DTeval

A Collective Intelligence Project

Loading blueprint versions...

Please wait while we gather all the unique runs for this blueprint.

Analysis: Gd4 Dtef Global Dialogues Gd4 Environment%3Aurban - Run 407f320...

Global Dialogues GD4 - Urban

DTEF: Predict response distributions for Urban. Source: Global Dialogues GD4 (https://github.com/collect-intel/global-dialogues)

TAGS:

Global Dialogues Gd4

Instruction Following & Prompt Adherence

Social interaction

AI Safety & Robustness

General Knowledge

Economics & Finance

Mental Health & Crisis Support

Best Models (Coverage)

1.GPT 4.1
83.3%
2.Claude Sonnet 4.5
83.3%
3.Claude Sonnet 4
83.2%
4.Claude Haiku 4.5
83.1%
5.Llama 4 Maverick
82.6%

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

	Prompts vs. Models	Claude Haiku 4.5	Claude Sonnet 4	Claude Sonnet 4.5	Gemini 2.5 Flash	Gemma 3 12b It	Llama 4 Maverick	Mistral Medium 3	GPT 4.1	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini	Qwen3 30b A3B Instruct 2507	Qwen3 Next 80b A3B Instruct
Score		4th 83.1%	3rd 83.2%	2nd 83.3%	6th 82.5%	11th 79.4%	5th 82.6%	9th 80.5%	1st 83.3%	7th 82.2%	13th 76.9%	10th 79.7%	12th 78.1%	8th 81.3%
66.5%		68%	73%	77%	65%	55%	65%	64%	69%	79%	70%	59%	59%	61%
68.6%		67%	69%	71%	85%	53%	58%	61%	86%	79%	67%	67%	59%	70%
81.3%		81%	84%	89%	75%	79%	86%	81%	86%	81%	76%	79%	77%	83%
87.9%		93%	90%	93%	89%	90%	85%	90%	89%	84%	81%	88%	86%	85%
72.7%		76%	79%	82%	74%	68%	76%	69%	74%	69%	72%	70%	63%	73%
86.2%		87%	88%	91%	89%	80%	86%	88%	95%	82%	90%	90%	78%	77%
62.2%		82%	67%	67%	69%	62%	68%	52%	53%	64%	34%	57%	67%	66%
80.5%		73%	82%	73%	75%	88%	86%	77%	86%	77%	77%	86%	81%	85%
86.5%		88%	84%	86%	79%	88%	95%	79%	97%	84%	94%	86%	75%	90%
78.5%		81%	58%	57%	62%	90%	69%	70%	92%	87%	88%	93%	82%	91%
87.8%		87%	90%	91%	89%	90%	87%	88%	88%	89%	87%	88%	80%	88%
90.8%		97%	94%	94%	94%	97%	95%	92%	96%	92%	70%	91%	84%	85%
86.4%		87%	84%	84%	88%	90%	85%	92%	89%	88%	89%	88%	80%	79%
65.8%		69%	69%	72%	65%	72%	66%	62%	61%	57%	67%	58%	68%	70%
75.5%		73%	80%	77%	68%	81%	83%	73%	81%	81%	77%	75%	63%	70%
83.3%		91%	77%	95%	93%	79%	88%	88%	89%	83%	75%	74%	72%	79%
81.7%		88%	80%	84%	86%	78%	85%	86%	80%	76%	88%	75%	74%	82%
89.7%		89%	96%	98%	93%	88%	94%	86%	86%	89%	84%	88%	88%	87%
86.2%		89%	96%	94%	87%	84%	85%	83%	94%	84%	68%	88%	78%	90%
76.8%		83%	73%	73%	76%	73%	78%	79%	76%	77%	81%	81%	71%	78%
87.4%		88%	95%	81%	94%	84%	89%	87%	85%	90%	81%	93%	84%	85%
89.9%		89%	90%	93%	91%	94%	98%	95%	81%	93%	81%	84%	83%	97%
85.2%		80%	89%	89%	91%	81%	83%	91%	88%	79%	92%	92%	78%	74%
60.1%		69%	68%	69%	56%	50%	65%	65%	65%	62%	62%	46%	49%	55%
87.3%		84%	88%	91%	86%	89%	87%	89%	93%	85%	91%	78%	86%	88%
67.2%		68%	59%	58%	77%	68%	68%	71%	60%	68%	38%	71%	85%	83%
86.9%		82%	86%	91%	88%	91%	87%	87%	92%	90%	89%	82%	82%	83%
78.7%		70%	79%	80%	82%	71%	78%	85%	89%	81%	84%	84%	65%	75%
77.8%		78%	84%	92%	84%	63%	85%	83%	83%	76%	80%	70%	65%	69%
79.8%		84%	84%	94%	76%	70%	82%	77%	85%	83%	77%	73%	69%	84%
87.3%		86%	86%	89%	91%	87%	92%	91%	92%	83%	90%	88%	85%	75%
85.5%		86%	88%	86%	85%	80%	86%	82%	83%	87%	87%	87%	84%	90%
76.2%		84%	72%	82%	87%	78%	72%	93%	80%	76%	80%	63%	58%	65%
71.8%		74%	69%	82%	88%	66%	72%	79%	77%	73%	67%	63%	57%	66%
81.7%		82%	85%	80%	86%	86%	87%	62%	78%	74%	83%	86%	90%	83%
86.4%		86%	87%	89%	86%	88%	87%	85%	93%	83%	88%	88%	83%	80%
75.2%		77%	85%	59%	72%	87%	75%	67%	70%	73%	75%	75%	93%	70%
82.4%		86%	88%	90%	90%	89%	82%	71%	87%	87%	56%	70%	83%	92%
87.8%		87%	91%	86%	90%	85%	84%	91%	89%	90%	88%	88%	82%	91%
73.5%		80%	69%	69%	66%	88%	73%	71%	75%	78%	64%	62%	80%	80%
89.7%		93%	96%	93%	88%	81%	94%	93%	93%	94%	75%	93%	76%	97%
86.4%		94%	96%	93%	84%	96%	93%	82%	86%	94%	78%	73%	81%	73%
86.0%		91%	91%	88%	93%	72%	91%	94%	92%	92%	90%	70%	64%	90%
74.2%		79%	75%	72%	77%	65%	89%	85%	76%	73%	72%	71%	72%	58%
87.8%		91%	94%	96%	83%	90%	90%	83%	91%	83%	80%	88%	82%	90%
85.5%		81%	85%	85%	86%	87%	92%	89%	88%	88%	74%	83%	85%	89%
82.7%		93%	83%	76%	89%	81%	86%	83%	79%	85%	84%	79%	81%	76%
88.5%		92%	96%	87%	82%	82%	85%	86%	93%	91%	75%	95%	96%	91%
88.2%		91%	88%	77%	91%	90%	99%	84%	82%	89%	83%	86%	93%	94%
87.5%		91%	96%	96%	81%	91%	88%	87%	93%	87%	71%	89%	79%	88%
86.4%		94%	94%	94%	82%	83%	90%	83%	86%	87%	71%	88%	83%	88%
73.7%		68%	83%	90%	77%	65%	78%	80%	83%	76%	61%	69%	61%	67%
70.4%		76%	69%	77%	76%	67%	59%	68%	68%	73%	73%	66%	60%	83%
64.0%		63%	61%	63%	69%	70%	63%	64%	56%	66%	66%	57%	65%	69%
87.4%		83%	94%	91%	76%	87%	87%	90%	91%	89%	88%	91%	84%	85%
84.9%		82%	85%	87%	87%	81%	79%	91%	94%	83%	88%	83%	75%	89%
74.8%		75%	84%	84%	62%	60%	88%	75%	91%	67%	72%	77%	67%	71%
90.1%		94%	87%	87%	93%	93%	87%	84%	86%	94%	89%	93%	87%	97%
68.0%		77%	64%	83%	83%	51%	71%	71%	73%	70%	61%	61%	54%	65%
80.5%		77%	85%	86%	84%	86%	80%	73%	80%	83%	72%	80%	85%	76%
88.2%		94%	90%	89%	89%	84%	93%	86%	91%	96%	93%	74%	68%	99%
71.4%		72%	81%	79%	73%	58%	72%	75%	76%	66%	77%	60%	70%	69%
86.7%		94%	94%	93%	92%	81%	93%	94%	93%	82%	72%	75%	82%	82%
88.4%		88%	90%	90%	88%	91%	91%	82%	87%	91%	90%	87%	84%	90%
84.6%		76%	82%	88%	82%	83%	84%	88%	91%	85%	93%	90%	80%	78%
86.9%		86%	92%	92%	87%	75%	94%	90%	89%	84%	89%	85%	77%	90%
77.8%		86%	79%	82%	80%	68%	80%	87%	86%	74%	75%	67%	72%	76%
77.9%		85%	80%	77%	77%	77%	76%	71%	76%	82%	74%	74%	78%	86%
80.5%		78%	82%	77%	81%	84%	78%	78%	85%	83%	83%	83%	77%	77%
88.6%		93%	83%	88%	89%	88%	85%	85%	89%	94%	86%	89%	85%	98%
87.7%		88%	91%	93%	88%	91%	87%	84%	88%	78%	88%	88%	91%	85%
86.0%		91%	88%	88%	70%	96%	87%	72%	93%	92%	89%	86%	83%	83%
92.4%		95%	95%	91%	92%	92%	94%	94%	86%	94%	92%	92%	88%	96%
74.9%		81%	85%	86%	81%	64%	71%	90%	85%	72%	64%	70%	63%	62%
79.8%		84%	79%	79%	80%	83%	77%	80%	75%	82%	72%	77%	85%	84%
83.3%		83%	88%	83%	89%	82%	88%	77%	79%	85%	78%	83%	82%	86%
86.2%		87%	94%	90%	91%	89%	85%	85%	83%	83%	77%	88%	87%	82%
82.3%		89%	81%	87%	82%	66%	84%	85%	84%	88%	88%	87%	75%	74%
85.1%		85%	85%	87%	78%	88%	86%	86%	88%	86%	86%	86%	81%	84%
84.7%		85%	91%	83%	75%	86%	91%	79%	87%	84%	77%	87%	89%	87%
92.2%		92%	92%	92%	90%	97%	92%	95%	87%	94%	92%	93%	94%	88%
89.3%		96%	95%	94%	89%	90%	90%	87%	96%	90%	68%	89%	88%	89%
80.8%		85%	84%	80%	70%	84%	89%	82%	78%	80%	74%	83%	81%	80%
92.0%		94%	97%	92%	95%	89%	95%	98%	83%	89%	85%	94%	90%	95%
86.8%		85%	94%	90%	90%	85%	91%	90%	82%	88%	78%	89%	87%	79%
85.6%		85%	82%	86%	87%	87%	86%	87%	85%	88%	86%	86%	83%	85%
74.2%		78%	75%	68%	78%	77%	70%	69%	63%	73%	66%	79%	86%	83%
81.8%		85%	81%	78%	84%	75%	78%	80%	87%	85%	78%	83%	83%	86%
76.2%		84%	86%	86%	92%	72%	68%	70%	72%	66%	46%	68%	85%	95%
81.2%		88%	78%	73%	81%	73%	76%	72%	73%	93%	89%	82%	92%	86%
76.2%		70%	70%	70%	70%	73%	86%	78%	84%	84%	79%	70%	76%	80%
51.4%		51%	56%	56%	63%	45%	46%	45%	48%	52%	35%	51%	67%	53%
68.6%		77%	61%	62%	61%	64%	54%	57%	79%	67%	60%	91%	83%	76%
84.7%		86%	85%	88%	89%	75%	85%	91%	90%	87%	85%	82%	78%	80%
68.5%		74%	76%	68%	67%	74%	73%	73%	64%	63%	56%	67%	70%	66%
84.8%		78%	88%	88%	90%	87%	86%	71%	87%	89%	77%	79%	90%	92%
88.5%		92%	90%	92%	88%	95%	96%	80%	94%	85%	76%	90%	83%	90%
92.0%		91%	92%	91%	96%	95%	93%	89%	91%	93%	92%	92%	89%	92%
80.8%		85%	85%	91%	96%	55%	82%	84%	92%	85%	67%	76%	67%	86%
78.4%		79%	84%	87%	86%	68%	70%	76%	86%	83%	71%	71%	83%	75%
74.0%		72%	81%	79%	77%	74%	73%	77%	85%	75%	69%	72%	61%	67%
87.2%		76%	90%	89%	91%	88%	85%	90%	92%	89%	92%	82%	80%	89%
59.8%		67%	47%	58%	74%	65%	65%	47%	60%	65%	35%	55%	73%	67%
83.7%		84%	78%	77%	85%	84%	76%	84%	90%	85%	90%	87%	83%	85%
87.4%		89%	90%	88%	91%	76%	96%	92%	90%	90%	78%	96%	79%	81%
89.1%		95%	92%	89%	92%	75%	95%	89%	95%	96%	74%	88%	83%	95%
83.3%		91%	96%	96%	91%	68%	81%	94%	90%	85%	80%	78%	50%	83%
69.6%		71%	69%	76%	74%	51%	72%	62%	88%	79%	65%	66%	64%	68%
81.4%		84%	84%	85%	81%	72%	87%	84%	84%	86%	67%	78%	82%	84%
84.9%		85%	83%	89%	88%	91%	88%	82%	91%	95%	90%	73%	67%	82%
80.0%		79%	82%	70%	70%	86%	78%	68%	74%	69%	87%	92%	97%	88%
86.5%		86%	82%	83%	94%	86%	93%	80%	81%	94%	89%	91%	81%	85%
73.6%		76%	67%	61%	84%	76%	77%	68%	69%	76%	62%	76%	84%	81%
87.3%		89%	90%	89%	70%	95%	90%	83%	88%	93%	84%	90%	87%	87%
90.3%		94%	96%	97%	94%	92%	98%	95%	92%	89%	66%	84%	91%	86%
77.6%		72%	80%	76%	78%	85%	82%	78%	73%	81%	76%	76%	84%	68%