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%3Agermany Ctx - Run b15471d...

Global Dialogues GD4 - Germany (with context)

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

Social interaction

AI Safety & Robustness

Best Models (Coverage)

1.Claude Sonnet 4.5
73.5%
2.Claude Sonnet 4
72.5%
3.GPT 4.1
71.3%
4.Gemini 2.5 Flash
70.6%
5.Claude Haiku 4.5
70.1%

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		5th 70.1%	2nd 72.5%	1st 73.5%	4th 70.6%	12th 62.3%	7th 69.1%	6th 69.2%	3rd 71.3%	8th 68.8%	13th 61.7%	10th 64.1%	11th 63.4%	9th 67.4%
54.7%		49%	60%	75%	74%	43%	49%	60%	58%	56%	21%	56%	57%	53%
54.5%		64%	71%	66%	66%	36%	64%	56%	66%	66%	35%	35%	35%	48%
85.5%		88%	91%	91%	84%	88%	81%	89%	93%	86%	85%	63%	86%	86%
67.8%		71%	71%	70%	57%	65%	68%	63%	76%	67%	70%	78%	74%	51%
66.4%		78%	71%	69%	34%	53%	80%	60%	62%	72%	63%	72%	78%	71%
70.8%		72%	73%	75%	75%	72%	67%	67%	69%	71%	79%	67%	67%	67%
68.5%		81%	81%	81%	46%	62%	68%	75%	57%	49%	49%	67%	87%	87%
64.2%		64%	59%	75%	68%	63%	59%	69%	63%	67%	71%	59%	56%	62%
56.8%		77%	59%	63%	44%	63%	58%	43%	54%	43%	44%	60%	59%	72%
50.1%		72%	58%	58%	28%	78%	50%	28%	34%	46%	34%	33%	59%	73%
74.8%		67%	74%	77%	73%	82%	84%	79%	83%	77%	63%	79%	71%	63%
80.9%		69%	69%	81%	90%	78%	90%	79%	90%	90%	56%	81%	89%	90%
73.2%		73%	73%	73%	73%	73%	75%	73%	73%	73%	73%	73%	73%	73%
70.2%		80%	93%	80%	74%	68%	68%	61%	45%	76%	73%	61%	73%	60%
55.2%		62%	64%	72%	48%	53%	63%	62%	51%	59%	53%	36%	35%	59%
51.8%		46%	64%	69%	63%	21%	54%	46%	74%	63%	29%	56%	27%	61%
49.8%		45%	37%	46%	66%	56%	51%	48%	51%	43%	66%	41%	46%	51%
59.5%		61%	57%	65%	50%	56%	63%	63%	59%	63%	61%	60%	56%	60%
71.2%		68%	74%	75%	81%	64%	75%	63%	74%	75%	62%	72%	71%	72%
63.0%		81%	63%	63%	35%	52%	65%	71%	54%	81%	39%	65%	69%	81%
71.2%		76%	65%	76%	60%	91%	71%	85%	68%	60%	76%	78%	60%	60%
77.5%		75%	91%	72%	75%	79%	71%	75%	86%	75%	77%	72%	85%	75%
76.5%		86%	77%	77%	80%	73%	79%	67%	67%	72%	75%	86%	77%	79%
51.8%		63%	64%	72%	79%	36%	63%	45%	61%	60%	24%	36%	24%	47%
60.8%		50%	62%	73%	69%	62%	72%	62%	68%	60%	58%	52%	43%	60%
61.7%		56%	78%	75%	61%	54%	56%	61%	56%	61%	61%	61%	61%	61%
63.3%		56%	62%	72%	74%	57%	58%	70%	65%	60%	60%	65%	64%	60%
59.8%		42%	63%	69%	72%	48%	56%	66%	64%	55%	64%	53%	53%	72%
59.7%		67%	75%	71%	78%	45%	61%	57%	75%	71%	47%	48%	41%	40%
74.0%		70%	69%	70%	78%	65%	69%	66%	90%	91%	40%	91%	72%	91%
67.8%		58%	70%	70%	65%	72%	68%	73%	75%	68%	75%	58%	56%	74%
80.0%		76%	80%	81%	84%	85%	79%	81%	81%	81%	74%	74%	83%	81%
66.4%		78%	75%	70%	75%	49%	65%	75%	73%	78%	73%	36%	59%	57%
60.3%		63%	68%	71%	71%	38%	58%	63%	72%	69%	56%	71%	20%	64%
80.0%		88%	78%	72%	75%	91%	77%	88%	80%	72%	80%	79%	79%	81%
79.4%		79%	82%	82%	87%	84%	71%	87%	82%	65%	65%	79%	82%	87%
76.0%		88%	73%	74%	80%	73%	69%	80%	82%	56%	55%	79%	79%	100%
95.4%		100%	100%	100%	100%	90%	90%	100%	100%	100%	90%	90%	90%	90%
58.8%		57%	62%	57%	56%	57%	57%	63%	51%	56%	58%	71%	61%	58%
89.0%		90%	90%	77%	90%	90%	90%	90%	90%	90%	90%	90%	90%	90%
67.1%		73%	78%	66%	63%	54%	85%	73%	63%	78%	58%	68%	29%	84%
54.4%		70%	76%	63%	45%	31%	67%	45%	40%	56%	61%	63%	51%	39%
64.0%		76%	61%	81%	68%	43%	68%	72%	68%	69%	68%	30%	76%	52%
72.7%		78%	82%	86%	79%	65%	91%	75%	79%	54%	75%	72%	60%	49%
66.8%		91%	89%	84%	88%	72%	86%	63%	81%	35%	35%	35%	35%	75%
72.6%		68%	74%	74%	73%	67%	71%	76%	77%	72%	61%	73%	78%	80%
58.1%		54%	66%	71%	72%	54%	61%	63%	72%	56%	41%	51%	48%	46%
84.4%		93%	100%	93%	89%	10%	93%	89%	90%	89%	80%	99%	92%	80%
75.6%		72%	73%	75%	82%	69%	85%	82%	65%	82%	65%	82%	69%	82%
81.0%		81%	93%	93%	81%	78%	93%	84%	88%	81%	81%	52%	78%	70%
69.8%		78%	64%	71%	72%	66%	64%	72%	71%	72%	72%	64%	69%	72%
56.3%		38%	64%	70%	79%	42%	53%	58%	75%	67%	59%	34%	39%	54%
60.5%		60%	66%	67%	69%	43%	58%	58%	55%	60%	60%	60%	71%	60%
70.8%		74%	71%	76%	80%	59%	67%	71%	91%	92%	64%	65%	50%	60%
79.1%		79%	79%	79%	79%	79%	80%	79%	79%	79%	79%	79%	79%	79%
62.7%		65%	70%	87%	87%	50%	51%	65%	63%	47%	91%	50%	37%	52%
53.7%		56%	53%	53%	60%	37%	76%	58%	81%	43%	21%	56%	56%	48%
73.4%		73%	73%	73%	73%	73%	77%	73%	74%	73%	73%	73%	73%	73%
59.6%		64%	64%	68%	80%	26%	70%	64%	74%	68%	47%	58%	14%	78%
82.7%		75%	72%	86%	91%	76%	95%	77%	100%	79%	74%	88%	74%	88%
70.9%		80%	87%	87%	63%	70%	75%	63%	67%	67%	68%	75%	66%	54%
66.3%		57%	81%	71%	71%	66%	63%	64%	66%	63%	59%	63%	78%	60%
81.6%		81%	81%	77%	81%	92%	82%	81%	81%	81%	81%	81%	81%	81%
57.9%		57%	56%	58%	45%	59%	59%	63%	63%	62%	54%	65%	61%	51%
83.5%		76%	84%	84%	77%	90%	79%	87%	84%	84%	82%	76%	95%	87%
66.5%		76%	72%	76%	81%	36%	93%	80%	89%	72%	34%	36%	47%	72%
40.9%		55%	58%	51%	44%	22%	39%	47%	45%	53%	26%	34%	27%	31%
72.2%		75%	82%	89%	89%	64%	69%	51%	77%	77%	54%	61%	69%	81%
63.2%		70%	62%	65%	56%	71%	62%	62%	58%	63%	47%	75%	59%	72%
84.8%		80%	84%	91%	57%	90%	93%	90%	84%	77%	84%	86%	90%	96%
82.2%		84%	84%	89%	84%	79%	61%	84%	84%	84%	84%	84%	84%	84%
65.2%		80%	64%	72%	43%	81%	75%	37%	65%	41%	74%	62%	77%	77%
78.4%		72%	86%	86%	91%	72%	78%	91%	71%	78%	72%	66%	78%	78%
50.2%		53%	60%	47%	65%	29%	67%	55%	50%	55%	44%	50%	35%	43%
70.7%		81%	89%	82%	67%	67%	63%	79%	69%	63%	54%	75%	56%	74%
83.3%		76%	84%	84%	89%	78%	84%	86%	82%	84%	84%	84%	84%	84%
75.4%		79%	90%	85%	81%	71%	66%	66%	85%	66%	66%	73%	75%	77%
57.0%		53%	60%	60%	70%	49%	60%	59%	63%	59%	21%	65%	59%	63%
77.2%		78%	76%	71%	81%	88%	71%	84%	80%	67%	70%	92%	71%	74%
79.0%		79%	79%	79%	79%	79%	79%	79%	79%	79%	79%	79%	79%	79%
78.1%		81%	88%	72%	81%	81%	69%	82%	56%	81%	81%	81%	81%	81%
76.8%		77%	66%	90%	93%	62%	78%	72%	87%	90%	62%	63%	69%	90%
60.0%		66%	69%	65%	41%	47%	73%	65%	70%	78%	59%	37%	49%	61%
79.3%		82%	82%	82%	82%	85%	72%	88%	85%	65%	81%	81%	81%	65%
73.9%		76%	85%	74%	76%	70%	74%	70%	76%	70%	77%	74%	63%	76%
59.4%		62%	63%	63%	54%	50%	54%	59%	63%	59%	49%	62%	70%	64%
70.1%		78%	69%	63%	68%	61%	70%	62%	68%	76%	65%	77%	77%	77%
64.1%		72%	69%	69%	62%	58%	69%	61%	64%	68%	53%	57%	64%	67%
69.7%		68%	65%	80%	62%	39%	77%	71%	71%	63%	93%	77%	77%	63%
79.5%		71%	75%	75%	81%	64%	93%	85%	100%	78%	94%	78%	70%	69%
67.7%		61%	76%	80%	74%	71%	76%	76%	61%	78%	73%	43%	60%	51%
59.2%		76%	91%	72%	73%	38%	41%	71%	57%	54%	63%	58%	33%	43%
63.5%		65%	67%	68%	39%	66%	50%	70%	62%	68%	28%	88%	79%	75%
55.4%		51%	62%	61%	62%	57%	53%	57%	61%	46%	58%	46%	53%	53%
48.0%		55%	60%	79%	25%	46%	47%	41%	46%	46%	35%	44%	55%	45%
77.3%		58%	84%	77%	90%	84%	79%	79%	80%	79%	38%	75%	91%	91%
74.3%		81%	75%	69%	73%	80%	81%	70%	83%	65%	63%	74%	78%	74%
74.5%		76%	72%	77%	81%	76%	61%	81%	75%	75%	75%	70%	75%	75%
64.8%		66%	77%	76%	75%	43%	70%	71%	68%	72%	69%	40%	57%	59%
60.7%		65%	61%	70%	78%	46%	57%	59%	63%	66%	48%	59%	60%	57%
52.6%		54%	66%	50%	45%	44%	59%	59%	63%	57%	47%	45%	47%	48%
65.5%		72%	53%	56%	68%	57%	64%	68%	72%	71%	57%	71%	71%	71%
57.6%		64%	62%	71%	65%	52%	70%	42%	43%	56%	56%	56%	56%	56%
57.9%		56%	49%	60%	67%	55%	58%	58%	60%	64%	60%	50%	58%	58%
67.6%		68%	66%	66%	70%	71%	66%	73%	71%	68%	59%	73%	68%	60%
69.4%		85%	71%	73%	73%	65%	66%	75%	69%	81%	69%	53%	57%	65%
61.8%		87%	67%	67%	76%	44%	52%	80%	87%	94%	43%	21%	43%	43%
61.7%		56%	83%	88%	78%	43%	65%	73%	80%	49%	57%	44%	48%	38%
60.5%		52%	52%	55%	61%	72%	57%	72%	60%	60%	49%	74%	62%	61%
70.7%		63%	86%	93%	78%	53%	63%	77%	88%	86%	90%	37%	45%	60%
75.6%		75%	88%	75%	88%	80%	73%	73%	83%	76%	77%	48%	71%	76%
59.2%		62%	62%	64%	64%	56%	50%	57%	62%	66%	58%	57%	49%	62%
53.9%		44%	55%	55%	61%	52%	55%	55%	79%	61%	29%	61%	56%	38%
72.1%		74%	71%	74%	81%	75%	63%	74%	74%	75%	67%	71%	71%	67%
91.1%		100%	100%	100%	98%	81%	100%	100%	100%	100%	79%	90%	36%	100%
83.5%		84%	89%	90%	84%	88%	84%	84%	84%	84%	71%	84%	84%	75%