DTeval

A Collective Intelligence Project

Loading blueprint versions...

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

Analysis: Gd4 C5 Dtef Global Dialogues Gd4 Country%3Amexico C5 - Run d552824...

Global Dialogues GD4 - Mexico (5 context Qs)

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
68.2%
2.Claude Haiku 4.5
68.2%
3.Claude Sonnet 4.5
67.8%
4.GPT 4.1
67.8%
5.GPT 4.1 Mini
67.8%

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		2nd 68.2%	1st 68.2%	4th 67.8%	7th 66.7%	13th 62.3%	8th 66.5%	6th 67.8%	3rd 67.8%	5th 67.8%	12th 63.4%	9th 65.8%	10th 65.3%	11th 65.0%
66.9%		63%	77%	80%	73%	53%	63%	73%	77%	62%	62%	53%	67%	67%
35.2%		34%	40%	36%	53%	11%	34%	37%	53%	34%	34%	36%	31%	25%
76.2%		77%	78%	78%	87%	70%	78%	73%	82%	80%	72%	68%	68%	80%
80.5%		79%	79%	80%	86%	76%	83%	85%	85%	79%	80%	83%	82%	69%
47.8%		51%	51%	63%	56%	25%	51%	53%	53%	51%	40%	44%	38%	45%
71.6%		76%	70%	72%	75%	66%	69%	74%	74%	76%	72%	80%	69%	58%
65.0%		69%	63%	72%	72%	60%	70%	60%	59%	63%	66%	59%	66%	66%
76.8%		78%	68%	70%	74%	72%	75%	82%	80%	78%	79%	83%	82%	78%
74.1%		76%	72%	59%	74%	79%	77%	64%	80%	79%	74%	75%	72%	82%
82.6%		93%	92%	89%	78%	72%	90%	88%	88%	79%	85%	85%	73%	62%
73.9%		70%	82%	72%	65%	67%	72%	83%	79%	74%	80%	74%	77%	66%
58.8%		62%	61%	55%	53%	64%	55%	55%	54%	66%	50%	57%	63%	69%
83.2%		86%	91%	92%	82%	78%	81%	83%	76%	82%	82%	81%	81%	87%
59.1%		67%	73%	68%	61%	48%	59%	59%	56%	59%	51%	47%	53%	67%
58.3%		53%	65%	65%	50%	55%	59%	64%	63%	56%	57%	63%	52%	56%
53.7%		53%	57%	57%	66%	37%	58%	62%	57%	53%	44%	55%	48%	51%
92.3%		90%	85%	86%	89%	100%	100%	91%	100%	93%	100%	83%	92%	91%
63.5%		73%	68%	46%	58%	62%	62%	61%	53%	77%	68%	68%	68%	62%
48.5%		55%	45%	47%	40%	56%	40%	47%	40%	59%	36%	54%	55%	57%
81.5%		83%	78%	78%	83%	74%	83%	83%	94%	73%	89%	80%	83%	78%
75.8%		82%	79%	69%	71%	84%	76%	75%	71%	92%	56%	75%	80%	76%
87.4%		91%	88%	92%	86%	86%	83%	87%	85%	88%	93%	92%	82%	83%
66.8%		75%	71%	74%	49%	57%	71%	75%	71%	62%	75%	73%	64%	51%
46.2%		47%	52%	52%	44%	42%	52%	53%	52%	47%	45%	33%	36%	46%
69.8%		69%	65%	65%	64%	72%	68%	72%	70%	71%	73%	69%	72%	77%
75.5%		87%	68%	75%	69%	80%	64%	76%	77%	79%	77%	71%	80%	79%
68.0%		77%	73%	69%	67%	61%	67%	62%	64%	70%	59%	69%	71%	75%
64.9%		67%	56%	68%	68%	48%	67%	75%	70%	67%	73%	65%	58%	62%
61.0%		63%	61%	51%	58%	70%	56%	57%	49%	61%	56%	69%	71%	71%
69.3%		70%	67%	61%	71%	62%	72%	67%	71%	73%	72%	72%	71%	72%
65.5%		69%	64%	70%	65%	62%	65%	64%	70%	71%	62%	66%	65%	59%
77.3%		81%	74%	85%	76%	71%	79%	81%	83%	85%	75%	79%	79%	57%
52.8%		49%	50%	62%	80%	40%	49%	65%	65%	49%	46%	48%	39%	45%
51.1%		52%	59%	59%	63%	34%	56%	62%	62%	45%	46%	52%	37%	37%
77.5%		88%	85%	71%	87%	71%	77%	75%	64%	70%	74%	82%	79%	85%
60.3%		61%	61%	57%	57%	61%	62%	61%	61%	63%	59%	59%	62%	60%
61.4%		62%	69%	69%	63%	62%	59%	58%	59%	59%	57%	58%	64%	59%
48.6%		36%	43%	43%	50%	55%	43%	43%	53%	43%	62%	46%	60%	55%
68.0%		70%	71%	61%	69%	69%	67%	69%	60%	67%	75%	64%	67%	75%
55.9%		49%	49%	49%	64%	62%	42%	58%	55%	59%	61%	71%	52%	56%
52.7%		53%	55%	55%	65%	32%	52%	62%	59%	53%	44%	49%	53%	53%
72.8%		75%	69%	77%	73%	69%	77%	72%	74%	73%	79%	66%	74%	68%
53.3%		49%	59%	67%	49%	41%	49%	64%	54%	54%	57%	52%	42%	56%
51.1%		52%	56%	50%	55%	37%	54%	56%	50%	50%	51%	57%	46%	50%
85.3%		87%	83%	89%	92%	82%	93%	82%	83%	81%	84%	77%	93%	83%
56.0%		56%	58%	55%	61%	47%	61%	57%	62%	59%	51%	48%	58%	55%
79.5%		86%	77%	71%	83%	75%	86%	82%	75%	81%	87%	80%	76%	74%
86.8%		91%	94%	95%	82%	75%	94%	75%	94%	94%	75%	98%	94%	67%
87.5%		88%	88%	88%	83%	89%	93%	90%	88%	82%	90%	88%	77%	93%
50.5%		59%	46%	49%	52%	56%	40%	40%	49%	64%	34%	50%	64%	54%
64.0%		69%	76%	62%	71%	73%	50%	56%	58%	76%	44%	59%	71%	67%
62.4%		68%	68%	74%	31%	65%	65%	73%	77%	61%	64%	61%	49%	55%
75.5%		76%	85%	85%	91%	64%	68%	73%	87%	77%	67%	69%	71%	68%
41.4%		43%	43%	32%	53%	36%	43%	49%	41%	43%	40%	45%	35%	35%
84.2%		80%	91%	82%	81%	77%	78%	87%	89%	85%	90%	86%	91%	78%
71.6%		78%	78%	60%	58%	67%	71%	75%	59%	73%	80%	80%	76%	76%
44.5%		36%	58%	55%	60%	31%	51%	38%	56%	45%	37%	41%	33%	37%
74.2%		75%	68%	73%	73%	75%	68%	73%	71%	81%	77%	79%	76%	76%
44.5%		42%	47%	45%	58%	33%	42%	52%	53%	42%	40%	45%	38%	42%
74.0%		77%	77%	73%	71%	77%	72%	68%	69%	72%	78%	73%	75%	80%
68.3%		72%	65%	73%	70%	69%	75%	70%	70%	69%	62%	62%	69%	62%
57.7%		59%	63%	71%	64%	39%	55%	57%	63%	51%	59%	57%	61%	51%
84.2%		80%	93%	88%	88%	94%	93%	89%	93%	77%	67%	77%	83%	73%
69.8%		77%	69%	74%	76%	66%	70%	68%	70%	67%	70%	72%	70%	58%
62.1%		61%	62%	65%	59%	55%	58%	62%	58%	71%	70%	65%	64%	57%
73.1%		73%	83%	90%	74%	58%	79%	81%	84%	71%	67%	62%	56%	72%
77.5%		79%	83%	85%	76%	57%	84%	100%	76%	78%	84%	72%	63%	71%
70.2%		75%	72%	72%	73%	67%	74%	74%	72%	75%	55%	71%	59%	73%
54.6%		53%	58%	58%	63%	58%	47%	48%	65%	54%	41%	50%	53%	62%
87.7%		94%	93%	93%	89%	90%	89%	84%	89%	74%	84%	82%	93%	86%
81.7%		82%	85%	80%	85%	73%	79%	76%	85%	82%	82%	84%	87%	82%
69.5%		71%	69%	69%	63%	69%	71%	67%	71%	73%	75%	75%	67%	63%
74.0%		76%	78%	83%	78%	74%	67%	88%	78%	72%	57%	72%	72%	67%
60.8%		66%	55%	65%	53%	49%	56%	65%	68%	59%	57%	69%	75%	53%
72.6%		71%	81%	63%	71%	84%	78%	66%	65%	79%	68%	68%	78%	72%
81.9%		87%	87%	87%	58%	94%	87%	76%	58%	84%	86%	87%	87%	87%
65.2%		69%	71%	66%	60%	76%	71%	60%	60%	63%	57%	63%	71%	60%
77.2%		80%	79%	82%	79%	63%	76%	76%	75%	80%	86%	76%	76%	75%
72.8%		76%	68%	71%	79%	63%	70%	80%	82%	77%	76%	71%	70%	64%
82.2%		90%	87%	68%	86%	77%	91%	85%	74%	87%	70%	86%	79%	89%
86.4%		81%	92%	92%	80%	89%	92%	86%	82%	92%	84%	79%	92%	82%
51.8%		50%	56%	47%	50%	67%	45%	50%	42%	57%	30%	53%	63%	63%
69.3%		76%	75%	68%	43%	71%	69%	69%	61%	75%	73%	73%	74%	74%
64.4%		66%	63%	64%	63%	64%	64%	70%	63%	64%	65%	70%	63%	58%
74.8%		73%	77%	77%	74%	77%	78%	75%	77%	73%	69%	73%	75%	74%
76.3%		83%	82%	71%	69%	77%	78%	78%	71%	79%	75%	80%	78%	71%
39.4%		43%	43%	40%	38%	37%	35%	38%	30%	43%	30%	43%	44%	48%
56.2%		63%	51%	41%	54%	71%	56%	49%	43%	59%	59%	64%	65%	55%
56.4%		61%	74%	62%	79%	39%	54%	56%	62%	56%	27%	41%	54%	68%
71.2%		77%	77%	77%	68%	60%	62%	65%	75%	77%	77%	66%	77%	68%
67.5%		59%	64%	74%	72%	51%	67%	78%	72%	63%	69%	69%	69%	70%
46.0%		62%	75%	63%	59%	23%	28%	45%	50%	59%	33%	31%	36%	34%
63.4%		59%	59%	65%	53%	66%	72%	72%	71%	78%	53%	67%	44%	65%
62.3%		62%	65%	53%	61%	63%	64%	64%	55%	67%	58%	62%	72%	64%
41.3%		42%	49%	38%	46%	46%	42%	35%	36%	35%	40%	39%	44%	45%
74.1%		74%	74%	76%	74%	72%	75%	71%	75%	75%	77%	75%	74%	71%
60.5%		62%	60%	63%	57%	62%	53%	60%	62%	60%	62%	62%	64%	60%
79.5%		84%	83%	92%	53%	79%	75%	84%	70%	81%	88%	81%	81%	83%
46.9%		49%	46%	59%	64%	29%	46%	51%	59%	46%	38%	41%	37%	45%
63.2%		70%	65%	65%		60%	56%	50%	63%	73%	47%	59%	73%	77%
64.8%		66%	74%	82%	31%	65%	67%	78%	74%	67%	54%	68%	51%	66%
74.9%		60%	75%	80%	82%	66%	76%	82%	75%	80%	76%	71%	75%	76%
66.4%		71%	58%	71%	66%	64%	64%	60%	68%	71%	60%	66%	76%	68%
60.9%		61%	58%	61%	55%	48%	64%	56%	72%	67%	60%	66%	64%	60%
48.7%		52%	45%	45%	43%	66%	47%	41%	37%	56%	32%	53%	57%	59%
74.5%		66%	62%	72%	21%	77%	88%	93%	88%	88%	86%	72%	73%	83%
56.2%		69%	38%	27%	71%	53%	64%	77%	80%	54%	56%	57%	38%	46%
47.5%		47%	45%	54%	77%	21%	46%	58%	68%	52%	24%	45%	33%	47%
74.2%		76%	83%	81%	78%	76%	83%	72%	69%	72%	59%	83%	62%	70%
65.1%		61%	63%	72%	67%	63%	62%	70%	83%	62%	62%	62%	57%	62%
75.8%		88%	83%	83%	93%	66%	73%	71%	73%	72%	70%	65%	76%	73%
60.2%		65%	58%	79%	79%	42%	70%	58%	66%	64%	63%	54%	42%	42%
72.8%		72%	70%	75%	77%	63%	78%	80%	85%	76%	62%	67%	69%	72%
73.3%		75%	75%	73%	56%	67%	73%	83%	73%	73%	77%	79%	73%	76%
73.4%		67%	67%	72%	77%	88%	83%	83%	72%	67%	56%	88%	67%	67%
49.4%		51%	52%	46%	53%	45%	53%	48%	46%	48%	47%	47%	53%	53%