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%3Achile C10 - Run b82f0e6...

Global Dialogues GD4 - Chile (10 context Qs)

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

TAGS:

Global Dialogues Gd4

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Social interaction

AI Safety & Robustness

Best Models (Coverage)

1.Claude Sonnet 4
76.0%
2.Claude Sonnet 4.5
74.8%
3.GPT 4.1
74.5%
4.Claude Haiku 4.5
74.2%
5.Mistral Medium 3
73.2%

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 74.2%	1st 76.0%	2nd 74.8%	7th 73.0%	12th 69.9%	6th 73.1%	5th 73.2%	3rd 74.5%	9th 72.0%	13th 67.7%	11th 70.5%	10th 71.5%	8th 72.4%
73.0%		79%	76%	80%	81%	58%	77%	75%	74%	73%	66%	72%	71%	67%
58.8%		57%	58%	64%	78%	35%	51%	68%	77%	63%	57%	57%	51%	49%
88.3%		88%	95%	95%	86%	76%	93%	95%	100%	90%	86%	86%	83%	75%
69.2%		72%	73%	72%	61%	68%	68%	68%	71%	70%	68%	68%	66%	74%
54.3%		57%	62%	60%	52%	50%	58%	54%	55%	55%	42%	53%	49%	59%
79.6%		79%	83%	79%	79%	82%	80%	81%	82%	80%	78%	82%	85%	65%
72.1%		88%	82%	88%	71%	63%	82%	66%	61%	65%	65%	65%	76%	65%
77.9%		86%	86%	78%	67%	70%	73%	78%	82%	67%	80%	79%	83%	84%
70.2%		73%	73%	75%	38%	76%	75%	63%	74%	71%	69%	71%	77%	77%
75.0%		67%	71%	66%	84%	87%	76%	70%	78%	71%	85%	82%	76%	62%
76.8%		77%	77%	72%	76%	77%	75%	75%	78%	72%	79%	80%	79%	82%
80.3%		91%	82%	86%	81%	94%	71%	76%	79%	74%	55%	75%	89%	91%
77.5%		81%	76%	83%	76%	77%	67%	83%	81%	79%	79%	74%	80%	72%
55.2%		64%	63%	62%	53%	47%	54%	54%	51%	62%	48%	48%	48%	63%
59.4%		54%	63%	70%	40%	60%	60%	73%	70%	63%	57%	57%	45%	60%
44.9%		47%	45%	53%	71%	41%	49%	50%	53%	39%	28%	41%	37%	30%
92.9%		89%	89%	89%	99%	96%	97%	91%	92%	95%	95%	86%	96%	94%
81.3%		87%	89%	81%	94%	73%	85%	84%	86%	84%	59%	71%	79%	85%
75.5%		72%	75%	71%	76%	77%	70%	70%	71%	78%	80%	80%	80%	81%
82.2%		86%	82%	83%	79%	70%	88%	78%	81%	85%	84%	91%	81%	80%
84.2%		88%	89%	87%	92%	77%	86%	86%	91%	83%	65%	77%	83%	90%
90.0%		92%	95%	88%	93%	89%	88%	90%	89%	90%	89%	89%	86%	92%
75.8%		84%	80%	73%	76%	82%	77%	76%	76%	77%	76%	76%	73%	59%
54.5%		57%	71%	53%	75%	42%	56%	58%	64%	45%	47%	43%	37%	60%
70.1%		72%	72%	70%	71%	71%	70%	71%	78%	69%	63%	60%	72%	72%
76.6%		81%	77%	85%	74%	80%	75%	74%	76%	78%	74%	74%	74%	74%
82.3%		86%	87%	86%	87%	78%	87%	79%	87%	77%	75%	78%	80%	83%
72.5%		77%	70%	71%	70%	63%	70%	73%	76%	72%	76%	74%	76%	74%
82.5%		87%	79%	85%	86%	74%	84%	84%	85%	83%	82%	78%	83%	83%
82.2%		89%	86%	82%	89%	76%	79%	84%	83%	79%	80%	79%	79%	83%
67.8%		71%	72%	64%	68%	69%	67%	71%	67%	60%	69%	61%	69%	73%
78.9%		90%	94%	94%	89%	68%	87%	76%	76%	60%	69%	69%	73%	81%
77.9%		83%	85%	87%	69%	76%	83%	81%	82%	76%	75%	78%	72%	66%
55.9%		50%	56%	67%	82%	45%	59%	64%	65%	55%	43%	50%	47%	44%
65.1%		79%	78%	62%	67%	61%	70%	61%	54%	48%	62%	61%	71%	72%
74.9%		83%	80%	66%	52%	80%	74%	80%	72%	87%	80%	66%	77%	77%
61.4%		66%	75%	76%	49%	55%	65%	62%	63%	47%	57%	57%	61%	65%
66.2%		60%	72%	72%	57%	60%	61%	60%	73%	60%	73%	63%	76%	74%
76.5%		78%	77%	64%	75%	84%	76%	74%	78%	69%	86%	76%	76%	82%
57.7%		43%	63%	60%	62%	59%	59%	49%	60%	61%	52%	60%	66%	56%
74.8%		77%	77%	84%	72%	67%	81%	90%	83%	75%	59%	65%	65%	78%
83.3%		89%	93%	85%	64%	92%	88%	85%	67%	80%	84%	71%	88%	97%
70.6%		70%	70%	68%	71%	66%	70%	74%	71%	69%	78%	73%	69%	69%
58.7%		59%	63%	60%	70%	49%	62%	65%	60%	53%	53%	54%	61%	54%
81.2%		84%	85%	84%	76%	87%	83%	78%	86%	82%	80%	74%	80%	76%
84.5%		82%	88%	91%	82%	75%	92%	85%	91%	88%	68%	78%	87%	91%
80.2%		88%	85%	80%	79%	77%	86%	82%	79%	81%	80%	74%	75%	77%
87.8%		84%	100%	98%	84%	82%	87%	80%	87%	89%	95%	92%	84%	80%
83.7%		93%	84%	71%	73%	79%	90%	87%	80%	73%	90%	91%	84%	93%
70.0%		65%	71%	72%	74%	75%	60%	64%	67%	75%	68%	76%	72%	71%
82.0%		82%	81%	78%	89%	81%	78%	77%	85%	83%	77%	85%	84%	86%
49.2%		37%	57%	71%	61%	42%	65%	63%	68%	38%	31%	43%	31%	33%
65.7%		67%	74%	74%	60%	68%	63%	64%	69%	71%	55%	59%	62%	68%
47.2%		49%	46%	49%	69%	36%	46%	52%	49%	47%	46%	38%	44%	42%
75.9%		78%	79%	76%	80%	81%	78%	76%	73%	69%	61%	75%	81%	80%
78.9%		80%	84%	90%	77%	74%	77%	80%	86%	78%	78%	76%	72%	74%
42.5%		36%	49%	41%	73%	27%	49%	49%	59%	41%	14%	42%	34%	38%
68.1%		70%	68%	67%	70%	71%	65%	66%	60%	68%	60%	70%	74%	76%
41.2%		42%	48%	50%	59%	32%	44%	48%	49%	40%	25%	37%	31%	31%
71.2%		68%	69%	69%	72%	89%	73%	64%	61%	70%	68%	73%	72%	77%
68.5%		73%	78%	75%	58%	63%	69%	73%	83%	82%	57%	64%	67%	48%
82.2%		87%	84%	92%	88%	67%	82%	89%	85%	74%	79%	78%	83%	81%
87.2%		85%	94%	94%	92%	91%	94%	88%	97%	85%	70%	78%	78%	87%
77.2%		83%	81%	76%	69%	78%	81%	76%	76%	76%	78%	72%	77%	80%
75.9%		83%	84%	72%	64%	83%	78%	80%	76%	78%	71%	76%	82%	60%
68.4%		68%	70%	67%	78%	59%	77%	84%	71%	79%	50%	59%	53%	74%
73.0%		76%	78%	78%	76%	62%	77%	83%	75%	76%	64%	65%	68%	71%
69.2%		78%	71%	73%	71%	72%	64%	67%	69%	73%	61%	64%	59%	77%
75.7%		77%	72%	74%	75%	71%	72%	81%	73%	81%	77%	76%	79%	76%
91.2%		92%	93%	93%	92%	90%	94%	89%	92%	89%	90%	91%	90%	90%
72.8%		68%	71%	69%	72%	71%	70%	71%	82%	72%	71%	76%	74%	79%
78.2%		82%	80%	68%	60%	90%	84%	66%	77%	79%	82%	82%	81%	86%
82.5%		91%	87%	93%	79%	64%	82%	93%	90%	88%	73%	86%	85%	61%
51.1%		42%	64%	67%	58%	47%	41%	68%	66%	46%	30%	42%	46%	47%
64.5%		66%	70%	59%	50%	65%	68%	64%	62%	63%	67%	56%	63%	86%
66.5%		64%	73%	73%	58%	70%	69%	63%	62%	74%	62%	66%	65%	65%
76.6%		80%	75%	77%	77%	83%	70%	74%	82%	75%	71%	80%	74%	78%
81.8%		84%	82%	83%	79%	67%	85%	88%	84%	84%	78%	89%	85%	76%
69.4%		71%	74%	65%	63%	71%	67%	71%	66%	70%	68%	68%	70%	78%
78.4%		84%	81%	74%	86%	82%	79%	77%	75%	71%	58%	78%	85%	89%
90.8%		92%	90%	95%	92%	89%	95%	91%	92%	89%	89%	89%	93%	85%
76.0%		76%	83%	88%	76%	85%	65%	66%	68%	78%	67%	79%	72%	85%
79.1%		82%	79%	74%	54%	90%	68%	76%	73%	77%	86%	88%	90%	91%
90.1%		92%	88%	91%	85%	86%	86%	92%	85%	95%	95%	95%	85%	96%
85.2%		86%	88%	69%	85%	91%	92%	87%	90%	87%	79%	88%	87%	79%
61.1%		62%	67%	55%	54%	60%	62%	62%	59%	64%	61%	59%	59%	70%
69.2%		67%	75%	73%	70%	73%	72%	62%	63%	65%	74%	61%	75%	70%
81.0%		83%	74%	75%	81%	87%	75%	81%	74%	84%	87%	91%	80%	81%
60.7%		61%	74%	63%	79%	72%	61%	58%	56%	51%	45%	46%	59%	64%
76.4%		77%	82%	76%	82%	69%	79%	76%	79%	74%	62%	75%	85%	77%
73.9%		75%	73%	80%	79%	63%	80%	74%	68%	77%	76%	76%	74%	66%
48.0%		64%	65%	66%	78%	22%	37%	45%	47%	68%	31%	31%	31%	39%
70.2%		75%	81%	81%	44%	78%	69%	69%	71%	67%	62%	66%	74%	76%
75.5%		76%	66%	65%	78%	81%	77%	74%	72%	73%	79%	80%	79%	82%
58.0%		61%	55%	56%	55%	68%	64%	60%	60%	53%	53%	53%	55%	61%
81.7%		86%	91%	87%	89%	74%	83%	78%	85%	77%	73%	73%	85%	81%
64.2%		58%	63%	66%	65%	62%	56%	52%	63%	74%	67%	70%	68%	71%
85.8%		90%	96%	81%	56%	88%	90%	78%	80%	81%	96%	94%	94%	91%
57.5%		53%	66%	67%	83%	35%	61%	55%	71%	61%	45%	47%	51%	52%
65.9%		66%	68%	60%	89%	54%	57%	54%	69%	67%	45%	67%	79%	82%
59.1%		64%	64%	84%	44%	55%	63%	80%	75%	52%	42%	50%	42%	53%
90.5%		90%	92%	90%	87%	90%	87%	95%	91%	94%	85%	92%	93%	90%
77.4%		77%	77%	76%	76%	78%	79%	77%	81%	76%	78%	82%	71%	78%
87.3%		81%	89%	82%	91%	83%	89%	95%	87%	82%	84%	86%	97%	89%
71.8%		70%	74%	73%	63%	83%	63%	66%	65%	78%	62%	72%	85%	80%
82.4%		92%	76%	85%	76%	70%	80%	80%	90%	92%	90%	80%	70%	90%
54.1%		57%	59%	59%	77%	39%	57%	65%	67%	62%	36%	43%	41%	41%
65.2%		61%	62%	75%	84%	40%	65%	70%	81%	70%	62%	62%	60%	55%
72.5%		71%	72%	75%	72%	75%	78%	72%	79%	72%	56%	70%	75%	75%
77.1%		83%	74%	83%	69%	76%	75%	84%	81%	83%	77%	77%	74%	66%
74.6%		77%	79%	86%	82%	72%	80%	69%	75%	64%	69%	67%	71%	79%
81.2%		85%	86%	86%	77%	80%	82%	82%	84%	81%	83%	82%	77%	71%
73.2%		64%	76%	74%	79%	70%	78%	74%	77%	75%	74%	76%	67%	68%
78.2%		78%	80%	72%	50%	80%	76%	83%	79%	75%	86%	85%	91%	82%
72.8%		65%	78%	76%	85%	63%	76%	76%	78%	76%	64%	77%	66%	66%
61.8%		64%	64%	59%	62%	66%	57%	60%	63%	59%	57%	68%	61%	63%