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%3Apoland C10 - Run c7b2b69...

Global Dialogues GD4 - Poland (10 context Qs)

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

TAGS:

Global Dialogues Gd4

Factual Accuracy & Hallucination

Instruction Following & Prompt Adherence

Social interaction

AI Safety & Robustness

Best Models (Coverage)

1.Claude Sonnet 4.5
66.7%
2.GPT 4.1
66.2%
3.Claude Sonnet 4
65.6%
4.Claude Haiku 4.5
64.7%
5.GPT 4.1 Mini
64.5%

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		4th 64.7%	3rd 65.6%	1st 66.7%	13th 57.1%	9th 60.9%	6th 64.5%	7th 62.9%	2nd 66.2%	5th 64.5%	11th 59.7%	8th 61.1%	10th 60.6%	12th 59.4%
64.8%		68%	74%	80%	54%	54%	60%	71%	72%	68%	72%	43%	60%	66%
46.4%		39%	47%	51%	72%	25%	39%	47%	68%	47%	43%	43%	39%	43%
55.9%		54%	61%	58%	74%	51%	53%	67%	51%	58%	54%	44%	54%	48%
56.1%		57%	54%	62%	49%	61%	62%	52%	55%	52%	56%	51%	56%	62%
31.5%		33%	30%	26%	22%	37%	30%	30%	30%	30%	30%	37%	37%	37%
77.8%		77%	84%	82%	47%	80%	84%	88%	82%	82%	86%	86%	86%	48%
58.2%		55%	59%	59%	66%	58%	70%	48%	59%	59%	57%	43%	58%	66%
71.2%		67%	57%	57%	65%	88%	75%	73%	72%	84%	72%	72%	72%	72%
75.5%		78%	86%	86%	37%	65%	89%	82%	71%	49%	86%	81%	86%	86%
67.5%		72%	72%	67%	66%	75%	69%	70%	66%	74%	75%	58%	63%	51%
84.2%		82%	89%	88%	89%	86%	79%	79%	89%	89%	87%	75%	89%	73%
80.8%		86%	87%	87%	87%	82%	78%	87%	81%	82%	51%	77%	80%	86%
73.8%		76%	74%	75%	77%	68%	72%	66%	77%	77%	77%	70%	74%	77%
49.3%		61%	57%	60%	49%	44%	55%	49%	40%	58%	54%	44%	10%	60%
59.8%		56%	62%	72%	22%	56%	54%	65%	80%	69%	63%	54%	56%	68%
52.0%		57%	53%	57%	68%	48%	56%	58%	63%	52%	41%	41%	41%	41%
84.8%		84%	76%	78%	82%	90%	90%	100%	78%	84%	78%	88%	85%	90%
45.4%		44%	48%	48%	48%	42%	48%	48%	40%	46%	48%	48%	46%	36%
72.8%		69%	70%	80%	70%	79%	54%	53%	73%	87%	77%	77%	81%	77%
46.7%		51%	44%	51%	0%	37%	56%	40%	44%	61%	58%	63%	58%	44%
68.6%		71%	81%	79%	68%	68%	78%	68%	71%	70%	55%	55%	57%	71%
64.4%		74%	74%	61%	18%	66%	73%	64%	58%	74%	64%	77%	66%	68%
65.9%		56%	64%	61%	69%	67%	72%	69%	61%	70%	75%	68%	68%	57%
44.5%		38%	55%	55%	88%	40%	42%	44%	49%	34%	31%	31%	31%	40%
55.3%		59%	54%	56%	45%	67%	61%	50%	53%	50%	57%	51%	53%	63%
65.8%		73%	61%	61%	68%	65%	63%	57%	68%	68%	68%	68%	68%	68%
51.5%		59%	53%	53%	58%	41%	58%	52%	53%	48%	38%	38%	59%	59%
64.4%		67%	63%	66%	63%	56%	72%	71%	66%	61%	77%	56%	60%	59%
44.6%		48%	41%	44%	62%	41%	51%	48%	44%	51%	51%	33%	33%	33%
58.0%		54%	55%	51%	36%	65%	64%	55%	66%	66%	58%	62%	64%	58%
80.5%		77%	86%	88%	88%	79%	86%	86%	89%	79%	66%	86%	88%	48%
53.2%		55%	49%	49%	37%	63%	58%	49%	46%	66%	62%	52%	62%	44%
60.0%		63%	61%	70%	75%	60%	55%	64%	61%	67%	53%	53%	49%	49%
52.3%		57%	53%	57%	57%	48%	51%	67%	63%	57%	41%	51%	41%	37%
78.3%		87%	80%	84%	47%	77%	86%	86%	60%	73%	84%	90%	80%	84%
67.5%		69%	69%	81%	81%	63%	69%	72%	81%	65%	47%	65%	81%	34%
63.5%		57%	68%	71%	55%	47%	73%	57%	82%	48%	62%	70%	64%	72%
68.1%		65%	77%	73%	61%	62%	61%	49%	73%	74%	66%	63%	77%	84%
61.6%		66%	68%	66%	66%	64%	68%	57%	66%	66%	63%	61%	50%	40%
55.0%		49%	52%	52%	50%	55%	54%	42%	52%	68%	69%	66%	44%	62%
69.8%		74%	68%	48%	48%	84%	78%	74%	49%	49%	93%	74%	86%	82%
34.9%		41%	37%	37%	0%	51%	37%	30%	30%	37%	37%	22%	51%	44%
63.0%		72%	57%	57%	57%	65%	63%	73%	69%	68%	62%	62%	57%	57%
64.7%		58%	68%	69%	66%	52%	63%	63%	81%	62%	65%	72%	66%	56%
63.8%		60%	53%	63%	53%	60%	54%	73%	68%	68%	72%	65%	72%	69%
73.5%		82%	81%	81%	74%	42%	73%	71%	77%	83%	66%	73%	73%	80%
52.5%		62%	56%	63%	66%	40%	54%	56%	62%	47%	37%	47%	52%	41%
95.2%		100%	100%	100%	88%	85%	100%	88%	100%	95%	100%	94%	100%	88%
50.5%		52%	67%	52%	13%	51%	68%	57%	44%	51%	57%	42%	42%	60%
46.1%		51%	51%	51%	44%	51%	44%	44%	51%	47%	44%	47%	37%	37%
56.5%		60%	65%	63%	57%	56%	62%	63%	53%	49%	62%	56%	42%	46%
49.8%		43%	37%	56%	30%	59%	53%	56%	50%	61%	46%	49%	38%	70%
49.4%		46%	51%	51%	45%	59%	63%	41%	58%	51%	44%	53%	38%	42%
55.2%		55%	48%	62%	69%	48%	48%	55%	71%	68%	48%	49%	48%	48%
55.4%		55%	55%	55%	55%	62%	61%	54%	54%	59%	56%	55%	50%	49%
52.2%		55%	61%	70%	63%	42%	50%	61%	61%	50%	38%	38%	52%	38%
54.6%		55%	63%	49%	51%	41%	51%	59%	88%	48%	40%	75%	40%	50%
58.2%		59%	63%	58%	57%	58%	51%	55%	70%	58%	58%	53%	58%	58%
71.5%		77%	73%	79%	71%	67%	77%	73%	71%	72%	62%	77%	64%	66%
42.8%		40%	48%	48%	0%	57%	48%	33%	42%	52%	48%	48%	48%	45%
58.3%		67%	66%	71%	74%	57%	61%	68%	68%	68%	46%	46%	66%	0%
64.3%		65%	70%	76%	89%	47%	65%	58%	63%	62%	67%	47%	70%	57%
65.5%		62%	66%	67%	77%	70%	75%	67%	75%	63%	50%	61%	51%	67%
48.7%		45%	50%	57%	37%	57%	46%	48%	54%	48%	52%	44%	57%	38%
71.2%		72%	87%	71%	29%	77%	87%	87%	70%	74%	77%	71%	69%	54%
60.9%		60%	66%	63%	54%	69%	62%	59%	55%	63%	53%	63%	57%	68%
50.7%		60%	47%	47%	77%	40%	56%	67%	51%	49%	49%	34%	34%	48%
56.3%		65%	58%	60%	54%	58%	48%	54%	63%	63%	40%	49%	51%	69%
65.1%		66%	68%	65%	61%	62%	71%	61%	68%	70%	61%	65%	63%	65%
78.8%		86%	81%	78%	78%	86%	78%	88%	68%	72%	74%	81%	74%	81%
63.5%		65%	67%	67%	29%	74%	67%	60%	72%	67%	65%	59%	67%	67%
67.8%		76%	70%	79%	30%	71%	72%	72%	58%	73%	73%	73%	74%	61%
73.8%		74%	76%	78%	58%	79%	71%	74%	89%	74%	74%	76%	74%	63%
55.9%		63%	67%	74%	0%	48%	79%	66%	72%	53%	44%	53%	46%	62%
64.4%		72%	75%	72%	26%	66%	71%	57%	65%	66%	62%	71%	66%	68%
73.5%		74%	76%	77%	48%	78%	80%	68%	88%	77%	68%	74%	74%	74%
75.5%		81%	80%	80%	37%	85%	75%	79%	80%	80%	65%	85%	75%	79%
65.2%		59%	66%	73%	70%	58%	74%	54%	81%	68%	50%	66%	68%	60%
53.8%		58%	57%	57%	60%	57%	49%	54%	57%	57%	56%	45%	56%	37%
53.9%		55%	55%	55%	56%	62%	54%	54%	50%	61%	56%	55%	44%	44%
75.4%		72%	80%	75%	81%	68%	80%	87%	75%	72%	70%	70%	80%	70%
82.0%		86%	89%	79%	89%	79%	77%	74%	77%	89%	66%	89%	89%	83%
75.1%		83%	83%	88%	61%	78%	77%	66%	86%	78%	73%	70%	64%	69%
64.3%		71%	73%	73%	58%	58%	67%	62%	67%	67%	62%	62%	49%	67%
42.1%		33%	44%	42%	44%	51%	44%	44%	44%	44%	40%	48%	36%	33%
63.9%		74%	73%	73%	40%	73%	65%	61%	67%	65%	66%	61%	59%	54%
54.5%		58%	53%	62%	56%	54%	53%	53%	53%	53%	40%	60%	57%	56%
66.8%		70%	61%	62%	61%	75%	65%	62%	65%	71%	60%	75%	71%	71%
56.9%		61%	74%	74%	74%	35%	55%	55%	64%	50%	24%	43%	61%	70%
73.9%		83%	74%	74%	100%	77%	77%	67%	77%	74%	51%	66%	74%	67%
44.9%		44%	36%	45%	77%	36%	47%	51%	36%	36%	44%	44%	44%	44%
50.7%		68%	72%	72%	76%	16%	48%	46%	65%	69%	38%	38%	38%	13%
75.0%		74%	84%	84%	51%	67%	80%	84%	88%	84%	65%	84%	65%	65%
72.7%		80%	79%	79%	58%	69%	73%	63%	82%	77%	75%	72%	72%	66%
54.3%		60%	55%	55%	34%	60%	66%	51%	55%	44%	50%	62%	54%	60%
65.7%		62%	62%	62%	66%	76%	62%	77%	51%	73%	73%	73%	73%	44%
58.8%		58%	65%	72%	32%	60%	54%	49%	67%	61%	66%	61%	66%	53%
77.0%		80%	82%	82%	69%	74%	79%	72%	91%	82%	72%	73%	72%	73%
70.8%		78%	78%	84%	54%	50%	77%	73%	66%	74%	64%	76%	73%	73%
76.7%		90%	82%	85%	67%	74%	85%	79%	74%	67%	79%	80%	63%	72%
56.6%		55%	68%	74%	30%	55%	53%	57%	75%	55%	58%	61%	40%	55%
80.5%		83%	79%	86%	58%	75%	84%	88%	86%	87%	73%	88%	80%	79%
67.1%		77%	70%	70%	63%	69%	61%	70%	61%	67%	73%	44%	74%	73%
72.0%		72%	71%	73%	73%	61%	64%	81%	82%	73%	76%	72%	71%	67%
77.9%		87%	89%	89%	68%	71%	74%	72%	89%	79%	72%	80%	68%	75%
75.5%		77%	79%	86%	73%	60%	87%	72%	78%	87%	87%	55%	55%	86%
56.4%		82%	46%	67%	60%	31%	49%	65%	88%	60%	42%	45%	38%	60%
47.2%		39%	51%	53%	72%	27%	39%	53%	62%	46%	39%	51%	39%	43%
63.6%		56%	58%	72%	73%	56%	67%	72%	62%	57%	58%	63%	67%	66%
57.4%		62%	66%	66%	62%	60%	51%	58%	65%	58%	50%	50%	49%	49%
60.3%		60%	63%	49%	63%	74%	63%	54%	62%	66%	59%	59%	63%	49%
71.0%		63%	73%	63%	63%	75%	76%	61%	87%	75%	55%	74%	79%	79%
75.7%		72%	88%	73%	34%	68%	81%	81%	81%	100%	68%	73%	88%	77%
59.0%		65%	65%	65%	44%	59%	57%	54%	60%	65%	59%	59%	65%	50%
72.2%		74%	74%	81%	90%	71%	74%	74%	81%	68%	51%	74%	59%	67%
66.0%		69%	71%	63%	63%	73%	68%	56%	65%	68%	62%	74%	63%	63%