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 Country%3Amexico Ctx - Run 7f81a53...

Global Dialogues GD4 - Mexico (with context)

DTEF: Predict response distributions for Mexico. 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 4.5
73.8%
2.Claude Sonnet 4
72.7%
3.GPT 4.1
72.0%
4.Gemini 2.5 Flash
71.0%
5.Mistral Medium 3
70.9%

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		6th 70.7%	2nd 72.7%	1st 73.8%	4th 71.0%	11th 65.0%	7th 70.1%	5th 70.9%	3rd 72.0%	8th 68.4%	13th 61.4%	12th 64.1%	10th 65.6%	9th 66.7%
65.2%		51%	76%	76%	82%	52%	68%	59%	72%	67%	33%	68%	65%	78%
51.1%		68%	63%	68%	54%	31%	43%	54%	81%	54%	25%	27%	45%	51%
67.6%		72%	72%	65%	71%	60%	56%	62%	76%	77%	50%	77%	64%	77%
71.3%		86%	65%	75%	67%	73%	62%	81%	82%	81%	70%	64%	80%	41%
53.8%		53%	63%	63%	73%	42%	51%	60%	56%	60%	44%	44%	37%	53%
80.4%		81%	87%	77%	90%	73%	77%	86%	87%	75%	72%	82%	81%	77%
64.8%		74%	74%	77%	62%	60%	65%	63%	65%	59%	59%	59%	66%	59%
73.8%		77%	69%	75%	64%	70%	72%	77%	77%	87%	83%	56%	78%	75%
70.0%		80%	84%	78%	48%	79%	80%	51%	55%	57%	51%	86%	69%	92%
68.8%		100%	75%	75%	56%	74%	59%	88%	64%	61%	61%	62%	52%	68%
76.8%		72%	78%	87%	77%	77%	73%	83%	87%	62%	73%	78%	77%	75%
58.8%		58%	58%	69%	51%	72%	56%	57%	56%	51%	65%	56%	64%	51%
73.0%		73%	73%	73%	73%	73%	73%	73%	73%	73%	73%	73%	73%	73%
55.5%		59%	68%	68%	56%	50%	53%	44%	36%	66%	50%	53%	59%	59%
68.8%		71%	74%	70%	78%	65%	71%	76%	74%	73%	58%	60%	56%	69%
60.9%		61%	66%	77%	64%	46%	75%	60%	66%	52%	53%	59%	52%	61%
86.5%		92%	100%	93%	86%	67%	84%	92%	94%	92%	86%	83%	84%	72%
75.6%		86%	86%	80%	87%	72%	83%	67%	77%	78%	53%	68%	76%	70%
73.2%		77%	69%	77%	70%	66%	77%	79%	79%	67%	79%	67%	77%	67%
77.1%		83%	75%	71%	77%	61%	81%	77%	71%	78%	93%	93%	71%	71%
68.9%		64%	64%	75%	70%	72%	64%	72%	75%	68%	62%	70%	70%	70%
85.5%		82%	82%	82%	86%	92%	88%	88%	85%	86%	86%	86%	82%	86%
84.0%		83%	90%	88%	90%	76%	79%	82%	92%	83%	79%	86%	88%	76%
59.1%		63%	62%	56%	89%	47%	67%	61%	78%	63%	42%	39%	33%	68%
67.1%		65%	75%	53%	66%	61%	60%	69%	54%	80%	72%	67%	71%	79%
73.8%		60%	76%	79%	77%	80%	57%	77%	68%	77%	77%	77%	77%	77%
73.5%		85%	82%	69%	75%	75%	72%	70%	77%	62%	62%	88%	76%	62%
43.5%		42%	45%	54%	38%	40%	43%	50%	58%	43%	25%	41%	49%	38%
59.9%		58%	56%	62%	58%	57%	64%	64%	62%	59%	58%	58%	65%	58%
61.5%		48%	72%	62%	63%	66%	57%	67%	72%	64%	45%	55%	67%	61%
81.2%		82%	86%	79%	83%	72%	70%	80%	83%	83%	92%	86%	82%	78%
78.9%		84%	80%	79%	75%	86%	86%	80%	79%	83%	62%	75%	75%	82%
62.3%		56%	70%	73%	88%	42%	70%	77%	60%	74%	72%	39%	37%	52%
64.8%		79%	65%	81%	71%	47%	74%	79%	80%	66%	31%	66%	38%	66%
84.2%		80%	93%	87%	86%	80%	83%	92%	79%	79%	87%	87%	82%	79%
68.5%		70%	68%	71%	77%	64%	67%	66%	70%	70%	67%	65%	65%	70%
65.9%		76%	69%	72%	69%	66%	56%	69%	67%	54%	49%	76%	65%	69%
70.4%		67%	72%	74%	74%	68%	74%	68%	74%	72%	68%	68%	68%	68%
79.2%		76%	82%	82%	71%	74%	82%	82%	76%	78%	78%	82%	86%	81%
70.1%		68%	68%	91%	68%	72%	68%	68%	68%	68%	68%	68%	68%	68%
62.6%		69%	72%	64%	68%	42%	67%	76%	74%	60%	44%	53%	56%	69%
68.2%		74%	63%	73%	68%	66%	79%	72%	63%	69%	61%	67%	68%	63%
64.7%		69%	63%	83%	78%	49%	62%	67%	71%	72%	83%	47%	43%	54%
52.3%		56%	55%	56%	46%	50%	58%	55%	52%	46%	50%	55%	49%	52%
66.8%		85%	88%	83%	84%	90%	90%	82%	78%	25%	32%	25%	38%	68%
57.7%		61%	61%	61%	53%	48%	67%	58%	58%	61%	37%	61%	62%	62%
79.5%		76%	83%	86%	90%	77%	87%	77%	82%	79%	71%	77%	72%	77%
87.5%		95%	94%	94%	94%	82%	82%	82%	67%	94%	89%	82%	94%	89%
83.3%		88%	88%	88%	78%	75%	90%	90%	84%	86%	69%	82%	79%	86%
70.5%		67%	74%	71%	67%	68%	71%	82%	74%	73%	67%	67%	69%	67%
85.2%		82%	87%	100%	82%	87%	80%	94%	94%	94%	77%	77%	74%	80%
64.2%		51%	73%	63%	61%	54%	70%	74%	86%	63%	63%	44%	64%	68%
76.9%		67%	89%	100%	74%	68%	82%	87%	84%	71%	60%	71%	76%	71%
49.1%		54%	58%	50%	59%	41%	58%	48%	56%	51%	51%	34%	43%	35%
80.0%		80%	80%	80%	80%	80%	80%	80%	80%	80%	80%	80%	80%	80%
70.2%		62%	78%	82%	74%	76%	62%	82%	83%	64%	62%	62%	62%	64%
48.6%		62%	49%	69%	58%	42%	53%	50%	66%	52%	16%	26%	38%	51%
73.2%		73%	73%	73%	73%	75%	73%	73%	73%	73%	73%	73%	73%	73%
61.8%		67%	68%	74%	61%	38%	77%	67%	70%	86%	42%	47%	40%	66%
72.2%		63%	68%	59%	48%	81%	80%	73%	80%	81%	69%	87%	70%	80%
72.8%		79%	77%	79%	65%	65%	70%	65%	76%	80%	80%	80%	62%	68%
53.5%		46%	66%	69%	59%	49%	53%	58%	53%	53%	42%	42%	60%	45%
80.9%		74%	86%	88%	86%	77%	100%	83%	88%	74%	74%	74%	74%	74%
78.0%		88%	81%	86%	83%	79%	76%	76%	86%	69%	65%	73%	79%	73%
73.4%		74%	70%	77%	80%	73%	68%	78%	78%	74%	69%	74%	70%	69%
58.6%		53%	71%	64%	82%	46%	79%	72%	74%	71%	21%	45%	30%	54%
55.8%		62%	68%	51%	70%	51%	59%	82%	68%	53%	32%	38%	46%	46%
69.5%		74%	69%	68%	74%	62%	73%	63%	73%	74%	55%	72%	73%	73%
58.2%		62%	56%	57%	65%	60%	62%	52%	65%	52%	47%	61%	62%	56%
88.0%		93%	82%	93%	75%	94%	93%	89%	94%	74%	93%	85%	94%	85%
58.5%		55%	55%	81%	55%	75%	55%	55%	55%	55%	55%	55%	55%	55%
67.0%		73%	77%	75%	49%	71%	71%	48%	74%	54%	71%	71%	62%	75%
67.1%		59%	72%	65%	72%	70%	64%	72%	65%	63%	55%	60%	89%	66%
58.4%		66%	53%	63%	62%	50%	76%	62%	61%	65%	52%	38%	49%	62%
74.0%		73%	80%	76%	68%	80%	80%	72%	66%	77%	79%	67%	77%	67%
84.1%		92%	100%	94%	74%	87%	92%	74%	80%	77%	77%	77%	92%	77%
68.9%		74%	81%	81%	57%	71%	74%	73%	73%	57%	47%	74%	66%	68%
69.5%		54%	66%	66%	74%	74%	79%	76%	75%	80%	46%	62%	74%	78%
79.0%		82%	81%	87%	90%	75%	72%	87%	89%	71%	72%	71%	75%	75%
80.0%		80%	80%	80%	80%	80%	80%	80%	80%	80%	80%	80%	80%	80%
82.2%		82%	82%	92%	85%	82%	88%	82%	80%	74%	74%	100%	74%	74%
68.2%		68%	76%	73%	63%	63%	74%	74%	68%	61%	76%	76%	63%	51%
67.0%		80%	74%	72%	50%	65%	64%	78%	72%	73%	49%	63%	73%	58%
65.4%		67%	66%	66%	65%	65%	69%	63%	61%	76%	63%	63%	63%	63%
75.6%		78%	77%	76%	77%	77%	77%	76%	73%	77%	71%	77%	69%	78%
82.9%		92%	85%	82%	74%	92%	78%	82%	77%	77%	83%	82%	92%	82%
54.8%		54%	54%	55%	52%	44%	54%	55%	54%	50%	55%	62%	62%	62%
56.7%		69%	56%	53%	58%	55%	53%	58%	41%	59%	74%	36%	60%	65%
76.2%		82%	80%	100%	94%	43%	70%	82%	81%	82%	74%	62%	62%	78%
75.4%		95%	73%	73%	84%	61%	77%	80%	82%	84%	80%	61%	77%	53%
57.0%		57%	55%	63%	78%	62%	52%	65%	43%	74%	28%	48%	62%	54%
59.0%		74%	64%	59%	64%	53%	59%	54%	55%	68%	82%	44%	44%	47%
62.9%		64%	64%	73%	64%	61%	69%	59%	67%	69%	34%	78%	54%	62%
61.4%		63%	63%	65%	63%	63%	63%	63%	63%	70%	62%	50%	55%	55%
44.4%		44%	54%	50%	40%	52%	58%	42%	42%	44%	31%	29%	47%	44%
72.5%		74%	74%	76%	88%	79%	79%	72%	81%	68%	60%	79%	56%	56%
58.0%		65%	62%	60%	66%	52%	67%	62%	60%	59%	38%	45%	62%	56%
70.0%		71%	75%	69%	72%	69%	70%	69%	69%	65%	59%	68%	77%	77%
52.9%		54%	80%	80%	69%	31%	60%	54%	80%	32%	31%	35%	37%	45%
68.4%		76%	86%	86%	69%	68%	68%	62%	64%	73%	63%	52%	52%	70%
66.7%		65%	78%	79%	87%	61%	57%	79%	76%	76%	37%	46%	66%	60%
64.6%		55%	62%	71%	71%	67%	71%	60%	62%	60%	69%	67%	57%	68%
62.7%		60%	71%	71%	60%	68%	60%	68%	57%	60%	60%	60%	60%	60%
53.4%		61%	51%	53%	67%	43%	49%	46%	61%	52%	62%	53%	43%	53%
71.3%		77%	77%	67%	62%	63%	67%	77%	70%	67%	79%	72%	79%	70%
84.1%		90%	85%	90%	82%	82%	81%	86%	86%	88%	86%	69%	82%	86%
66.5%		80%	59%	64%	80%	40%	69%	85%	74%	74%	67%	56%	50%	67%
59.8%		48%	74%	77%	82%	40%	59%	66%	100%	32%	56%	35%	69%	40%
74.4%		69%	83%	69%	77%	74%	78%	88%	83%	80%	59%	80%	65%	62%
70.5%		77%	72%	78%	74%	51%	77%	70%	76%	83%	66%	45%	80%	67%
77.6%		84%	79%	79%	77%	89%	71%	81%	68%	63%	58%	86%	82%	92%
68.6%		71%	77%	76%	80%	61%	53%	62%	87%	64%	54%	64%	70%	73%
70.0%		66%	80%	72%	77%	70%	92%	72%	86%	77%	41%	59%	59%	59%
75.9%		76%	76%	79%	75%	80%	75%	75%	83%	76%	64%	76%	76%	76%
83.4%		82%	82%	82%	82%	82%	82%	82%	82%	82%	100%	82%	82%	82%
59.1%		55%	63%	63%	55%	57%	57%	62%	55%	55%	57%	62%	62%	65%