DTeval

A Collective Intelligence Project

Loading blueprint versions...

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

Analysis: Gd4 C10 Dtef Global Dialogues Gd4 Country%3Achina C10 - Run 23cf949...

Global Dialogues GD4 - China (10 context Qs)

DTEF: Predict response distributions for China. 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

General Knowledge

Efficiency & Succinctness

Best Models (Coverage)

1.Claude Sonnet 4
79.9%
2.Llama 4 Maverick
79.9%
3.GPT 4.1 Mini
79.4%
4.Mistral Medium 3
78.6%
5.Claude Haiku 4.5
78.4%

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 78.4%	1st 79.9%	6th 78.0%	13th 66.3%	7th 76.9%	2nd 79.9%	4th 78.6%	10th 76.2%	3rd 79.4%	12th 75.2%	8th 76.6%	9th 76.2%	11th 75.6%
70.5%		76%	81%	80%	74%	51%	71%	75%	82%	65%	65%	63%	71%	63%
66.1%		66%	64%	73%	59%	42%	59%	64%	94%	79%	69%	69%	61%	60%
74.6%		63%	68%	70%	45%	87%	87%	75%	60%	88%	83%	83%	77%	84%
81.2%		86%	84%	91%	63%	84%	89%	83%	87%	79%	80%	80%	73%	77%
54.5%		56%	59%	56%	61%	50%	60%	60%	54%	49%	53%	51%	46%	53%
82.6%		91%	91%	83%	60%	83%	84%	90%	87%	93%	83%	95%	86%	48%
69.2%		88%	84%	84%	79%	58%	76%	60%	59%	63%	56%	56%	63%	74%
77.4%		83%	88%	86%	54%	72%	77%	80%	69%	75%	80%	75%	81%	86%
78.0%		87%	66%	76%	88%	80%	72%	88%	79%	85%	77%	78%	79%	59%
77.4%		74%	85%	74%	64%	89%	81%	76%	77%	82%	81%	75%	76%	72%
75.4%		81%	86%	75%	52%	80%	78%	71%	71%	79%	78%	78%	72%	79%
75.1%		81%	69%	60%	75%	86%	75%	75%	66%	81%	68%	78%	79%	83%
82.2%		86%	86%	84%	81%	82%	84%	83%	78%	80%	85%	82%	82%	75%
72.1%		87%	77%	77%	80%	59%	72%	67%	72%	73%	60%	64%	75%	74%
69.8%		63%	75%	82%	27%	67%	72%	59%	72%	81%	79%	79%	70%	82%
78.7%		77%	77%	87%	78%	77%	84%	83%	88%	87%	68%	74%	70%	73%
78.8%		79%	75%	79%	76%	82%	79%	83%	79%	78%	81%	79%	75%	79%
87.1%		85%	89%	88%	90%	84%	92%	93%	85%	89%	86%	72%	91%	88%
67.2%		70%	68%	63%	22%	73%	83%	79%	62%	66%	73%	67%	70%	78%
88.1%		93%	92%	94%	97%	65%	91%	80%	96%	87%	89%	90%	87%	84%
75.2%		71%	77%	76%	76%	71%	89%	85%	71%	72%	59%	61%	84%	86%
86.2%		86%	93%	87%	80%	93%	82%	87%	91%	88%	85%	84%	80%	85%
75.3%		71%	92%	88%	63%	83%	81%	90%	90%	66%	77%	92%	45%	41%
61.9%		66%	59%	56%	60%	59%	58%	71%	60%	60%	73%	51%	59%	73%
73.1%		79%	81%	79%	31%	83%	82%	76%	74%	73%	72%	60%	75%	85%
92.4%		90%	91%	90%	93%	93%	91%	93%	95%	93%	93%	93%	93%	93%
87.4%		88%	91%	92%	94%	82%	92%	83%	92%	84%	83%	84%	85%	86%
79.8%		88%	94%	92%	74%	55%	83%	86%	85%	79%	81%	80%	70%	71%
72.9%		71%	80%	82%	55%	68%	84%	77%	79%	76%	76%	63%	61%	76%
70.5%		66%	73%	73%	54%	69%	78%	70%	71%	75%	67%	70%	73%	77%
81.5%		98%	88%	78%	53%	88%	89%	83%	82%	89%	80%	89%	86%	56%
76.2%		84%	83%	83%	58%	83%	67%	76%	84%	84%	84%	84%	81%	39%
83.8%		88%	89%	86%	47%	88%	89%	84%	84%	95%	81%	88%	86%	84%
69.9%		72%	71%	75%	88%	70%	81%	79%	65%	73%	63%	55%	56%	61%
75.6%		81%	81%	69%	16%	88%	86%	84%	61%	73%	86%	81%	87%	90%
77.1%		92%	89%	80%	45%	84%	82%	79%	87%	83%	76%	90%	64%	51%
82.3%		86%	88%	88%	81%	87%	84%	80%	73%	80%	74%	84%	85%	80%
73.1%		71%	75%	75%	90%	64%	54%	63%	81%	87%	72%	72%	69%	77%
82.5%		89%	83%	75%	86%	86%	86%	88%	82%	88%	83%	84%	84%	59%
59.9%		39%	48%	62%	43%	64%	41%	52%	70%	81%	71%	71%	71%	66%
79.8%		90%	88%	95%	39%	83%	89%	70%	82%	82%	82%	80%	77%	80%
75.6%		83%	82%	81%	65%	78%	72%	71%	71%	78%	83%	70%	76%	73%
83.5%		86%	90%	84%	77%	83%	83%	80%	83%	89%	80%	85%	79%	86%
69.0%		64%	61%	63%	66%	72%	85%	82%	67%	63%	75%	71%	65%	63%
75.6%		79%	76%	71%	84%	85%	91%	70%	60%	70%	74%	66%	79%	78%
75.0%		72%	77%	76%	71%	71%	76%	82%	75%	83%	66%	72%	77%	77%
78.6%		90%	85%	75%	85%	77%	88%	80%	78%	76%	67%	71%	73%	77%
86.9%		95%	65%	64%	93%	89%	99%	100%	66%	95%	89%	82%	98%	95%
85.2%		86%	87%	85%	54%	90%	88%	92%	88%	93%	88%	83%	88%	85%
68.7%		51%	71%	60%	34%	87%	79%	79%	51%	77%	74%	78%	78%	74%
71.8%		79%	88%	72%	33%	67%	86%	83%	75%	71%	79%	67%	66%	68%
70.4%		64%	63%	84%	78%	63%	82%	82%	77%	65%	63%	71%	59%	64%
76.5%		79%	83%	89%	71%	77%	77%	80%	82%	79%	54%	74%	71%	79%
72.1%		74%	70%	67%	71%	73%	78%	76%	76%	75%	73%	66%	67%	71%
80.8%		82%	87%	80%	83%	80%	73%	81%	80%	84%	81%	83%	84%	72%
83.7%		89%	88%	88%	76%	84%	84%	88%	87%	84%	74%	82%	82%	82%
50.1%		41%	51%	44%	59%	37%	50%	65%	68%	49%	44%	53%	42%	48%
82.3%		84%	91%	80%	57%	87%	90%	78%	70%	83%	84%	86%	89%	91%
69.1%		75%	65%	78%	82%	58%	72%	72%	80%	76%	56%	60%	59%	65%
65.2%		65%	69%	61%	41%	79%	71%	64%	57%	67%	66%	69%	72%	67%
79.6%		87%	88%	88%	51%	79%	80%	84%	84%	86%	66%	76%	89%	77%
68.6%		81%	85%	84%	80%	41%	71%	70%	80%	52%	64%	57%	71%	56%
86.3%		88%	88%	82%	91%	93%	99%	95%	80%	93%	76%	74%	82%	81%
80.7%		87%	87%	76%	40%	93%	87%	77%	70%	91%	86%	87%	87%	81%
75.5%		89%	90%	89%	63%	82%	84%	78%	89%	83%	64%	83%	44%	44%
77.4%		75%	89%	92%	40%	84%	87%	61%	85%	78%	83%	77%	78%	77%
69.9%		79%	79%	84%	52%	52%	76%	75%	83%	77%	68%	53%	62%	69%
72.2%		81%	73%	73%	67%	70%	68%	71%	76%	80%	65%	68%	68%	79%
75.8%		81%	74%	74%	65%	78%	70%	76%	74%	81%	74%	73%	86%	79%
82.0%		67%	80%	84%	77%	81%	88%	85%	89%	75%	81%	86%	83%	90%
82.2%		81%	85%	85%	63%	90%	87%	84%	78%	83%	85%	81%	83%	84%
82.5%		93%	93%	95%	47%	81%	90%	84%	83%	93%	75%	81%	87%	70%
81.9%		90%	89%	84%	47%	90%	89%	85%	75%	95%	77%	89%	83%	72%
70.0%		67%	82%	79%	78%	65%	76%	77%	74%	64%	52%	72%	49%	75%
75.1%		73%	76%	63%	77%	82%	82%	65%	60%	80%	82%	75%	80%	81%
68.6%		71%	63%	66%	36%	86%	78%	61%	51%	73%	73%	78%	76%	80%
81.1%		78%	90%	79%	56%	92%	85%	85%	71%	78%	77%	90%	86%	87%
81.5%		81%	89%	85%	72%	68%	84%	82%	89%	86%	78%	79%	83%	83%
75.3%		80%	82%	80%	63%	78%	70%	71%	75%	74%	78%	79%	75%	74%
81.5%		81%	87%	77%	85%	82%	79%	83%	74%	85%	78%	83%	88%	77%
83.9%		83%	89%	85%	84%	87%	90%	88%	79%	83%	80%	82%	79%	82%
75.3%		70%	66%	66%	71%	94%	69%	70%	60%	82%	69%	85%	83%	94%
61.2%		54%	62%	59%	18%	76%	68%	57%	56%	66%	70%	74%	67%	69%
84.7%		85%	86%	87%	83%	81%	83%	89%	82%	80%	90%	86%	85%	84%
82.8%		81%	86%	69%	73%	93%	93%	92%	69%	89%	78%	96%	83%	74%
81.2%		86%	86%	76%	53%	91%	85%	85%	74%	84%	82%	86%	83%	85%
79.6%		78%	82%	83%	75%	84%	79%	80%	72%	80%	82%	84%	80%	76%
70.8%		71%	62%	57%	53%	80%	68%	76%	58%	79%	79%	78%	79%	81%
78.5%		81%	86%	70%	79%	78%	75%	85%	73%	76%	59%	74%	96%	89%
86.8%		93%	95%	77%	94%	75%	86%	91%	88%	97%	75%	78%	91%	89%
78.9%		82%	84%	86%	75%	72%	82%	79%	88%	81%	78%	74%	72%	73%
76.8%		88%	86%	76%	79%	54%	72%	85%	62%	93%	76%	65%	81%	81%
62.9%		77%	73%	84%	41%	50%	57%	48%	57%	63%	50%	61%	90%	67%
77.2%		73%	86%	77%	70%	73%	88%	80%	73%	76%	82%	83%	71%	72%
70.1%		73%	75%	62%	45%	84%	75%	71%	56%	64%	77%	76%	70%	83%
84.6%		87%	93%	89%	87%	91%	82%	85%	82%	88%	83%	79%	87%	67%
67.9%		57%	66%	77%	41%	72%	67%	64%	65%	76%	75%	75%	74%	74%
78.5%		74%	75%	75%	42%	92%	89%	74%	63%	83%	88%	88%	86%	91%
72.2%		74%	80%	84%	59%	52%	80%	77%	90%	81%	62%	69%	62%	69%
76.9%		80%	68%	69%	71%	79%	78%	80%	66%	85%	70%	71%	90%	93%
71.4%		76%	78%	84%	27%	79%	80%	81%	88%	71%	63%	69%	61%	71%
88.6%		91%	93%	88%	92%	88%	78%	88%	91%	90%	94%	93%	85%	81%
85.1%		84%	85%	94%	91%	79%	85%	82%	77%	72%	94%	80%	87%	96%
78.0%		70%	72%	72%	91%	70%	81%	88%	79%	80%	71%	79%	81%	80%
81.6%		82%	88%	76%	88%	70%	90%	91%	77%	87%	86%	83%	71%	72%
79.9%		63%	67%	80%	69%	73%	86%	87%	85%	90%	97%	85%	77%	80%
71.9%		80%	74%	70%	85%	60%	68%	83%	81%	79%	51%	66%	70%	68%
72.3%		64%	69%	77%	89%	49%	73%	77%	92%	73%	67%	77%	60%	73%
77.4%		83%	71%	71%	81%	86%	84%	68%	85%	68%	68%	77%	83%	81%
81.9%		86%	89%	87%	79%	88%	82%	84%	85%	87%	74%	74%	78%	72%
83.2%		77%	88%	79%	86%	87%	88%	83%	74%	78%	83%	85%	88%	86%
80.2%		79%	83%	73%	62%	88%	85%	84%	83%	86%	81%	86%	77%	76%
90.2%		88%	90%	92%	96%	90%	89%	89%	91%	88%	93%	88%	90%	88%
78.4%		82%	83%	76%	50%	88%	84%	83%	69%	86%	80%	82%	81%	75%
75.7%		73%	79%	84%	80%	78%	83%	79%	85%	78%	60%	77%	60%	68%
81.4%		80%	83%	72%	53%	93%	80%	78%	72%	87%	91%	91%	86%	92%