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%3Achina - Run deef1b7...

Global Dialogues GD4 - China

DTEF: Predict response distributions for China. 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
78.8%
2.Llama 4 Maverick
78.7%
3.Claude Sonnet 4
78.4%
4.GPT 4.1 Mini
77.4%
5.Claude Haiku 4.5
77.2%

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		5th 77.2%	3rd 78.4%	1st 78.8%	8th 76.1%	10th 74.6%	2nd 78.7%	6th 76.5%	7th 76.5%	4th 77.4%	13th 73.0%	9th 74.8%	12th 73.7%	11th 74.2%
66.5%		71%	72%	79%	86%	49%	65%	70%	84%	57%	68%	57%	54%	52%
74.4%		77%	75%	80%	93%	55%	59%	63%	91%	87%	73%	72%	58%	84%
77.6%		82%	73%	73%	70%	85%	82%	68%	69%	88%	75%	84%	78%	82%
84.2%		86%	82%	93%	87%	83%	90%	87%	84%	80%	81%	80%	77%	85%
58.2%		61%	66%	66%	59%	51%	61%	60%	53%	59%	61%	51%	49%	60%
87.2%		93%	91%	91%	95%	85%	91%	94%	88%	88%	89%	91%	79%	59%
59.2%		80%	63%	63%	60%	35%	65%	45%	61%	61%	22%	62%	71%	82%
65.5%		60%	64%	64%	57%	65%	72%	61%	65%	63%	58%	70%	83%	70%
78.7%		78%	66%	66%	89%	78%	77%	89%	79%	86%	86%	82%	61%	86%
72.0%		83%	82%	82%	75%	82%	83%	71%	83%	78%	43%	60%	73%	41%
78.6%		81%	80%	83%	80%	80%	80%	78%	74%	83%	72%	78%	72%	81%
76.8%		87%	70%	70%	64%	86%	89%	78%	59%	87%	66%	83%	79%	80%
82.4%		82%	86%	87%	84%	85%	83%	86%	81%	80%	81%	82%	72%	82%
64.8%		74%	75%	77%	60%	50%	59%	58%	69%	60%	56%	58%	73%	74%
74.5%		69%	83%	83%	55%	83%	78%	60%	73%	76%	79%	79%	71%	80%
80.4%		87%	77%	87%	85%	74%	85%	84%	86%	87%	73%	74%	69%	77%
75.4%		86%	75%	75%	79%	57%	81%	80%	81%	71%	74%	71%	74%	76%
84.5%		85%	88%	85%	89%	86%	90%	89%	76%	82%	87%	77%	79%	86%
66.1%		56%	71%	59%	48%	82%	82%	76%	59%	55%	75%	68%	69%	59%
83.5%		93%	88%	88%	85%	61%	87%		92%	90%	77%	86%	73%	82%
79.8%		80%	84%	74%	74%	82%	92%	77%	64%	81%	75%	85%	84%	85%
88.5%		86%	95%	87%	89%	93%	88%	90%	90%	90%	84%	91%	80%	87%
83.8%		90%	86%	92%	86%	82%	88%	90%	93%	76%	94%	79%	78%	56%
62.8%		70%	58%	59%	69%	59%	65%	68%	57%	70%	63%	51%	60%	67%
77.8%		78%	81%	81%	77%	79%	83%	75%	79%	74%	83%	67%	71%	83%
60.5%		68%	50%	62%	70%	52%	61%	45%	62%	64%	32%	65%	78%	78%
81.8%		71%	84%	90%	92%	83%	85%	89%	88%	81%	91%	69%	71%	69%
72.2%		85%	78%	84%	77%	56%	64%	74%	87%	69%	75%	69%	60%	61%
70.8%		80%	78%	82%	57%	69%	77%	79%	75%	72%	73%	59%	58%	61%
69.5%		71%	77%	76%	65%	56%	79%	71%	72%	69%	66%	70%	59%	73%
87.6%		98%	88%	88%	91%	90%	94%	91%	83%	88%	91%	91%	81%	65%
74.0%		62%	72%	72%	71%	82%	79%	82%	67%	83%	85%	77%	79%	51%
85.2%		89%	88%	91%	82%	84%	87%	87%	90%	91%	93%	81%	72%	72%
73.5%		73%	71%	79%	78%	72%	77%	79%	77%	82%	69%	70%	56%	72%
72.7%		59%	81%	78%	82%	79%	58%	57%	71%	65%	73%	83%	87%	72%
82.7%		84%	89%	89%	82%	85%	86%	87%	91%	77%	76%	84%	82%	63%
82.8%		77%	85%	85%	76%	90%	77%	85%	84%	84%	77%	83%	85%	88%
64.6%		59%	75%	75%	58%	73%	42%	45%	69%	69%	54%	58%	72%	91%
84.6%		92%	83%	83%	86%	88%	88%	85%	81%	88%	89%	85%	83%	69%
51.7%		39%	47%	59%	45%	70%	31%	41%	56%	68%	41%	60%	70%	45%
80.7%		77%	89%	85%	70%	83%	85%	76%	87%	84%	81%	78%	74%	80%
77.2%		82%	80%	82%	71%	81%	81%	73%	76%	78%	73%	75%	77%	74%
78.0%		75%	80%	81%	57%	83%	86%	82%	81%	82%	70%	78%	75%	84%
70.8%		65%	71%	60%	63%	72%	85%	85%	74%	70%	76%	74%	73%	52%
78.9%		79%	76%	76%	84%	89%	87%	74%	78%	77%	68%	77%	83%	78%
74.3%		68%	74%	78%	82%	68%	67%	79%	80%	80%	65%	72%	78%	75%
81.0%		84%	86%	83%	90%	75%	87%	78%	77%	85%	79%	76%	78%	75%
91.7%		95%	91%	91%	95%	82%	99%	100%	83%	95%	92%	82%	98%	89%
87.8%		87%	86%	82%	88%	90%	91%	93%	90%	83%	88%	89%	83%	91%
67.3%		62%	67%	60%	48%	92%	83%	57%	50%	64%	62%	80%	76%	74%
70.6%		68%	77%	63%	70%	79%	86%	84%	73%	72%	75%	57%	56%	58%
65.1%		71%	70%	76%	67%	60%	63%	75%	70%	61%	59%	61%	54%	59%
74.2%		78%	79%	85%	87%	58%	65%	74%	80%	76%	66%	70%	64%	82%
78.0%		79%	70%	69%	84%	78%	77%	88%	85%	81%	79%	67%	76%	81%
78.8%		84%	90%	90%	70%	81%	84%	83%	83%	83%	73%	73%	73%	58%
79.5%		62%	88%	88%	85%	76%	81%	88%	84%	79%	82%	65%	70%	86%
64.4%		50%	74%	63%	56%	53%	82%	72%	67%	64%	67%	72%	55%	62%
84.2%		82%	91%	84%	79%	88%	92%	79%	71%	84%	86%	86%	81%	91%
71.4%		77%	65%	82%	79%	64%	73%	73%	78%	76%	62%	62%	58%	79%
68.8%		69%	69%	65%	65%	82%	70%	69%	61%	66%	70%	70%	72%	67%
79.6%		86%	87%	87%	78%	76%	80%	87%	88%	78%	76%	65%	60%	87%
63.3%		80%	75%	83%	70%	41%	63%	64%	75%	45%	65%	49%	55%	58%
85.5%		92%	93%	76%	90%	91%	92%	97%	90%	79%	76%	75%	80%	80%
86.2%		86%	87%	87%	89%	88%	91%	81%	82%	89%	80%	86%	86%	88%
81.7%		70%	90%	90%	92%	84%	82%	87%	91%	76%	80%	79%	80%	61%
78.3%		85%	87%	84%	78%	85%	83%	69%	74%	81%	76%	74%	70%	72%
68.5%		74%	80%	81%	78%	47%	75%	71%	78%	65%	64%	56%	53%	68%
70.1%		79%	73%	72%	73%	69%	60%	65%	68%	70%	66%	66%	75%	75%
75.5%		78%	69%	66%	71%	70%	77%	75%	76%	80%	78%	74%	84%	83%
80.8%		75%	84%	84%	76%	81%	83%	84%	83%	82%	73%	84%	77%	84%
85.7%		89%	88%	86%	86%	89%	84%	87%	84%	83%	85%	85%	84%	84%
82.5%		81%	81%	76%	78%	87%	92%	89%	80%	92%	91%	79%	74%	73%
86.2%		89%	91%	92%	82%	91%	95%	84%	82%	77%	85%	85%	80%	88%
64.0%		66%	84%	83%	0%	53%	77%	78%	78%	65%	65%	64%	58%	61%
79.5%		72%	77%	77%	78%	87%	83%	83%	71%	81%	76%	81%	79%	88%
72.1%		75%	63%	68%	61%	76%	78%	69%	62%	82%	77%	78%	77%	71%
86.2%		91%	90%	90%	85%	86%	93%	80%	75%	91%	78%	91%	86%	84%
78.1%		83%	83%	87%	87%	65%	83%	80%	81%	72%	81%	78%	68%	67%
77.2%		80%	80%	79%	69%	78%	78%	77%	79%	80%	78%	79%	71%	75%
80.5%		84%	86%	86%	77%	81%	84%	82%	86%	83%	80%	77%	79%	62%
83.2%		83%	92%	92%	77%	86%	91%	90%	78%	83%	80%	80%	83%	66%
75.8%		67%	66%	66%	83%	89%	72%	78%	56%	89%	65%	84%	89%	82%
62.6%		65%	63%	59%	38%	77%	69%	61%	49%	63%	64%	67%	67%	72%
86.1%		86%	83%	83%	86%	85%	91%	91%	86%	75%	90%	88%	87%	88%
83.4%		84%	91%	89%	88%	89%	89%	90%	69%	84%	78%	92%	78%	63%
85.8%		90%	86%	87%	87%	87%	87%	86%	76%	88%	87%	84%	83%	88%
78.2%		77%	82%	83%	78%	81%	79%	82%	75%	79%	74%	82%	78%	67%
74.2%		66%	76%	67%	73%	79%	68%	75%	63%	85%	70%	78%	80%	84%
81.0%		90%	92%	89%	79%	89%	75%	86%	70%	83%	55%	76%	93%	76%
87.5%		93%	87%	91%	92%	75%	86%	79%	88%	95%	78%	85%	95%	93%
76.7%		82%	72%	84%	82%	70%	79%	79%	82%	81%	69%	70%	68%	79%
67.0%		63%	72%	53%	89%	61%	59%	54%	87%	61%	61%	63%	82%	66%
63.9%		72%	60%	77%	44%	55%	59%	54%	84%	66%	49%	78%	77%	56%
74.0%		74%	86%	80%	72%	73%	85%	84%	66%	76%	75%	71%	60%	60%
73.9%		73%	75%	75%	76%	87%	80%	69%	58%	64%	76%	77%	77%	74%
85.2%		88%	93%	87%	86%	86%	78%	71%	89%	86%	83%	88%	86%	87%
71.6%		75%	83%	84%	69%	68%	69%	64%	63%	67%	63%	74%	75%	77%
80.9%		82%	79%	75%	69%	92%	86%	75%	72%	80%	86%	85%	88%	83%
74.7%		82%	71%	87%	77%	55%	80%	77%	85%	81%	63%	69%	64%	80%
76.2%		66%	74%	69%	92%	76%	73%	62%	67%	84%	72%	80%	89%	87%
72.4%		78%	78%	80%	76%	64%	73%	73%	80%	74%	71%	66%	56%	72%
79.2%		78%	81%	97%	96%	76%	69%	78%	91%	78%	83%	56%	70%	77%
58.2%		79%	46%	66%	63%	38%	61%	48%	66%	60%	32%	55%	67%	76%
79.9%		82%	82%	80%	87%	75%	84%	83%	78%	79%	78%	80%	77%	74%
82.1%		79%	88%	89%	87%	65%	93%	94%	76%	86%	86%	86%	70%	68%
81.5%		64%	80%	80%	85%	82%	92%	91%	79%	90%	74%	86%	90%	66%
61.1%		57%	53%	53%	82%	41%	63%	72%	65%	60%	82%	52%	45%	69%
76.8%		75%	70%	82%	91%	54%	72%	79%	95%	85%	66%	81%	65%	83%
78.2%		81%	81%	83%	84%	65%	86%	78%	82%	80%	58%	76%	81%	82%
78.2%		84%	78%	73%	82%	82%	82%	82%	84%	86%	72%	73%	69%	69%
76.6%		77%	75%	68%	65%	86%	73%	67%	61%	78%	85%	84%	88%	89%
79.3%		79%	84%	82%	87%	62%	85%	81%	88%	89%	83%	82%	65%	64%
62.5%		66%	56%	65%	54%	54%	65%	53%	68%	67%	48%	68%	71%	78%
82.8%		82%	85%	85%	81%	87%	85%	76%	80%	82%	83%	82%	82%	87%
72.9%		66%	81%	81%	83%	68%	75%	86%	84%	72%	59%	75%	61%	57%
87.3%		82%	95%	90%	89%	95%	94%	88%	78%	87%	86%	88%	82%	81%