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 cfad704...

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

AI Safety & Robustness

Social interaction

AI Bias & Fairness

Best Models (Coverage)

1.Claude 3.7 Sonnet
77.7%
2.Claude Sonnet 4
76.0%
3.GPT 5.1
75.2%
4.GPT 5
75.1%
5.Claude Sonnet 4.5
74.9%

🔀 Least Similar Models

Claude Sonnet 4.5vsGPT OSS 20b

71.8% similarity

👯 Most Similar Models

GPT 4.1 NanovsGPT 4o Mini

89.1% similarity

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 3.7 Sonnet	Claude Haiku 4.5	Claude Sonnet 4	Claude Sonnet 4.5	Gemini 2.5 Flash	Gemma 3 12b It	Llama 4 Maverick	Mistral Large 2411	Mistral Medium 3	GPT 4.1	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o	GPT 4o Mini	GPT 5	GPT 5.1	GPT OSS 120b	GPT OSS 20b	Qwen3 30b A3B Instruct 2507	Qwen3 32b	Grok 4.1 Fast
Score		1st 77.7%	7th 74.5%	2nd 76.0%	5th 74.9%	8th 73.4%	18th 69.9%	11th 73.1%	13th 72.3%	9th 73.3%	6th 74.6%	14th 72.0%	21st 68.0%	12th 73.1%	17th 70.3%	4th 75.1%	3rd 75.2%	19th 69.7%	20th 69.7%	15th 71.4%	16th 70.9%	10th 73.3%
73.7%		86%	79%	76%	80%	79%	58%	75%	74%	75%	74%	66%	66%	75%	65%	77%	76%	74%	67%	74%	78%	74%
58.9%			57%	58%	64%	87%	38%	50%	49%	61%	78%	63%	57%	72%	58%	74%	79%	46%	37%	55%	37%	57%
89.6%		92%	90%	96%	93%	80%	76%	93%	92%	95%	97%	93%	86%	93%	82%	96%	97%	86%	87%	83%	90%	85%
68.2%			69%	76%	72%	70%	71%	65%	70%	67%	70%	71%	68%	71%	68%	68%	71%	68%	59%	68%	57%	65%
53.5%			63%	61%	61%	53%	53%	60%	50%	54%	55%	53%	55%	53%	54%	58%	52%	40%	40%	53%	42%	61%
79.8%			79%	83%	79%	88%	82%	80%	79%	80%	85%	78%	81%	83%	82%	77%	85%	64%	85%	81%	71%	74%
69.5%		78%	84%	82%	88%	65%	61%	74%	67%	69%	61%	65%	65%	65%	56%	71%	72%	65%	70%	72%	65%	65%
73.7%			82%	86%	78%	77%	68%	73%	75%	75%	73%	67%	77%	72%	79%	78%	60%	70%	74%	73%	61%	76%
66.0%		74%	73%	73%	74%	36%	76%	75%	71%	63%	79%	71%	69%	69%	71%	45%	71%	69%	43%	70%	62%	52%
74.3%		55%	69%	71%	66%	84%	85%	77%	81%	66%	74%	71%	85%	78%	80%	70%	67%	85%	64%	77%	77%	79%
75.5%			77%	77%	72%	80%	77%	75%	75%	75%	78%	72%	74%	76%	80%	70%	73%	67%	74%	82%	81%	74%
77.6%		88%	88%	86%	86%	82%	91%	71%	71%	71%	80%	87%	69%	70%	79%	86%	76%	70%	57%	81%	70%	70%
78.6%			84%	76%	83%	83%	79%	75%	77%	83%	81%	76%	78%	73%	74%	77%	83%	83%	79%	86%	62%	79%
53.3%			64%	64%	62%	51%	47%	51%	41%	54%	51%	49%	48%	47%	48%	63%	64%	42%	42%	60%	56%	61%
62.6%		60%	54%	63%	68%	37%	61%	65%	70%	73%	75%	61%	57%	65%	57%	76%	68%	54%	73%	46%	73%	58%
46.9%			47%	45%	53%	60%	39%	49%	39%	48%	60%	45%	34%	53%	36%	62%	60%	40%	48%	37%	42%	41%
90.3%		89%	89%	86%	89%	96%	96%	92%	92%	91%	91%	91%	95%	86%	86%	82%	90%	95%	92%	89%	85%	94%
78.3%		73%	87%	89%	81%	83%	71%	84%	71%	84%	86%	85%	59%	85%	71%	81%	76%	66%	83%	79%	73%	78%
74.9%		76%	72%	76%	71%	78%	75%	68%	72%	74%	75%	75%	80%	75%	80%	75%	78%	69%	72%	79%	78%	75%
81.4%		90%	87%	79%	83%	80%	70%	92%	73%	75%	77%	83%	91%	85%	91%		91%	78%	74%	78%	78%	73%
85.8%		88%	88%	88%	90%	94%	77%	86%	85%	89%	91%	83%	65%	94%	76%	87%	90%	76%	88%	90%	89%	87%
88.8%		88%	92%	95%	88%	83%	89%	88%	90%	92%	88%	91%	92%	79%	89%	89%	84%	84%	92%	87%	95%	90%
76.3%			84%	80%	73%	72%	82%	77%	77%	78%	79%	79%	70%	78%	77%	72%	78%	74%	77%	64%	77%	78%
54.8%			59%	71%	60%	70%	42%	56%	62%	58%	56%	39%	42%	66%	43%	49%	63%	47%	55%	41%	56%	61%
69.1%			72%	72%	71%	66%	71%	71%	72%	62%	76%	66%	71%	73%	58%	81%	69%	65%	68%	70%	69%	60%
74.0%		72%	81%	76%	85%	74%	80%	75%	77%	74%	76%	75%	74%	74%	74%	67%	69%	73%	60%	74%	74%	69%
81.9%		84%	86%	87%	88%	86%	78%	84%	76%	79%	87%	76%	75%	84%	78%	89%	87%	80%	78%	80%	77%	80%
72.9%		73%	77%	70%	71%	70%	63%	70%	72%	74%	72%	72%	75%	75%	74%	75%	75%	75%	74%	76%	73%	75%
82.5%		88%	83%	83%	85%	81%	74%	85%	81%	85%	88%	83%	82%	84%	78%	87%	87%	83%	75%	78%	83%	79%
82.5%		86%	89%	86%	82%	89%	76%	79%	82%	87%	85%	77%	80%	85%	73%	89%	89%	79%	85%	79%	83%	73%
66.1%			74%	75%	64%	43%	69%	65%	67%	68%	66%	62%	69%	70%	61%	68%	65%	65%	71%	66%	64%	70%
82.7%			90%	93%	91%	84%	68%	94%	82%	86%	82%	72%	69%	83%	69%	92%	92%	93%	86%	72%	70%	87%
81.3%			80%	85%	86%	68%	75%	85%	80%	83%	85%	81%	75%	80%	70%	85%	83%	90%	94%	72%	85%	84%
52.8%			53%	51%	65%	70%	43%	59%	53%	55%	65%	53%	43%	57%	50%	61%	57%	43%	29%	40%	51%	59%
61.9%			79%	78%	63%	61%	62%	66%	67%	61%	47%	54%	61%	57%	61%	60%	56%	57%	58%	69%		60%
76.5%			83%	83%	66%	81%	80%	73%	78%	80%	74%	87%	80%	75%	67%	73%	74%	76%	72%	77%	80%	70%
66.7%			66%	75%	76%	83%	56%	65%	62%	62%	64%	50%	57%	64%	66%	81%	65%	62%	56%	69%	75%	79%
66.0%		65%	62%	72%	72%	69%	56%	61%	74%	62%	73%	65%	50%	51%	65%	77%	65%	61%	59%	74%	71%	81%
76.4%			78%	77%	64%	66%	84%	76%	84%	74%	64%	71%	86%	68%	75%	66%	78%	81%	94%	84%	81%	78%
56.8%		55%	43%	63%	60%	56%	59%	49%	65%	53%	51%	63%	55%	48%	60%	66%	70%	52%	47%	62%		59%
77.6%			77%	77%	84%	72%	69%	81%	79%	87%	84%	80%	65%	79%	65%	87%	86%	78%	87%	65%	76%	74%
80.5%		87%	89%	90%	83%	76%	92%	88%	95%	84%	73%	80%	73%	63%	70%	81%	76%	57%	57%	97%	85%	94%
71.5%			72%	70%	68%	84%	68%	70%	63%	73%	67%	67%	78%	69%	67%	77%	72%	70%	80%	69%		75%
64.8%			59%	61%	60%	65%	49%	64%	58%	65%	64%	55%	66%	73%	61%	55%	58%	73%	83%	57%	91%	79%
78.5%			84%	85%	84%	77%	82%	85%	84%	78%	87%	80%	80%	81%	80%	86%	85%	69%	63%	80%	41%	78%
83.8%			80%	88%	88%	90%	75%	89%	83%	86%	95%	88%	68%	93%	78%	89%	86%	83%	71%	86%	87%	73%
82.1%			88%	83%	82%	89%	77%	86%	89%	82%	81%	79%	80%	85%	74%	82%	78%	77%	81%	75%	83%	91%
89.4%			96%	92%	98%	84%	79%	89%	80%	80%	95%	95%	87%	87%	92%	98%	99%	98%	87%	84%	87%	80%
81.4%		74%	90%	84%	77%	72%	79%	84%	78%	87%	80%	88%	91%	63%	91%	87%	79%	85%	69%	81%	89%	82%
70.7%		75%	65%	74%	72%	78%	75%	61%	48%	64%	68%	76%	68%	68%	76%	66%	75%	74%	79%	76%	70%	76%
80.0%		85%	74%	81%	81%	85%	81%	78%	72%	77%	85%	85%	77%	80%	85%	80%	83%	83%	68%	82%	72%	85%
56.5%		68%	42%	54%	74%	61%	36%	65%	50%	62%	70%	42%	29%	62%	36%	68%	70%	69%	65%	31%	64%	69%
65.6%		70%	65%	72%	69%	60%	65%	65%	70%	67%	71%	71%	53%	66%	60%	72%	63%	61%	61%	62%	68%	66%
48.1%			49%	46%	50%	61%	39%	46%	47%	55%	46%	52%	46%	49%	38%	52%	49%	46%	39%	44%	52%	57%
75.0%			78%	79%	76%	78%	81%	78%	71%	75%	72%	69%	56%	71%	69%	80%	77%	72%	82%	81%	76%	79%
80.6%		88%	80%	84%	88%	78%	74%	77%	84%	80%	86%	75%	78%	80%	76%	82%	84%	86%	82%	72%	78%	80%
48.0%		52%	36%	49%	41%	73%	27%	47%	56%	48%	63%	39%	14%	50%	47%	69%	72%	48%	42%	28%	56%	50%
68.2%			70%	68%	69%	65%	71%	65%	73%	66%	60%	69%	66%	67%	71%	70%	64%	62%	72%	74%	67%	76%
42.3%			42%	45%	50%	68%	32%	42%	37%	44%	47%	42%	25%	49%	37%	54%	47%	29%	36%	33%	41%	45%
69.6%			76%	69%	71%	76%	89%	72%	75%	62%	66%	66%	60%	70%	71%	60%	70%	67%	64%	72%	63%	73%
71.3%		75%	73%	78%	75%	62%	63%	75%	78%	73%	80%	85%	57%	64%	64%	76%	79%	68%	77%	59%	69%	67%
83.9%		89%	87%	87%	90%	87%	68%	84%	85%	85%	89%	74%	79%	90%	78%	91%	87%	84%	80%	85%		80%
86.0%		92%	85%	94%	94%	89%	91%	94%	94%	97%	100%	85%	69%	90%	83%	91%	92%	67%	75%	78%	55%	91%
77.9%			82%	81%	76%	70%	80%	81%	76%	76%	74%	79%	69%	84%	78%	82%	80%	75%	83%	75%	81%	76%
79.6%			82%	84%	72%	76%	83%	77%	77%	79%	78%	86%	71%	83%	76%	80%	81%	74%	82%	84%	84%	83%
69.0%		73%	68%	68%	67%	78%	59%	80%	76%	84%	71%	71%	56%	78%	59%	74%	73%	72%	67%	66%	27%	81%
75.9%		85%	78%	78%	75%	83%	62%	78%	84%	82%	77%	71%	64%	76%	63%	82%	82%	77%	83%	68%	70%	76%
64.5%			78%	71%	74%	65%	72%	64%	55%	67%	70%	71%	60%	62%	64%	65%	68%	68%	56%	59%	42%	60%
74.4%		79%	77%	73%	73%	72%	73%	72%	74%	81%	74%	81%	77%	70%	77%	82%	79%	66%	60%	80%	67%	75%
91.1%			92%	92%	93%	92%	90%	94%	76%	89%	95%	90%	90%	97%	91%	95%	90%	95%	81%	90%	95%	95%
73.2%			71%	71%	69%	72%	71%	81%	69%	71%	83%	68%	71%	77%	84%	76%	81%	68%	67%	72%	63%	79%
76.7%		74%	82%	79%	68%	33%	90%	84%	89%	70%	77%	74%	83%	87%	83%	69%	75%	87%	67%	81%	81%	78%
86.3%		95%	91%	87%	93%	79%	64%	82%	95%	93%	89%	86%	64%	100%	86%	93%	92%	77%	83%	86%		91%
56.9%		60%	59%	61%	67%	77%	47%	41%	70%	68%	73%	53%	32%	65%	42%	61%	57%	61%	58%	26%		60%
68.4%			66%	76%	59%	51%	65%	68%	72%	63%	65%	64%	81%	71%	65%	60%	70%	72%	82%	64%	78%	76%
64.6%		68%	68%	73%	73%	58%	70%	69%	66%	63%	66%	73%	66%	58%	66%	70%	65%	58%	42%	65%	67%	53%
73.9%			80%	87%	77%	77%	83%	73%	77%	74%	81%	66%	61%	74%	71%	81%	71%	63%	69%	74%	72%	66%
82.8%		82%	84%	82%	78%	81%	75%	85%	84%	87%	83%	90%	87%	82%	84%	83%	85%	75%	90%	83%	79%	79%
68.9%			70%	74%	65%	48%	70%	67%	69%	71%	66%	64%	75%	75%	75%	69%	72%	71%	63%	73%		72%
76.7%			80%	81%	74%	84%	82%	79%	76%	77%	75%	71%	61%	69%	70%	85%	82%	72%	73%	86%	79%	79%
88.5%		90%	92%	90%	95%	95%	93%	95%	85%	91%	95%	90%	89%	88%	89%	93%	87%	87%	80%	95%	68%	72%
70.1%		71%	76%	82%	88%	77%	83%	63%	61%	67%	69%	78%	56%	62%	79%	62%	69%	62%	62%	81%	62%	62%
76.9%		76%	82%	79%	72%	53%	90%	72%	67%	76%	73%	76%	86%	79%	86%	69%	73%	74%	79%	90%	79%	83%
89.5%		88%	92%	94%	93%	88%	83%	90%	100%	92%	88%	95%	95%	73%	93%	92%	91%	89%	72%	83%	93%	96%
84.8%			86%	88%	68%	92%	91%	92%	86%	87%	83%	88%	79%	82%	87%	85%	88%	80%	83%	92%	82%	77%
60.1%			60%	63%	56%	58%	60%	62%	57%	57%	57%	57%	61%	56%	59%	63%	60%	63%	69%	59%	59%	65%
67.3%			70%	75%	74%	70%	73%	63%	63%	61%	64%	66%	74%	64%	74%	60%	64%	50%	66%	75%		72%
79.1%		74%	83%	74%	75%	82%	87%	83%	70%	78%	83%	83%	87%	79%	88%	69%	79%	81%	78%	85%	72%	72%
58.5%			61%	71%	63%	74%	78%	61%	63%	58%	57%	51%	45%	61%	46%	56%	62%	44%	41%	60%		60%
72.2%		77%	79%	81%	76%	82%	69%	79%	76%	70%	77%	71%	62%	75%	75%	57%	52%	65%	72%	85%	70%	66%
73.4%			75%	73%	80%	78%	63%	82%	71%	74%	66%	77%	76%	74%	76%	74%	70%	77%	54%	77%		77%
52.1%			64%	65%	66%	76%	27%	37%	49%	45%	48%	64%	31%	44%	31%	71%	72%	63%	34%	39%	37%	79%
71.3%		75%	76%	81%	79%	44%	69%	72%	75%	74%	65%	74%	62%	72%	66%	78%	76%	82%	72%	71%	72%	62%
72.6%		71%	74%	66%	68%	77%	81%	67%	64%	74%	72%	76%	79%	76%	82%	64%	68%	66%	72%	83%	84%	60%
56.9%			61%	66%	56%	63%	68%	64%	63%	59%	58%	49%	53%	55%	53%	49%	56%	45%	57%	61%	53%	48%
81.4%			81%	91%	87%	85%	74%	82%	78%	78%	91%	77%	73%	81%	73%	81%	88%	84%	71%	84%		88%
65.1%		55%	61%	63%	74%	65%	62%	55%	61%	53%	65%	68%	81%	62%	75%	64%	73%	53%	86%	75%	56%	61%
86.5%		90%	86%	96%	81%	56%	88%	90%	88%	90%	80%	81%	96%	87%	94%	79%	81%	88%	94%	95%	96%	81%
58.2%			53%	64%	66%	73%	31%	63%	47%	56%	66%	64%	45%	77%	52%	74%	80%	48%	64%	46%	45%	50%
65.7%			67%	63%	60%	82%	54%	57%	71%	54%	69%	70%	45%	76%	61%	64%	70%	63%	61%	66%	89%	72%
64.8%		83%	64%	65%	86%	44%	57%	63%	75%	76%	75%	49%	42%	61%	51%	70%	75%	49%	87%	40%	69%	79%
90.0%		92%	90%	92%	90%	86%	90%	87%	92%	95%	88%	94%	85%	92%	94%	95%	91%	85%	83%	90%	91%	89%
77.2%		72%	80%	77%	74%	73%	81%	81%	84%	80%	74%	77%	78%	71%	78%	80%	77%	73%	74%	78%	81%	78%
84.0%		79%	81%	89%	82%	95%	83%	89%	91%	94%	87%	82%	84%	89%	84%	73%	80%	80%	84%	89%	75%	75%
68.1%		66%	70%	71%	73%	66%	82%	63%	59%	63%	68%	78%	62%	71%	72%	78%	66%	66%	66%	80%	66%	45%
82.5%		76%	92%	76%	89%	79%	70%	85%	83%	77%	90%	88%	80%	95%	74%	88%	91%	92%	68%	70%	79%	91%
58.7%			57%	59%	57%	77%	39%	53%	46%	70%	65%	62%	36%	48%	43%	82%	74%	49%	62%	45%	82%	67%
65.8%			62%	62%	71%	80%	40%	61%	55%	70%	76%	69%	62%	79%	62%	79%	85%	60%	61%	60%	58%	63%
72.8%		77%	76%	72%	75%	71%	75%	78%	75%	71%	79%	73%	61%	70%	73%	77%	72%	65%	69%	75%	73%	72%
77.4%			85%	74%	81%	69%	76%	74%	74%	83%	83%	74%	77%	81%	77%	81%	81%	77%	80%	73%	68%	80%
74.1%			77%	83%	88%	84%	72%	80%	77%	76%	72%	63%	69%	74%	67%	77%	74%	60%	67%	71%	64%	87%
83.5%		86%	85%	86%	86%	86%	80%	86%	87%	86%	85%	80%	88%	83%	83%	85%	82%	78%	82%	77%	82%	81%
74.0%		80%	64%	76%	74%	79%	70%	78%	81%	79%	78%	74%	74%	78%	72%	79%	80%	72%	62%	62%	68%	74%
78.4%			78%	80%	72%	50%	80%	76%	81%	81%	76%	74%	85%	77%	77%	70%	79%	90%	94%	87%		82%
75.1%		76%	65%	78%	76%	85%	63%	76%	62%	76%	78%	73%	71%	74%	77%	84%	78%	71%	81%	69%	77%	87%
65.2%			64%	56%	56%	76%	71%	57%	63%	62%	60%	66%	57%	64%	67%	76%	64%	76%	54%	63%	76%	76%

Model Similarity Dendrogram

Hierarchical clustering of models based on response similarity. Models grouped closer are more similar.