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%3Asuburban - Run 560390a...

Global Dialogues GD4 - Suburban

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

TAGS:

Global Dialogues Gd4

Factual Accuracy & Hallucination

Instruction Following & Prompt Adherence

AI Safety & Robustness

Social interaction

Economics & Finance

Education Systems & Pedagogy

Best Models (Coverage)

1.GPT 4.1
82.3%
2.Claude Sonnet 4.5
82.3%
3.Claude Haiku 4.5
82.1%
4.Claude Sonnet 4
81.8%
5.GPT 4.1 Mini
81.1%

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		3rd 82.1%	4th 81.8%	2nd 82.3%	6th 80.8%	13th 77.5%	7th 80.6%	10th 79.1%	1st 82.3%	5th 81.1%	11th 77.8%	9th 79.3%	12th 77.7%	8th 80.5%
67.8%		70%	67%	74%	71%	56%	65%	69%	65%	72%	72%	62%	66%	72%
64.5%		64%	67%	69%	73%	40%	55%	58%	84%	74%	64%	65%	58%	68%
83.4%		84%	88%	87%	93%	83%	86%	80%	84%	85%	77%	78%	76%	83%
81.5%		87%	85%	87%	78%	82%	78%	81%	83%	81%	79%	81%	78%	80%
67.6%		74%	76%	78%	71%	59%	73%	65%	70%	62%	63%	58%	63%	67%
85.2%		86%	88%	90%	90%	78%	84%	89%	90%	84%	91%	92%	75%	71%
50.8%		64%	54%	65%	45%	42%	49%	48%	44%	48%	22%	50%	65%	65%
82.5%		84%	82%	73%	79%	83%	86%	80%	82%	78%	97%	86%	75%	88%
87.5%		91%	82%	85%	82%	93%	96%	81%	94%	90%	91%	86%	74%	92%
77.7%		80%	61%	59%	66%	89%	81%	67%	71%	85%	91%	91%	78%	91%
86.3%		85%	88%	89%	79%	80%	85%	88%	88%	87%	89%	88%	86%	90%
87.5%		96%	93%	93%	86%	86%	92%	82%	95%	91%	70%	86%	83%	84%
81.1%		81%	83%	83%	70%	88%	76%	88%	88%	78%	85%	73%	78%	83%
74.0%		80%	74%	78%	79%	87%	72%	73%	72%	66%	72%	62%	72%	75%
78.8%		76%	85%	79%	66%	72%	90%	76%	81%	92%	80%	82%	70%	76%
79.0%		81%	75%	93%	94%	74%	86%	85%	89%	81%	60%	69%	63%	77%
82.4%		91%	85%	88%	91%	75%	88%	89%	79%	77%	80%	72%	71%	85%
89.1%		89%	95%	83%	92%	91%	95%	87%	88%	94%	84%	88%	85%	87%
84.5%		83%	93%	83%	88%	84%	83%	82%	88%	80%	73%	85%	85%	91%
75.9%		79%	72%	72%	73%	76%	77%	73%	77%	78%	79%	79%		76%
87.4%		92%	95%	80%	89%	84%	91%	84%	85%	87%	80%	96%	85%	88%
88.7%		90%	93%	96%	90%	73%	81%	89%	91%	95%	85%	89%	89%	92%
81.7%		75%	79%	88%	87%	80%	84%	90%	84%	77%	91%	79%	78%	70%
64.7%		69%	79%	79%	61%	54%	68%	78%	67%	70%	59%	46%	55%	56%
85.1%		81%	85%	91%	86%	88%	90%	80%	91%	82%	89%	76%	78%	89%
62.2%		70%	48%	64%	64%	64%	74%	55%	48%	64%	43%	62%	84%	69%
87.4%		83%	82%	81%	91%	92%	86%	91%	89%	88%	93%	89%	84%	87%
77.2%		70%	80%	81%	80%	59%	78%	83%	87%	81%	80%	78%	66%	81%
82.8%		87%	93%	87%	90%	74%	91%	79%	93%	82%	80%	76%	67%	78%
82.9%		84%	87%	92%	90%	70%	79%	85%	86%	85%	82%	79%	73%	86%
88.7%		88%	91%	90%	86%	85%	92%	91%	96%	88%	90%	87%	86%	83%
89.0%		91%	90%	82%	87%	85%	90%	89%	93%	91%	91%	91%	91%	86%
72.2%		73%	64%	82%	84%	74%	71%	83%	74%	71%	83%	60%	56%	63%
67.5%		71%	67%	83%	73%	61%	70%	76%	76%	70%	50%	62%	54%	64%
78.6%		80%	83%	78%	85%	85%	70%	59%	76%	72%	80%	84%	87%	83%
85.7%		85%	84%	88%	89%	78%	85%	90%	90%	89%	89%	84%	81%	82%
78.8%		83%	88%	60%	74%	90%	78%	69%	75%	70%	91%	81%	91%	75%
78.7%		83%	82%	82%	77%	90%	69%	66%	84%	82%	75%	73%	85%	75%
88.4%		89%	90%	85%	89%	88%	89%	92%	90%	90%	90%	90%	83%	84%
68.8%		65%	68%	69%	65%	81%	65%	59%	65%	73%	76%	68%	73%	68%
87.5%		93%	92%	92%	91%	79%	91%	91%	94%	88%	74%	90%	71%	91%
85.4%		89%	85%	79%	90%	79%	89%	87%	86%	87%	79%	88%	89%	83%
84.9%		88%	88%	84%	86%	71%	83%	89%	90%	86%	91%	82%	74%	92%
73.2%		76%	73%	71%	73%	62%	88%	82%	82%	70%	73%	72%	68%	61%
87.2%		89%	92%	94%	83%	90%	89%	85%	91%	87%	84%	82%	78%	90%
85.4%		81%	86%	86%	86%	87%	92%	87%	90%	84%	72%	82%	86%	91%
83.2%		94%	89%	84%	91%	71%	88%	82%	83%	84%	78%	83%	83%	72%
87.0%		84%	90%	89%	84%	84%	88%	84%	94%	84%	77%	93%	93%	87%
90.0%		88%	90%	88%	90%	94%	87%	91%	88%	88%	90%	88%	91%	97%
89.3%		92%	89%	91%	90%	91%	92%	92%	93%	84%	83%	92%	83%	89%
89.5%		94%	92%	95%	92%	85%	90%	86%	96%	87%	79%	90%	83%	94%
72.7%		71%	80%	88%	79%	67%	67%	79%	82%	72%	63%	70%	61%	66%
67.4%		70%	69%	72%	64%	61%	53%	62%	66%	76%	66%	68%	74%	75%
65.0%		63%	64%	64%	69%	68%	63%	72%	68%	70%	53%	65%	61%	65%
84.5%		77%	86%	97%	84%	83%	86%	89%	87%	84%	85%	81%	81%	78%
85.7%		85%	83%	83%	84%	85%	83%	93%	91%	85%	91%	84%	77%	90%
72.2%		72%	80%	81%	66%	55%	87%	69%	84%	70%	76%	65%	72%	61%
89.5%		93%	90%	90%	85%	95%	88%	86%	92%	93%	91%	83%	85%	93%
67.5%		75%	62%	82%	85%	51%	68%	74%	73%	69%	56%	60%	49%	73%
78.9%		80%	86%	85%	81%	92%	77%	68%	76%	79%	73%	79%	84%	66%
88.1%		93%	89%	91%	89%	79%	87%	89%	90%	94%	93%	82%	77%	92%
72.0%		74%	82%	82%	72%	57%	66%	72%	77%	69%	74%	69%	69%	73%
88.2%		92%	90%	90%	86%	96%	95%	90%	90%	90%	75%	87%	84%	81%
89.3%		90%	91%	91%	80%	94%	85%	83%	89%	95%	93%	93%	86%	91%
81.8%		77%	81%	90%	77%	76%	85%	90%	90%	85%	92%	77%	80%	64%
83.2%		83%	86%	88%	90%	79%	86%	78%	87%	84%	84%	78%	71%	87%
76.2%		77%	77%	77%	88%	62%	82%	79%	83%	77%	79%	72%	61%	77%
76.4%		82%	78%	73%	72%	78%	74%	71%	72%	81%	71%	73%	84%	84%
82.2%		78%	83%	80%	81%	86%	78%	82%	85%	81%	86%	83%	84%	81%
87.6%		91%	81%	87%	84%	91%	84%	91%	83%	91%	85%	87%	87%	97%
87.3%		92%	88%	94%	87%	89%	88%	85%	92%	87%	86%	86%	75%	86%
83.3%		89%	84%	84%	66%	94%	85%	68%	92%	85%	86%	84%	83%	83%
88.9%		94%	94%	80%	84%	93%	95%	79%	80%	93%	92%	91%	87%	94%
74.7%		83%	79%	79%	75%	63%	74%	87%	77%	80%	71%	70%	65%	68%
79.8%		85%	81%	83%	81%	82%	79%	75%	74%	81%	76%	76%	80%	85%
79.1%		79%	77%	77%	77%	85%	80%	69%	71%	85%	81%	82%	82%	83%
87.7%		89%	98%	91%	92%	89%	95%	87%	84%	87%	76%	89%	86%	77%
84.5%		88%	87%	88%	85%	70%	86%	86%	89%	89%	79%	89%	77%	85%
87.8%		88%	89%	90%	80%	89%	85%	87%	89%	89%	89%	89%	86%	92%
85.4%		83%	91%	87%	84%	85%	84%	82%	88%	88%	85%	82%	87%	84%
85.8%		87%	84%	84%	80%	81%	86%	84%	91%	90%	87%	84%	82%	95%
87.1%		94%	94%	93%	93%	88%	78%	85%	95%	85%	68%	85%	87%	87%
79.2%		85%	81%	81%	74%	87%	85%	66%	76%	79%	80%	80%	80%	76%
86.3%		90%	79%	92%	91%	63%	78%	92%	95%	81%	87%	81%	96%	97%
83.5%		83%	88%	86%	84%	81%	86%	87%	85%	84%	75%	86%	83%	77%
86.9%		87%	88%	89%	89%	88%	84%	85%	86%	88%	87%	88%	83%	88%
79.4%		88%	79%	91%	71%	86%	76%	73%	69%	77%	69%	82%	85%	86%
74.8%		77%	75%	73%	75%	76%	70%	70%	80%	78%	67%	77%	78%	76%
81.6%		87%	91%	91%	92%	92%	78%	80%	76%	69%	51%	72%	88%	94%
81.5%		85%	75%	75%	75%	68%	77%	72%	76%	80%	99%	85%	94%	98%
73.2%		68%	70%	69%	68%	72%	73%	75%	79%	77%	73%	69%	73%	85%
50.7%		48%	56%	49%	62%	52%	46%	37%	48%	51%	46%	50%	68%	46%
62.1%		75%	60%	60%	50%	60%	51%	53%	60%	59%	61%	79%	80%	59%
88.2%		90%	91%	91%	90%	77%	96%	92%	96%	88%	83%	90%	78%	85%
71.7%		73%	76%	84%	78%	74%	74%	74%	64%	63%	69%	69%	69%	65%
85.2%		78%	90%	89%	86%	87%	81%	69%	88%	82%	90%	89%	88%	91%
84.2%		86%	87%	92%	76%	94%	87%	66%	89%	84%	79%	88%	89%	78%
86.2%		88%	86%	83%	76%	93%	92%	83%	77%	91%	88%	88%	87%	89%
78.5%		80%	82%	90%	91%	56%	78%	84%	93%	81%	68%	72%	63%	82%
82.3%		93%	91%	91%	90%	71%	73%	79%	91%	85%	74%	74%	78%	80%
75.2%		74%	82%	75%	70%	78%	66%	76%	83%	84%	72%	79%	65%	73%
84.0%		74%	82%	88%	87%	83%	81%	87%	91%	86%	91%	78%	78%	86%
56.8%		69%	49%	49%	62%	56%	53%	52%	43%	65%	38%	59%	76%	67%
79.9%		80%	76%	77%	83%	67%	74%	83%	79%	82%	88%	88%	82%	80%
87.7%		97%	94%	89%	92%	75%	93%	90%	92%	89%	80%	88%	75%	86%
89.0%		79%	89%	90%	88%	72%	96%	90%	95%	97%	84%	88%	95%	94%
81.3%		90%	90%	82%	89%	67%	84%	91%	91%	84%	78%	78%	52%	81%
63.7%		66%	63%	76%	66%	36%	57%	76%	82%	69%	60%	61%	53%	63%
77.1%		80%	80%	84%	78%	67%	85%	68%	82%	75%	66%	73%	81%	83%
82.8%		83%	76%	87%	91%	85%	81%	81%	88%	84%	90%	83%	66%	82%
82.7%		83%	91%	71%	80%	90%	85%	71%	81%	75%	82%	92%	85%	89%
76.2%		77%	70%	70%	93%	61%	78%	76%	72%	78%	86%	78%	79%	72%
66.5%		69%	62%	52%	69%	69%	78%	61%	51%	69%	66%	69%	80%	70%
86.6%		90%	91%	91%	73%	93%	89%	79%	88%	92%	81%	89%	85%	85%
91.9%		88%	92%	87%	96%	96%	96%	98%	95%	96%	82%	97%	88%	84%
83.2%		84%	90%	83%	83%	85%	87%	79%	84%	83%	78%	87%	88%	71%