0%	0%	0%	86%	74%
30.2%	0%	8%	0%	87%	86%	0%
25.8%	0%	78%	0%	0%	77%	0%
59.3%	95%	89%	0%	92%	0%	80%
0.0%	0%	0%	0%	0%	0%	0%
0.0%	0%	0%	0%	0%	0%	0%
3.8%	0%	23%	0%	0%	0%	0%
0.8%	0%	0%	0%	0%	5%	0%
61.2%	67%	54%	0%	91%	78%	77%
64.2%		78%	0%	91%	78%	74%
39.0%	19%	54%	97%	0%	64%	0%
30.2%	5%	14%	84%	0%	0%	78%
21.0%	26%	0%	0%	16%	78%	6%
0.0%	0%	0%	0%	0%	0%	0%
46.8%	0%	0%	100%	0%	86%	95%
64.5%	99%	89%	0%	99%	0%	100%
20.4%		14%	0%	0%	88%	0%
69.8%	88%	78%	0%	91%	88%	74%
67.5%	81%	78%	0%	91%	78%	77%
71.2%	95%	78%	0%	91%	86%	77%
42.2%	0%	78%	97%	0%	78%	0%
39.8%	75%	0%	0%	87%	77%	0%
64.8%	95%	78%	0%	87%	78%	51%
22.7%	0%	32%	73%	0%	0%	31%
65.5%	88%	78%	0%	91%	78%	58%
0.0%	0%	0%	0%	0%	0%	0%
24.5%	0%	32%	84%	0%	0%	31%
69.7%	84%	78%	0%	91%	88%	77%
17.7%	0%	0%	84%	0%	15%	7%
71.3%	93%	78%	0%	97%	86%	74%
14.0%	0%	0%	84%	0%	0%	0%
26.5%	5%	32%	84%	0%	7%	31%
17.7%	0%	0%	84%	0%	7%	15%
34.3%	38%	84%	0%	84%	0%	0%
32.0%	7%	0%	97%	0%	88%	0%
1.3%	0%	0%	0%	0%	0%	8%
25.0%	0%	0%	84%	0%	0%	66%
58.0%	51%	54%	0%	88%	78%	77%
51.3%	55%	0%	0%	88%	88%	77%
68.7%	84%	78%	0%	88%	88%	74%
54.3%	21%	0%	92%	88%	65%	60%
39.2%	66%	0%	84%	0%	7%	78%
30.8%		79%	0%	75%	0%	0%