DTeval

A Collective Intelligence Project

Loading blueprint versions...

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

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

Global Dialogues GD4 - Urban (with context)

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

TAGS:

Global Dialogues Gd4

Factual Accuracy & Hallucination

Instruction Following & Prompt Adherence

Social interaction

AI Safety & Robustness

Cognitive Impact & Dependency

Best Models (Coverage)

1.Claude Sonnet 4.5
87.7%
2.Claude Sonnet 4
87.4%
3.Gemini 2.5 Flash
86.8%
4.GPT 4.1
86.2%
5.Claude Haiku 4.5
85.7%

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		5th 85.7%	2nd 87.4%	1st 87.7%	3rd 86.8%	12th 80.3%	8th 83.8%	6th 85.5%	4th 86.2%	9th 83.7%	13th 79.3%	10th 81.6%	11th 80.7%	7th 84.2%
79.8%		76%	83%	86%	87%	82%	83%	86%	79%	84%	49%	83%	79%	81%
78.5%		95%	85%	91%	92%	65%	75%	86%	95%	75%	59%	67%	72%	63%
78.9%		88%	89%	83%	88%	75%	69%	89%	89%	77%	60%	83%	68%	68%
88.4%		90%	82%	94%	91%	90%	96%	87%	90%	84%	84%	84%	86%	91%
77.2%		82%	84%	88%	79%	63%	80%	81%	81%	74%	70%	73%	68%	81%
90.1%		89%	94%	94%	90%	84%	91%	90%	94%	90%	89%	89%	89%	88%
69.7%		93%	87%	84%	73%	59%	58%	71%	66%	57%	57%	60%	63%	78%
86.2%		92%	90%	90%	82%	76%	87%	91%	88%	83%	91%	87%	83%	80%
85.0%		95%	91%	92%	76%	87%	85%	78%	94%	74%	67%	85%	89%	92%
67.1%		62%	64%	64%	52%	86%	60%	85%	65%	73%	52%	71%	61%	77%
92.5%		85%	97%	96%	97%	89%	97%	89%	98%	86%	96%	94%	82%	96%
92.2%		83%	83%	97%	93%	88%	95%	97%	95%	94%	93%	94%	93%	94%
88.7%		89%	89%	89%	89%	85%	89%	89%	89%	89%	89%	89%	89%	89%
64.8%		70%	87%	73%	66%	64%	53%	55%	57%	75%	72%	54%	60%	57%
83.6%		82%	84%	90%	91%	70%	76%	89%	90%	81%	75%	75%	91%	93%
86.5%		96%	95%	93%	91%	75%	96%	91%	92%	89%	50%	92%	70%	94%
83.8%		92%	84%	88%	89%	79%	85%	87%	79%	85%	80%	79%	79%	83%
89.5%		81%	81%	90%	85%	94%	88%	92%	91%	90%	84%	93%	97%	98%
92.0%		93%	96%	94%	92%	92%	91%	91%	89%	92%	92%	86%	94%	94%
76.3%		82%	71%	78%	76%	59%	80%	79%	78%	78%	79%	82%	74%	76%
92.2%		84%	93%	96%	96%	91%	91%	94%	94%	97%	81%	89%	96%	96%
93.4%		97%	93%	98%	97%	92%	97%	97%	90%	98%	98%	98%	61%	98%
93.0%		88%	97%	98%	96%	87%	92%	98%	96%	92%	90%	84%	95%	96%
71.0%		93%	80%	81%	81%	62%	74%	68%	78%	72%	56%	56%	51%	71%
85.1%		80%	86%	84%	83%	89%	89%	85%	90%	86%	87%	84%	83%	80%
87.8%		96%	82%	89%	89%	89%	75%	89%	88%	89%	89%	89%	89%	89%
85.9%		91%	91%	92%	92%	81%	80%	83%	94%	74%	83%	83%	77%	96%
74.6%		56%	81%	83%	78%	68%	74%	73%	86%	79%	66%	72%	78%	76%
83.2%		86%	90%	87%	91%	77%	81%	82%	92%	90%	81%	78%	73%	74%
87.9%		74%	94%	93%	83%	88%	89%	96%	96%	93%	64%	92%	88%	93%
94.0%		97%	93%	92%	90%	90%	95%	92%	95%	99%	98%	92%	94%	95%
89.9%		95%	92%	91%	89%	90%	91%	88%	94%	93%	72%	90%	91%	93%
81.1%		83%	92%	95%	89%	77%	81%	89%	91%	86%	89%	57%	53%	72%
86.0%		89%	90%	88%	95%	73%	87%	95%	90%	91%	78%	92%	61%	89%
88.8%		85%	94%	84%	92%	91%	85%	92%	83%	84%	90%	90%	93%	91%
93.2%		98%	92%	90%	91%	93%	96%	96%	92%	93%	93%	93%	92%	93%
90.9%		91%	91%	90%	96%	91%	80%	94%	90%	75%	94%	94%	97%	99%
90.3%		89%	90%	90%	89%	89%	91%	92%	90%	90%	91%	91%	91%	91%
92.5%		93%	93%	94%	92%	91%	91%	92%	92%	89%	94%	93%	95%	94%
89.8%		91%	92%	88%	91%	91%	91%	91%	91%	91%	78%	91%	91%	91%
84.4%		96%	94%	79%	87%	77%	90%	85%	87%	94%	50%	90%	72%	96%
86.3%		95%	83%	97%	93%	74%	81%	80%	79%	93%	91%	79%	94%	83%
86.5%		94%	87%	92%	92%	71%	85%	93%	88%	86%	91%	67%	92%	87%
80.6%		81%	88%	76%	70%	78%	86%	81%	91%	73%	83%	87%	83%	71%
80.5%		90%	89%	90%	92%	84%	86%	72%	90%	67%	63%	84%	62%	78%
84.1%		74%	88%	95%	85%	72%	94%	83%	91%	81%	75%	77%	89%	89%
82.8%		87%	85%	75%	91%	90%	78%	82%	83%	84%	81%	80%	83%	78%
91.5%		87%	96%	92%	94%	79%	92%	86%	87%	90%	99%	89%	99%	99%
93.8%		96%	86%	94%	96%	94%	94%	96%	94%	96%	96%	98%	82%	98%
93.2%		90%	95%	95%	93%	96%	94%	94%	96%	94%	92%	92%	91%	89%
92.2%		94%	94%	93%	92%	94%	89%	92%	91%	92%	92%	92%	92%	91%
74.2%		74%	89%	86%	87%	62%	70%	71%	88%	80%	62%	70%	55%	71%
78.3%		79%	84%	92%	89%	74%	76%	79%	74%	76%	74%	70%	77%	74%
68.4%		76%	74%	73%	79%	62%	65%	65%	74%	72%	65%	64%	65%	55%
91.0%		91%	91%	91%	91%	91%	91%	91%	91%	91%	91%	91%	91%	91%
79.9%		85%	82%	88%	77%	77%	75%	85%	80%	79%	77%	80%	74%	80%
61.2%		60%	72%	61%	68%	42%	77%	73%	70%	61%	29%	60%	54%	68%
89.0%		89%	89%	89%	89%	89%	89%	89%	89%	89%	89%	89%	89%	89%
83.1%		88%	84%	91%	91%	65%	90%	93%	86%	83%	86%	72%	59%	92%
84.0%		83%	86%	91%	78%	76%	89%	89%	84%	79%	90%	90%	65%	92%
85.2%		90%	92%	80%	78%	86%	84%	83%	83%	77%	77%	94%	91%	93%
79.0%		66%	88%	86%	76%	77%	84%	91%	75%	73%	69%	81%	87%	74%
87.3%		91%	92%	91%	80%	93%	88%	92%	93%	83%	83%	83%	83%	83%
92.5%		86%	96%	97%	96%	95%	88%	97%	95%	90%	95%	87%	85%	96%
92.1%		90%	94%	95%	93%	90%	90%	93%	92%	91%	90%	90%	94%	95%
72.2%		63%	84%	82%	91%	63%	82%	80%	78%	78%	51%	58%	55%	73%
72.3%		76%	74%	76%	85%	66%	78%	73%	79%	76%	63%	61%	64%	69%
79.5%		87%	79%	85%	84%	75%	70%	80%	79%	85%	69%	79%	76%	86%
81.8%		82%	81%	84%	80%	82%	82%	79%	85%	83%	81%	81%	78%	86%
82.6%		93%	80%	82%	72%	83%	68%	80%	75%	97%	86%	89%	85%	84%
80.8%		80%	80%	89%	80%	82%	80%	80%	80%	80%	80%	80%	80%	80%
81.5%		89%	88%	96%	66%	87%	80%	58%	74%	67%	90%	84%	92%	89%
85.5%		87%	89%	97%	86%	81%	88%	88%	89%	84%	65%	84%	89%	85%
78.0%		84%	88%	79%	86%	73%	88%	87%	81%	84%	62%	80%	57%	65%
84.5%		87%	85%	85%	84%	88%	81%	91%	84%	82%	82%	83%	82%	85%
90.6%		93%	97%	95%	89%	91%	96%	87%	90%	88%	88%	84%	89%	91%
82.4%		95%	91%	91%	69%	91%	74%	69%	76%	83%	69%	86%	86%	91%
87.4%		89%	89%	93%	91%	88%	89%	92%	88%	92%	64%	88%	87%	86%
88.9%		82%	93%	93%	95%	86%	91%	92%	94%	81%	92%	81%	84%	92%
91.4%		91%	91%	91%	91%	96%	91%	91%	91%	91%	91%	91%	91%	91%
86.4%		83%	92%	92%	93%	83%	89%	84%	92%	83%	83%	83%	83%	83%
92.8%		95%	95%	96%	94%	84%	91%	95%	93%	94%	93%	88%	94%	94%
84.8%		91%	91%	90%	77%	79%	94%	93%	89%	91%	69%	78%	76%	84%
91.5%		89%	94%	95%	96%	92%	97%	96%	77%	87%	96%	96%	79%	96%
87.3%		95%	90%	77%	90%	88%	85%	86%	90%	90%	88%	88%	82%	86%
92.2%		90%	93%	93%	90%	94%	90%	95%	94%	90%	95%	94%	87%	94%
79.6%		82%	88%	73%	89%	84%	86%	85%	82%	87%	70%	68%	73%	68%
80.7%		89%	82%	83%	85%	70%	79%	73%	75%	82%	91%	70%	92%	78%
80.9%		95%	87%	86%	93%	62%	70%	91%	83%	80%	83%	70%	70%	82%
83.4%		79%	82%	81%	96%	61%	80%	86%	92%	89%	88%	75%	87%	88%
73.6%		64%	73%	78%	85%	66%	73%	73%	73%	80%	94%	67%	69%	62%
77.7%		80%	80%	92%	88%	76%	60%	88%	82%	71%	80%	65%	71%	77%
75.2%		91%	78%	76%	83%	82%	60%	54%	60%	69%	79%	72%	90%	84%
85.4%		77%	88%	87%	80%	86%	84%	86%	93%	88%	88%	85%	86%	82%
60.2%		61%	68%	69%	58%	75%	64%	45%	51%	58%	49%	54%	56%	75%
85.3%		85%	95%	93%	79%	82%	89%	96%	94%	90%	70%	80%	78%	78%
90.6%		93%	94%	95%	97%	89%	95%	88%	92%	90%	79%	87%	89%	90%
84.8%		82%	87%	85%	86%	80%	84%	84%	87%	83%	83%	87%	89%	85%
81.6%		93%	96%	87%	94%	59%	92%	92%	97%	79%	60%	77%	70%	65%
82.7%		94%	93%	94%	92%	77%	75%	87%	85%	81%	77%	67%	76%	77%
77.4%		76%	85%	73%	87%	71%	80%	83%	85%	79%	59%	83%	68%	77%
81.5%		78%	79%	87%	80%	78%	81%	84%	83%	81%	85%	91%	74%	79%
86.4%		96%	96%	90%	88%	86%	85%	71%	80%	59%	96%	88%	95%	93%
81.8%		84%	77%	80%	96%	67%	76%	80%	92%	85%	99%	75%	73%	79%
89.4%		84%	89%	88%	92%	89%	87%	93%	89%	93%	84%	90%	93%	91%
86.0%		91%	82%	92%	90%	77%	87%	90%	93%	84%	87%	88%	70%	87%
82.3%		95%	82%	90%	89%	69%	72%	89%	92%	93%	77%	73%	72%	77%
74.2%		65%	82%	88%	90%	60%	85%	88%	92%	59%	58%	58%	84%	55%
77.5%		64%	78%	70%	88%	78%	86%	80%	77%	84%	57%	80%	86%	80%
89.0%		97%	95%	95%	96%	73%	93%	91%	95%	90%	89%	71%	95%	77%
87.5%		86%	87%	85%	93%	91%	78%	92%	87%	82%	86%	89%	90%	92%
88.3%		86%	90%	90%	96%	85%	92%	87%	89%	89%	74%	94%	87%	89%
88.9%		86%	93%	90%	90%	80%	96%	87%	96%	94%	89%	84%	87%	84%
92.6%		89%	93%	96%	95%	98%	94%	94%	93%	84%	96%	90%	86%	96%
87.2%		90%	92%	92%	91%	70%	88%	92%	92%	91%	82%	88%	78%	88%
82.2%		80%	80%	82%	80%	90%	81%	85%	80%	80%	88%	80%	83%	80%