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 Country%3Aunited Kingdom - Run e846fc0...

Global Dialogues GD4 - United Kingdom

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

TAGS:

Global Dialogues Gd4

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

AI Safety & Robustness

Social interaction

Best Models (Coverage)

1.Claude Sonnet 4.5
78.0%
2.Claude Sonnet 4
77.4%
3.GPT 4.1
76.8%
4.Claude Haiku 4.5
76.5%
5.GPT 4.1 Mini
76.2%

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 76.5%	2nd 77.4%	1st 78.0%	8th 74.8%	11th 73.1%	6th 76.1%	9th 74.8%	3rd 76.8%	5th 76.2%	13th 72.0%	10th 74.1%	12th 72.2%	7th 75.4%
71.8%		77%	72%	75%	77%	54%	71%	74%	71%	76%	77%	72%	66%	72%
78.2%		84%	81%	84%	85%	62%	70%	79%	81%	83%	77%	80%	70%	81%
74.3%		74%	76%	73%	85%	73%	77%	71%	73%	76%	70%	72%	67%	79%
59.2%		66%	66%	65%	54%	55%	60%	64%	60%	57%	56%	54%	54%	59%
72.1%		79%	77%	79%	75%	60%	77%	69%	73%	66%	72%	70%	69%	71%
82.3%		80%	84%	84%	83%	76%	83%	90%	87%	88%	84%	88%	79%	64%
58.8%		72%	62%	62%	62%	53%	58%	41%	50%	74%	39%	57%	62%	72%
78.6%		72%	82%	76%	72%	86%	77%	76%	89%	70%	81%	85%	74%	82%
83.1%		85%	88%	88%	39%	95%	91%	78%	93%	89%	90%	83%	71%	90%
77.7%		83%	79%	76%	68%	84%	81%	70%	78%	81%	82%	85%	69%	74%
76.8%		82%	79%	83%	68%	76%	81%	76%	77%	76%	75%	76%	70%	79%
83.5%		85%	97%	86%	84%	88%	82%	83%	86%	82%	61%	83%	82%	87%
70.8%		70%	73%	74%	63%	74%	70%	72%	69%	74%	72%	74%	64%	71%
66.2%		71%	66%	71%	63%	72%	67%	61%	67%	65%	67%	57%	68%	66%
63.3%		64%	68%	65%	48%	64%	70%	68%	71%	60%	60%	67%	59%	59%
84.6%		90%	85%	90%	82%	78%	92%	89%	92%	90%	74%	79%	75%	84%
79.6%		85%	85%	85%	77%	72%	78%	83%	85%	77%	79%	74%	70%	85%
76.8%		68%	74%	79%	72%	79%	73%	84%	86%	75%	88%	63%	72%	86%
69.3%		72%	70%	74%	72%	72%	70%	62%	77%	65%	58%	69%	64%	76%
78.8%		86%	70%	73%	76%	71%	72%	79%	69%	86%	87%	87%	80%	88%
72.7%		64%	74%	76%	80%	71%	68%	78%	80%	72%	77%	71%	68%	66%
87.2%		92%	95%	84%	76%	86%	92%	86%	76%	94%	85%	90%	84%	94%
79.0%		69%	82%	93%	86%	77%	86%	81%	81%	77%	86%	83%	71%	55%
68.3%		71%	76%	76%	72%	65%	76%	75%	72%	65%	63%	56%	58%	63%
78.5%		80%	76%	76%	70%	85%	87%	72%	85%	77%	76%	75%	78%	84%
44.0%		50%	37%	39%	44%	45%	49%	42%	34%	49%	28%	50%	50%	55%
78.3%		65%	77%	74%	83%	87%	82%	80%	78%	82%	84%	75%	75%	76%
79.3%		75%	81%	81%	87%	59%	85%	87%	83%	83%	83%	82%	71%	74%
74.1%		79%	80%	83%	76%	67%	79%	73%	79%	69%	69%	72%	68%	69%
74.0%		76%	78%	85%	80%	59%	77%	71%	74%	73%	72%	76%	65%	76%
86.3%		90%	94%	85%	89%	90%	89%	85%	90%	81%	87%	83%	82%	77%
84.8%		81%	86%	88%	86%	78%	88%	84%	76%	90%	87%	85%	90%	84%
76.2%		86%	72%	79%	86%	75%	81%	81%	72%	80%	85%	66%	59%	69%
80.8%		83%	84%	92%	86%	77%	86%	87%	89%	86%	63%	76%	63%	78%
69.2%		61%	77%	61%	82%	76%	53%	60%	64%	61%	82%	77%	81%	64%
89.0%		86%	92%	90%	91%	91%	92%	90%	94%	87%	91%	90%	83%	80%
75.6%		78%	70%	70%	60%	87%	79%	79%	73%	64%	79%	84%	84%	76%
72.5%		69%	76%	76%	79%	78%	69%	60%	75%	72%	66%	61%	77%	84%
81.4%		78%	87%	90%	85%	80%	83%	78%	88%	80%	78%	83%	73%	75%
64.7%		50%	63%	65%	60%	76%	58%	61%	69%	69%	59%	62%	72%	77%
73.6%		81%	77%	73%	71%	65%	77%	78%	80%	75%	61%	74%	65%	80%
72.8%		74%	77%	76%	75%	80%	74%	74%	72%	74%	62%	58%	74%	76%
81.0%		82%	87%	85%	83%	75%	86%	83%	90%	84%	86%	69%	64%	79%
83.8%		87%	92%	85%	87%	80%	85%	90%	92%	81%	81%	78%	79%	72%
58.0%		60%	62%	64%	48%	52%	58%	58%	58%	62%	58%	58%	57%	59%
79.6%		79%	81%	85%	76%	74%	78%	78%	78%	86%	71%	85%	82%	82%
84.2%		86%	77%	73%	83%	89%	77%	92%	78%	89%	82%	87%	95%	86%
94.9%		99%	94%	94%	94%	99%	99%	97%	97%	94%	97%	77%	94%	99%
78.8%		76%	82%	81%	78%	83%	79%	79%	75%	78%	79%	83%	74%	78%
73.2%		72%	69%	74%	79%	81%	74%	70%	79%	70%	65%	78%	72%	69%
77.5%		81%	78%	88%	79%	78%	72%	69%	81%	78%	64%	80%	78%	81%
62.9%		60%	70%	72%	70%	56%	69%	68%	81%	63%	47%	55%	52%	55%
58.4%		63%	58%	68%	55%	50%	49%	51%	58%	74%	53%	67%	52%	61%
66.1%		63%	64%	66%	66%	72%	73%	71%	65%	67%	51%	69%	60%	72%
68.5%		65%	72%	72%	63%	70%	69%	71%	65%	67%	70%	76%	67%	64%
74.9%		77%	79%	72%	73%	71%	77%	77%	74%	77%	81%	77%	71%	68%
63.3%		60%	60%	66%	59%	48%	78%	64%	69%	61%	62%	60%	69%	67%
83.2%		77%	83%	78%	84%	88%	81%	85%	84%	87%	87%	87%	74%	87%
67.5%		76%	73%	77%	80%	60%	72%	68%	77%	66%	54%	58%	48%	68%
83.8%		82%	92%	95%	81%	84%	85%	81%	90%	80%	71%	80%	89%	79%
60.8%		66%	58%	58%	60%	55%	61%	67%	65%	62%	63%	62%	52%	62%
60.9%		67%	69%	69%	65%	44%	59%	62%	64%	52%	69%	57%	57%	58%
73.4%		75%	86%	83%	81%	74%	74%	77%	84%	77%	59%	57%	64%	63%
83.0%		87%	90%	88%	72%	92%	75%	76%	77%	73%	88%	86%	86%	89%
84.8%		74%	86%	88%	86%	85%	92%	94%	89%	91%	93%	88%	77%	59%
85.9%		88%	85%	93%	89%	76%	92%	95%	86%	87%	77%	82%	74%	93%
68.8%		76%	78%	78%	71%	49%	73%	73%	71%	68%	63%	65%	58%	71%
64.2%		71%	65%	68%	71%	61%	57%	57%	62%	66%	63%	56%	67%	71%
76.2%		74%	78%	78%	72%	77%	86%	76%	78%	73%	75%	80%	71%	72%
91.8%		87%	95%	95%	99%	85%	85%	92%	97%	87%	94%	95%	95%	87%
88.8%		95%	89%	85%	91%	89%	92%	84%	89%	85%	90%	89%	84%	93%
85.3%		92%	86%	93%	66%	92%	91%	72%	90%	89%	92%	81%	77%	88%
87.8%		89%	98%	80%	74%	94%	91%	79%	82%	92%	92%	91%	91%	89%
63.3%		73%	77%	78%	74%	49%	60%	74%	74%	52%	47%	54%	49%	62%
67.5%		60%	73%	75%	69%	67%	63%	63%	73%	63%	63%	63%	71%	74%
89.0%		93%	92%	92%	89%	92%	87%	88%	76%	91%	89%	87%	88%	93%
82.5%		82%	82%	83%	78%	82%	84%	86%	84%	86%	77%	84%	87%	77%
70.9%		74%	74%	74%	73%	58%	69%	69%	73%	73%	71%	73%	69%	72%
84.8%		89%	91%	89%	58%	88%	86%	88%	87%	87%	87%	88%	83%	81%
74.5%		72%	82%	82%	70%	78%	76%	70%	77%	73%	67%	75%	77%	70%
88.5%		90%	85%	80%	87%	87%	85%	83%	83%	92%	97%	93%	99%	90%
79.5%		86%	83%	82%	80%	90%	75%	74%	81%	84%	55%	74%	82%	88%
74.0%		78%	78%	78%	68%	78%	80%	66%	72%	71%	72%	74%	75%	72%
83.8%		87%	86%	85%	75%	80%	82%	89%	82%	85%	88%	80%	83%	88%
77.2%		72%	78%	87%	70%	76%	84%	80%	87%	84%	59%	78%	78%	70%
90.5%		93%	89%	93%	77%	92%	94%	94%	89%	91%	98%	94%	82%	91%
79.8%		82%	75%	84%	86%	87%	81%	77%	79%	77%	71%	75%	81%	82%
69.7%		69%	73%	71%	67%	69%	65%	62%	75%	77%	62%	76%	69%	71%
79.6%		90%	90%	87%	72%	78%	84%	84%	78%	73%	56%	78%	85%	80%
76.2%		82%	81%	79%	81%	67%	77%	73%	79%	77%	65%	73%	80%	77%
63.8%		62%	59%	63%	67%	62%	65%	68%	65%	68%	60%	60%	64%	67%
59.4%		44%	54%	51%	81%	58%	57%	47%	54%	49%	75%	63%	80%	59%
58.3%		65%	65%	61%	43%	57%	46%	58%	48%	64%	49%	74%	69%	59%
72.4%		77%	75%	72%	75%	67%	75%	73%	73%	72%	67%	70%	71%	74%
77.4%		80%	81%	85%	77%	80%	78%	77%	77%	68%	77%	74%	79%	73%
86.4%		87%	87%	88%	82%	88%	84%	86%	89%	87%	88%	88%	83%	86%
76.1%		78%	77%	85%	64%	84%	77%	66%	85%	77%	72%	74%	80%	70%
83.3%		82%	86%	82%	82%	84%	89%	76%	85%	92%	82%	79%	80%	84%
79.5%		88%	80%	88%	90%	51%	81%	84%	84%	84%	67%	82%	64%	90%
68.8%		76%	80%	79%	73%	60%	58%	60%	75%	77%	61%	59%	67%	70%
59.3%		59%	72%	75%	70%	54%	54%	57%	67%	59%	47%	50%	44%	63%
50.5%		44%	49%	54%	57%	45%	54%	55%	51%	53%	53%	48%	43%	51%
52.5%		69%	40%	49%	57%	48%	44%	47%	37%	65%	46%	60%	56%	65%
71.5%		70%	67%	69%	82%	66%	71%	73%	73%	72%	75%	76%	67%	68%
79.4%		86%	75%	75%	81%	76%	86%	75%	81%	81%	71%	82%	81%	82%
79.9%		77%	83%	85%	87%	66%	88%	81%	88%	86%	52%	67%	88%	91%
78.8%		86%	76%	82%	90%	63%	80%	84%	85%	88%	81%	72%	56%	82%
68.1%		69%	65%	72%	73%	50%	67%	71%	74%	74%	65%	69%	62%	74%
80.2%		79%	74%	74%	87%	81%	87%	83%	84%	81%	74%	85%	76%	77%
73.7%		67%	78%	75%	83%	73%	70%	84%	77%	82%	72%	69%	57%	71%
83.3%		87%	85%	90%	85%	86%	90%	87%	90%	85%	69%	76%	72%	81%
77.5%		81%	82%	78%	83%	62%	79%	77%	78%	81%	77%	78%	76%	76%
60.4%		65%	54%	54%	60%	59%	66%	54%	48%	65%		63%	66%	71%
77.8%		82%	86%	86%	55%	85%	79%	75%	78%	79%	75%	79%	75%	77%
86.9%		95%	86%	84%	85%	92%	86%	83%	83%	94%	71%	86%	96%	89%
85.2%		81%	94%	90%	87%	84%	90%	83%	90%	84%	86%	80%	80%	79%