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%3Agermany C10 - Run 1b7c7ce...

Global Dialogues GD4 - Germany (10 context Qs)

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

TAGS:

Global Dialogues Gd4

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Efficiency & Succinctness

AI Safety & Robustness

Best Models (Coverage)

1.Claude 3.7 Sonnet
70.2%
2.Claude Sonnet 4
70.1%
3.Claude Sonnet 4.5
70.0%
4.GPT 4.1
69.0%
5.Mistral Large 2411
68.0%

🔀 Least Similar Models

Claude Sonnet 4.5vsGPT OSS 20b

71.8% similarity

👯 Most Similar Models

Claude 3.7 SonnetvsClaude Sonnet 4

91.9% 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 70.2%	7th 67.6%	2nd 70.1%	3rd 70.0%	19th 62.2%	16th 63.2%	9th 67.3%	5th 68.0%	12th 65.7%	4th 69.0%	11th 67.0%	18th 62.2%	6th 68.0%	13th 64.9%	10th 67.2%	8th 67.6%	20th 62.0%	21st 60.6%	14th 64.9%	15th 63.3%	17th 63.0%
64.8%		71%	60%	60%	70%	81%	38%	57%	66%	65%	60%	65%	66%	59%	57%	69%	67%	60%	69%	65%	78%	78%
47.4%			47%	54%	63%	64%	27%	36%	46%	45%	62%	45%	52%	59%	43%	65%	53%	50%	43%	41%	30%	23%
76.1%		78%	75%	69%	70%	43%	86%	85%	84%	75%	75%	85%	75%	69%	85%	86%	86%	75%	70%	84%	84%	59%
64.2%			70%	70%	70%	56%	75%	68%	65%	68%	61%	65%	65%	71%	63%	61%	68%	53%	59%	63%	62%	51%
54.5%			60%	60%	59%	46%	51%	54%	57%	57%	57%	51%	63%	68%	50%	55%	44%	48%	43%	50%	57%	60%
77.3%			71%	79%	79%	52%	60%	79%	77%	89%	88%	89%	89%	87%	85%	79%	88%	77%	48%	75%		77%
73.3%		81%	71%	81%	81%	87%	62%	81%	81%	81%	66%	75%	86%	66%	66%		74%	55%	49%	87%	49%	87%
68.8%			64%	74%	52%	72%	76%	71%	74%	70%	74%	77%	72%	67%	72%	51%	72%	62%	63%	64%	71%	77%
67.7%			64%	72%	72%	44%	68%	77%	77%	67%	62%	44%	82%	63%	76%	77%	73%	77%	73%	72%	49%	65%
55.3%			45%	46%	46%	28%	65%	72%	81%	58%	58%	53%	71%	63%	71%	29%	48%	49%	53%	71%	40%	58%
78.0%			84%	84%	84%	35%	84%	86%	83%	72%	84%	86%	78%	78%	84%	72%	84%	76%	70%	86%	65%	84%
63.1%		78%	69%	75%	78%	60%	67%	60%	56%	60%	70%	75%	43%	66%	67%	57%	61%	53%	67%	65%	53%	46%
65.1%			71%	70%	70%	66%	66%	71%	71%	58%	70%	66%	65%	72%	72%	63%	70%	42%	47%	65%	65%	62%
72.7%			76%	76%	73%	67%	62%	80%	60%	73%	67%	89%	41%	62%	76%	78%	91%	81%	57%	76%	73%	96%
58.9%			67%	65%	71%	61%	69%	60%	68%	59%	75%	54%	56%	53%	49%	55%	56%	59%	63%	48%	63%	27%
54.9%			51%	51%	68%	95%	34%	51%	45%	51%	73%	56%	35%	51%	48%	73%	76%	41%	51%	41%	53%	54%
46.2%		46%	46%	38%	46%	38%	53%	45%	61%	45%	43%	45%	46%	51%	47%	36%	38%	46%	46%	45%	43%	66%
54.5%		57%	57%	67%	59%	57%	52%	52%	63%	56%	50%	54%	43%	46%	48%	57%	57%	63%	52%	63%	43%	48%
65.2%		68%	65%	67%	74%	67%	60%	64%	71%	64%	72%	64%	60%	58%	65%	69%	68%	64%	60%	64%	58%	67%
71.0%		78%	70%	60%	60%	63%	52%	73%	75%	60%	57%	90%	70%	70%	73%	70%	81%	79%	89%	69%	75%	78%
78.7%		74%	89%	74%	79%	76%	84%	78%	92%	91%	74%	100%	63%	76%	68%	79%	84%	79%	66%	86%	69%	71%
72.4%			70%	76%	72%	74%	81%	62%	79%	79%	74%	72%	79%	74%	79%	80%	58%	75%	80%	79%	61%	45%
67.5%			71%	83%	66%	64%	65%	71%	73%	64%	64%	70%	66%	68%	71%	58%	56%	79%	33%	70%	68%	90%
40.7%			45%	63%	63%	54%	34%	36%	26%	45%	54%	29%	41%	54%	29%	22%	29%	38%	39%	27%	51%	36%
65.2%			65%	65%	74%	68%	67%	69%	62%	56%	88%	56%	63%	61%	45%	69%	72%	50%	60%	56%	74%	83%
67.5%		84%	72%	78%	84%	61%	61%	72%	69%	61%	61%	61%	61%	61%	61%	73%	68%	71%	58%	61%	79%	61%
66.9%		77%	71%	77%	72%	74%	56%	68%	63%	63%	71%	60%	60%	72%	64%	70%	70%	60%	63%	68%	60%	66%
75.2%		81%	79%	79%	69%	81%	49%	79%	77%	75%	85%	78%	78%	79%	66%	93%	77%	59%	69%	62%	79%	85%
61.5%		70%	64%	66%	60%	59%	48%	70%	65%	65%	59%	63%	65%	65%	59%	63%	64%	52%	57%	48%	63%	66%
67.4%		78%	65%	78%	75%	70%	62%	71%	72%	65%	77%	65%	65%	64%	65%	71%	69%	47%	49%	72%	65%	71%
65.3%			67%	67%	59%	71%	75%	65%	70%	60%	67%	64%	60%	73%	65%	67%	71%	69%	67%	64%	56%	49%
69.3%			73%	70%	74%	73%	60%	73%	68%	65%	78%	62%	67%	69%	87%	65%	78%	40%	65%	69%	69%	80%
66.8%			74%	75%	60%	55%	68%	62%	68%	66%	74%	78%	59%	75%	62%	70%	68%	65%	64%	51%	68%	74%
51.8%			48%	55%	63%	73%	38%	48%	55%	55%	63%	55%	38%	55%	41%	64%	59%	52%	30%	43%	71%	30%
67.3%			78%	78%	88%	80%	73%	78%	73%	59%	43%	64%	65%	43%	73%	43%	62%	59%	72%	78%	64%	73%
80.5%			89%	86%	74%	56%	72%	86%	84%	89%	85%	79%	76%	80%	82%	72%	84%	85%	88%	91%		71%
70.7%			72%	78%	78%	70%	59%	74%	73%	64%	78%	64%	64%	68%	73%	78%	77%	73%	64%	78%	65%	64%
68.3%			78%	75%	75%	90%	48%	57%	66%	53%	70%	75%	64%	62%	62%	75%	77%	65%	70%	72%	59%	72%
55.3%			60%	59%	57%	42%	53%	54%	50%	51%	59%	53%	50%	56%	53%	58%	63%	60%	60%	65%	52%	52%
60.2%			51%	58%	58%	62%	57%	53%	60%	55%	75%	70%	67%	44%	65%	73%	70%	51%	52%	67%	58%	57%
77.1%			86%	88%	81%	61%	66%	90%	81%	71%	66%	93%	72%	88%	72%	88%	69%	76%	67%	65%	72%	90%
53.0%		56%	52%	56%	56%	45%	70%	56%	60%	56%	38%	63%	56%	37%	45%	45%	45%	40%	40%	56%	70%	70%
64.8%			60%	63%	52%	84%	66%	60%	49%	63%	69%	79%	56%	56%	63%	72%	75%	69%	68%	48%	75%	68%
68.0%			65%	78%	70%	77%	51%	78%	72%	69%	75%	51%	72%	78%	59%	59%	50%	78%	77%	66%	76%	59%
68.6%			76%	72%	78%	77%	76%	76%	75%	63%	72%	72%	63%	72%	62%	67%	74%	50%	59%	70%	51%	67%
86.3%			80%	96%	95%	89%	76%	90%	89%	96%	96%	89%	80%	96%	79%	86%	86%	88%	83%	80%	95%	58%
55.3%			54%	64%	66%	65%	51%	60%	70%	60%	60%	45%	41%	57%	43%	59%	57%	51%	36%	48%	63%	55%
88.8%			86%	80%	93%	89%	97%	93%	96%	93%	99%	86%	86%	86%	80%	80%	74%	86%	100%	93%	86%	93%
67.7%			72%	74%	63%	62%	69%	75%	65%	74%	53%	68%	72%	67%	74%	68%	62%	73%	54%	65%	74%	69%
73.2%		75%	73%	77%	80%	79%	76%	79%	65%	75%	84%	71%	75%	75%	84%	76%	70%	67%	48%	63%	69%	77%
66.9%		74%	69%	69%	73%	75%	56%	74%	78%	69%	64%	61%	74%	63%	63%	63%	67%	67%	61%	50%	69%	66%
59.7%			59%	42%	81%	44%	52%	10%	61%	72%	78%	48%	38%	69%	35%	76%	78%	78%	77%	42%	73%	81%
59.1%		67%	57%	67%	67%	53%	56%	47%	60%	59%	56%	60%	57%	60%	47%	59%	60%	54%	65%	70%	60%	60%
65.5%			68%	65%	65%	65%	57%	74%	63%	70%	70%	63%	72%	70%	62%	80%	62%	74%	61%	63%	72%	35%
82.0%			75%	77%	77%	77%	77%	82%	87%	85%	91%	91%	78%	87%	77%	85%	91%	85%	85%	91%	84%	58%
66.9%		81%	59%	81%	81%	61%	57%	59%	66%	74%	70%	63%	60%	66%	60%	81%	73%	69%	69%	44%	60%	70%
50.2%		53%	36%	56%	53%	60%	23%	56%	63%	56%	71%	36%	36%	58%	44%	58%	64%	63%	44%	24%	66%	34%
69.7%			73%	79%	81%	79%	68%	76%	66%	65%	79%	65%	66%	76%	75%	82%	70%	52%	56%	75%	59%	51%
47.5%			49%	58%	66%	73%	31%	49%	47%	49%	65%	58%	32%	66%	35%	60%	60%	34%	22%	28%	39%	28%
61.3%			65%	75%	75%	50%	76%	66%	76%	59%	75%	65%	66%	66%	61%	46%	57%	39%	39%	75%	44%	51%
75.2%			75%	83%	83%	63%	83%	85%	73%	63%	65%	67%	74%	85%	77%	70%	65%	74%	79%	73%	75%	92%
67.1%		80%	71%	71%	81%	63%	56%	63%	72%	65%	68%	63%	65%	72%	66%	80%	66%	58%	50%	71%	60%	69%
81.7%		88%	86%	90%	88%	81%	82%	88%	88%	82%	82%	82%	69%	90%	79%	86%	81%	69%	63%	90%	74%	77%
50.4%			49%	49%	55%	51%	50%	51%	51%	50%	55%	50%	46%	54%	55%	45%	55%	51%	48%	57%	37%	50%
83.1%			89%	89%	79%	38%	87%	87%	89%	95%	89%	87%	75%	87%	87%	87%	93%	89%	82%	89%	87%	57%
73.5%		77%	73%	78%	77%	75%	72%	73%	75%	66%	73%	78%	59%	75%	61%	75%	73%	75%	70%	89%	75%	75%
61.3%		72%	70%	63%	72%	73%	32%	59%	62%	66%	60%	54%	43%	72%	41%	78%	67%	57%	66%	43%	62%	76%
69.5%			75%	73%	81%	55%	61%	74%	70%	63%	78%	79%	54%	71%	64%	75%	66%	69%	60%	65%	81%	77%
63.8%			67%	56%	56%	59%	65%	66%	63%	67%	63%	65%	65%	62%	70%	71%	69%	60%	61%	69%	64%	58%
85.4%			89%	84%	85%	86%	84%	93%	77%	90%	93%	71%	89%	93%	83%	96%	76%	83%	93%	83%	83%	77%
64.1%			66%	75%	56%	52%	72%	69%	75%	66%	72%	59%	62%	79%	79%	62%	55%	50%	51%	75%	54%	54%
69.5%			79%	64%	64%	37%	88%	84%	86%	69%	69%	64%	80%	75%	79%	56%	68%	53%	73%	77%	53%	73%
83.4%			93%	91%	71%	60%	91%	75%	91%	93%	77%	100%	93%	75%	86%	97%	85%	93%	96%	86%	40%	75%
48.7%			53%	56%	57%	34%	60%	49%	65%	55%	56%	43%	27%	61%	37%	43%	39%	40%	49%	34%	50%	66%
60.0%			60%	68%	59%	64%	60%	66%	64%	44%	71%	53%	47%	64%	60%	53%	66%	74%	52%	57%	50%	68%
79.2%			84%	90%	70%	46%	90%	90%	84%	79%	68%	86%	84%	86%	90%	68%	70%	85%	79%	92%	84%	60%
63.2%			66%	73%	73%	35%	72%	66%	65%	66%	73%	66%	66%	66%	66%	66%	69%	50%	64%	65%	48%	48%
56.6%		63%	53%	54%	65%	63%	46%	60%	53%	59%	59%	59%	53%	53%	60%	60%	57%	43%	57%	59%	53%	60%
73.5%			84%	84%	77%	37%	78%	78%	81%	73%	76%	70%	70%	90%	80%	74%	72%	73%	65%	85%	70%	53%
77.8%			89%	89%	85%	89%	89%	73%	79%	79%	89%	77%	63%	75%	89%	79%	78%	59%	66%	79%	72%	58%
72.8%		82%	72%	82%	82%	90%	82%	75%	72%	67%	79%	59%	59%	72%	72%	75%	66%	72%	50%	75%	68%	78%
60.7%		61%	64%	73%	77%	54%	69%	55%	51%	61%	61%	75%	38%	69%	75%	49%	57%	49%	62%	71%	42%	61%
59.9%		65%	64%	65%	65%	41%	66%	68%	63%	53%	65%	63%	66%	61%	65%	58%	62%	52%	52%	53%	54%	57%
80.0%			80%	78%	80%	69%	85%	72%	80%	87%	80%	84%	87%	78%	87%	80%	80%	83%	82%	80%	76%	71%
70.6%			69%	76%	71%	70%	68%	69%	76%	69%	70%	76%	70%	76%	76%	76%	75%	70%	68%	70%	70%	47%
47.2%			54%	54%	54%	27%	48%	47%	53%	44%	44%	48%	43%	49%	54%	47%	47%	48%	43%	54%	52%	35%
44.7%			53%	54%	54%	43%	55%	53%	48%	43%	43%	48%	32%	38%	40%	36%	43%	23%	27%	57%	54%	49%
56.0%		59%	64%	69%	69%	65%	58%	55%	59%	51%	67%	65%	50%	59%	56%	41%	50%	50%	42%	59%	50%	38%
54.3%			55%	65%	65%	67%	53%	55%	63%	65%	60%	54%	23%	54%	49%	60%	58%	58%	21%	65%	36%	60%
81.0%			94%	100%	75%	79%	75%	93%	89%	85%	89%	86%	60%	89%	80%	75%	72%	75%	68%	81%	81%	75%
84.3%			87%	76%	87%	63%	79%	87%	87%	91%	87%	87%	91%	91%	89%	87%	91%	74%	94%	79%	78%	80%
53.9%			58%	76%	76%	77%	21%	43%	46%	52%	46%	79%	32%	37%	30%	62%	65%	32%	65%	43%	62%	76%
68.1%		80%	65%	66%	66%	39%	78%	65%	68%	65%	65%	65%	74%	74%	88%	75%	70%	66%	50%	55%	82%	74%
67.1%		70%	70%	80%	77%	72%	57%	70%	70%	70%	71%	70%	70%	70%	62%	71%	71%	65%	57%	52%	58%	57%
40.0%			53%	45%	45%	16%	55%	53%	45%	39%	40%	40%	40%	40%	43%	35%	40%	34%	39%	48%	24%	25%
65.1%			67%	71%	70%	72%	73%	72%	74%	61%	74%	70%	65%	61%	69%	61%	55%	47%	57%	67%	65%	50%
66.0%		69%	63%	75%	73%	34%	78%	69%	69%	59%	63%	69%	69%	72%	67%	68%	69%	59%	65%	73%	69%	55%
74.7%			81%	81%	61%	59%	83%	81%	81%	81%	64%	63%	81%	81%	79%	62%	81%	64%	95%	90%	61%	65%
64.3%			70%	72%	70%	51%	35%	67%	59%	70%	70%	72%	63%	72%	59%	71%	73%	60%	77%	57%		53%
51.0%			54%	57%	57%	64%	45%	45%	57%	39%	53%	54%	34%	53%	47%	40%	53%	54%	38%	44%	65%	66%
54.6%			57%	59%	64%	29%	54%	56%	55%	58%	60%	52%	53%	56%	40%	71%	66%	54%	55%	46%	48%	59%
72.2%		72%	68%	66%	65%	77%	65%	68%	67%	68%	64%	79%	77%	68%	77%	75%	77%	84%	77%	67%	78%	77%
57.3%		71%	62%	62%	62%	62%	56%	62%	61%	58%	43%	62%	56%	42%	56%	62%	71%	42%	48%	65%	55%	46%
60.4%		69%	60%	52%	54%	58%	55%	58%	60%	60%	60%	62%	62%	62%	62%	69%	62%	66%	60%	62%	55%	61%
62.5%		58%	65%	62%	67%	28%	68%	66%	58%	65%	71%	68%	53%	65%	68%	65%	68%	59%	57%	66%	68%	68%
75.6%			85%	72%	72%	73%	60%	85%	66%	73%	80%	85%	85%	89%	73%	82%	86%	67%	56%	66%	85%	72%
80.7%			87%	78%	94%	76%	54%	72%	74%	87%	94%	100%	52%	94%	75%	100%	87%	77%	83%	81%	87%	61%
61.4%			52%	58%	79%	80%	34%	58%	58%	60%	83%	71%	60%	83%	58%	83%	73%	48%	27%	48%	66%	48%
60.5%		46%	72%	53%	53%	57%	77%	60%	59%	59%	59%	49%	86%	62%	62%	51%	66%	70%	49%	74%	57%	49%
79.8%			69%	91%	91%	74%	73%	69%	79%	77%	86%	86%	69%	93%	70%	100%	77%	93%	76%	55%	78%	91%
68.7%			66%	75%	73%	65%	72%	70%	75%	69%	79%	69%	66%	75%	75%	70%	66%	60%	68%	75%	52%	54%
58.3%			56%	58%	62%	62%	50%	57%	55%	62%	55%	58%	55%	62%	55%	62%	57%	62%	60%	55%	62%	62%
58.3%		60%	49%	58%	58%	72%	49%	63%	50%	55%	67%	58%	61%	61%	61%	70%	70%	49%	53%	39%	61%	61%
68.5%			78%	78%	74%	26%	74%	78%	75%	65%	68%	78%	67%	78%	74%	59%	68%	73%	69%	72%	65%	52%
69.8%			65%	70%	79%	85%	67%	75%	54%	70%	79%	65%	62%	70%	70%	79%	75%	67%	70%	55%	63%	75%
65.6%			70%	68%	71%	76%	76%	71%	71%	57%	71%	59%	61%	71%	68%	47%	65%	52%	59%	70%	52%	78%

Model Similarity Dendrogram

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