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%3Aphilippines C5 - Run 8b8a5a7...

Global Dialogues GD4 - Philippines (5 context Qs)

DTEF: Predict response distributions for Philippines. 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
68.8%
2.Llama 4 Maverick
67.9%
3.Claude Haiku 4.5
67.3%
4.GPT 4.1 Mini
66.0%
5.GPT 4o Mini
65.5%

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		3rd 67.3%	1st 68.8%	8th 63.7%	13th 51.9%	11th 62.1%	2nd 67.9%	6th 65.2%	9th 63.1%	4th 66.0%	12th 56.0%	5th 65.5%	10th 63.1%	7th 65.2%
46.8%		57%	68%	65%	0%	38%	43%	49%	59%	43%	53%	54%	29%	51%
49.5%		50%	51%	51%	48%	41%	41%	58%	61%	44%	53%	49%	48%	48%
77.6%		82%	80%	83%	56%	73%	80%	83%	81%	83%	81%	80%	71%	76%
62.3%		65%	73%	63%	39%	68%	70%	57%	68%	66%	45%	59%	67%	70%
65.0%		69%	69%	58%	58%	54%	62%	69%	51%	61%	75%	60%	83%	76%
72.5%		85%	81%	80%	20%	84%	84%	81%	60%	80%	76%	80%	84%	48%
70.1%		83%	72%	83%	81%	63%	72%	67%	61%	67%	67%	69%	59%	67%
72.0%		80%	83%	83%	52%	76%	78%	78%	68%	62%	40%	78%	80%	78%
72.7%		82%	68%	68%	60%	66%	77%	78%	70%	72%	76%	84%	77%	67%
70.8%		72%	80%	80%	78%	75%	66%	68%	65%	78%	78%	78%	70%	33%
57.0%		71%	65%	44%	28%	60%	59%	57%	46%	62%	59%	49%	66%	75%
69.9%		76%	74%	72%	68%	77%	76%	72%	80%	80%	30%	72%	66%	66%
77.0%		84%	88%	70%	50%	85%	84%	73%	70%	84%	55%	84%	87%	87%
59.2%		74%	74%	64%	35%	44%	71%	67%	60%	61%	41%	56%	49%	73%
62.4%		67%	75%	61%	34%	70%	68%	48%	56%	74%	52%	76%	59%	71%
57.8%		60%	55%	64%	63%	49%	60%	66%	69%	53%	51%	58%	53%	51%
84.2%		86%	82%	93%	93%	83%	91%	77%	83%	89%	67%	83%	77%	91%
43.3%		63%	48%	41%	15%	44%	44%	41%	29%	48%	41%	42%	59%	48%
66.4%		74%	63%	54%	62%	82%	61%	62%	42%	78%	60%	77%	73%	75%
48.8%		51%	46%	48%	46%	39%	52%	49%	52%	48%	58%	47%	52%	46%
36.1%		41%	47%	28%	18%	38%	43%	42%	28%	42%	42%	37%	16%	47%
65.4%		73%	69%	55%	25%	63%	71%	74%	67%	66%	77%	77%	63%	70%
65.2%		74%	88%	89%	40%	77%	79%	85%	70%	56%	54%	56%	47%	33%
37.4%		46%	46%	29%	40%	34%	38%	46%	39%	37%	28%	38%	26%	39%
55.5%		56%	55%	55%	58%	52%	60%	60%	60%	55%	49%	52%	54%	55%
72.5%		68%	68%	73%	79%	68%	74%	68%	77%	74%	79%	65%	69%	81%
65.0%		78%	72%	61%	41%	59%	72%	55%	44%	70%	75%	67%	75%	76%
63.2%		72%	74%	62%	56%	59%	72%	57%	75%	67%	37%	62%	63%	66%
62.6%		63%	74%	73%	59%	59%	68%	62%	74%	57%	63%	53%	48%	61%
69.5%		82%	88%	82%	65%	47%	78%	74%	90%	55%	52%	73%	42%	76%
55.9%		65%	62%	58%	28%	63%	62%	58%	46%	62%	63%	46%	57%	57%
72.2%		59%	92%	92%	17%	55%	82%	79%	92%	85%	79%	74%	63%	70%
76.1%		77%	80%	81%	56%	74%	80%	78%	84%	76%	92%	72%	84%	55%
54.4%		55%	54%	59%	67%	48%	55%	62%	66%	45%	47%	53%	48%	48%
62.5%		63%	63%	65%	73%	63%	66%	59%	52%	61%	63%	65%	60%	59%
68.7%		80%	74%	74%	36%	78%	77%	80%	55%	69%	69%	74%	72%	55%
59.7%		60%	67%	66%	58%	48%	72%	72%	45%	70%	31%	67%	59%	61%
59.1%		45%	52%	49%	61%	63%	53%	57%	64%	54%	62%	65%	78%	65%
62.2%		70%	69%	70%	50%	66%	66%	68%	58%	56%	59%	64%	60%	52%
35.8%		29%	33%	42%	32%	39%	34%	32%	32%	37%	37%	54%	39%	26%
78.1%		84%	90%	80%	59%	59%	90%	84%	79%	85%	55%	78%	80%	92%
73.2%		71%	77%	80%	33%	80%	80%	73%	52%	89%	67%	67%	88%	94%
70.4%		73%	74%	69%	67%	73%	70%	80%	65%	70%	48%	74%	76%	76%
48.2%		43%	42%	34%	52%	51%	64%	52%	44%	37%	63%	57%	45%	42%
73.6%		84%	77%	71%	51%	83%	84%	70%	71%	87%	47%	71%	81%	80%
81.6%		69%	84%	91%	80%	70%	90%	87%	91%	89%	65%	78%	91%	76%
52.2%		50%	51%	52%	39%	57%	61%	52%	37%	54%	65%	50%	62%	48%
77.3%		74%	97%	81%	74%	71%	74%	74%	98%	74%	81%	81%	67%	59%
67.2%		70%	75%	58%	15%	69%	87%	77%	73%	78%	48%	84%	66%	74%
66.5%		76%	71%	66%	69%	81%	66%	73%	71%	69%	23%	65%	65%	69%
70.4%		80%	64%	64%	74%	84%	70%	70%	83%	78%	40%	70%	67%	71%
47.8%		54%	53%	40%	26%	64%	61%	28%	55%	46%	47%	53%	40%	55%
51.4%		54%	63%	54%	50%	36%	42%	48%	64%	38%	41%	59%	68%	51%
53.5%		58%	57%	43%	78%	44%	61%	60%	64%	42%	42%	63%	42%	42%
71.5%		77%	78%	64%	71%	72%	76%	74%	57%	74%	74%	76%	73%	64%
56.4%		72%	56%	25%	25%	67%	65%	53%	53%	68%	49%	57%	78%	65%
30.4%		25%	28%	28%	66%	22%	36%	35%	39%	27%	18%	26%	21%	24%
59.9%		61%	75%	50%	31%	70%	69%	54%	54%	69%	35%	66%	75%	70%
63.5%		61%	62%	78%	97%	43%	61%	67%	78%	62%	46%	57%	48%	65%
65.7%		74%	78%	69%	49%	66%	72%	57%	67%	72%	53%	68%	53%	76%
76.0%		83%	90%	77%	57%	57%	77%	75%	82%	87%	74%	70%	79%	80%
59.3%		67%	76%	83%	59%	41%	53%	59%	75%	48%	61%	45%	57%	47%
84.6%		82%	91%	91%	83%	94%	89%	91%	91%	77%	75%	65%	88%	83%
68.1%		77%	69%	54%	31%	73%	80%	73%	49%	74%	81%	80%	79%	65%
67.5%		77%	75%	75%	42%	80%	79%	74%	59%	66%	57%	76%	74%	44%
69.8%		72%	72%	69%	68%	60%	74%	75%	74%	75%	69%	66%	60%	74%
70.5%		75%	72%	89%	71%	53%	74%	73%	87%	72%	82%	62%	38%	69%
66.5%		71%	65%	55%	57%	74%	79%	65%	62%	72%	59%	81%	59%	65%
62.3%		59%	56%	56%	58%	62%	60%	69%	58%	73%	62%	61%	66%	70%
69.4%		71%	67%	75%	74%	57%	75%	59%	54%	81%	54%	73%	71%	91%
59.9%		70%	70%	50%	33%	70%	60%	54%	59%	72%	54%	63%	52%	72%
73.8%		77%	76%	79%	37%	79%	76%	72%	94%	82%	70%	73%	78%	66%
74.9%		84%	83%	57%	36%	84%	86%	76%	57%	86%	73%	83%	82%	87%
57.1%		68%	60%	57%	64%	10%	65%	63%	66%	35%	59%	69%	55%	71%
43.9%		48%	49%	48%	24%	44%	52%	45%	40%	47%	24%	46%	45%	59%
70.2%		73%	77%	68%	36%	79%	77%	69%	60%	74%	73%	77%	72%	77%
68.8%		79%	83%	58%	40%	85%	76%	64%	58%	79%	40%	72%	89%	72%
71.5%		84%	89%	66%	58%	74%	71%	87%	69%	53%	53%	87%	53%	86%
59.8%		66%	66%	49%	30%	62%	69%	65%	49%	59%	58%	65%	68%	72%
61.2%		62%	63%	58%	61%	61%	65%	65%	59%	59%	59%	60%	61%	63%
64.7%		60%	68%	68%	57%	72%	71%	67%	62%	61%	62%	61%	71%	61%
68.6%		68%	80%	73%	61%	74%	67%	72%	64%	74%	64%	73%	61%	61%
72.0%		77%	82%	75%	48%	76%	72%	70%	77%	75%	73%	71%	68%	72%
73.6%		80%	77%	75%	60%	64%	94%	80%	77%	77%	45%	86%	65%	77%
50.5%		51%	51%	39%	62%	50%	55%	58%	39%	41%	41%	58%	45%	67%
56.8%		63%	65%	47%	22%	59%	64%	61%	51%	66%	41%	64%	65%	71%
46.2%		56%	44%	44%	43%	48%	44%	48%	30%	58%	24%	46%	58%	58%
52.4%		57%	62%	46%	45%	50%	57%	47%	52%	54%	34%	61%	62%	54%
54.2%		52%	61%	52%	62%	45%	59%	56%	52%	59%	14%	52%	67%	73%
74.6%		82%	82%	77%	77%	67%	77%	71%	74%	77%	69%	73%	72%	72%
74.5%		65%	74%	86%	81%	61%	73%	82%	80%	65%	81%	82%	61%	77%
40.0%		33%	63%	49%	42%	25%	41%	54%	42%	68%	17%	34%	43%	9%
66.1%		45%	67%	67%	49%	54%	78%	78%	74%	83%	71%	67%	46%	80%
63.0%		67%	70%	69%	48%	67%	72%	67%	68%	74%	46%	62%	45%	64%
30.5%		31%	39%	22%	11%	46%	34%	34%	22%	34%	11%	30%	44%	38%
67.9%		65%	71%	64%	81%	62%	80%	59%	64%	68%	33%	70%	85%	81%
67.8%		76%	82%	66%	35%	75%	57%	52%	69%	82%	66%	69%	82%	70%
74.5%		83%	72%	84%	63%	63%	72%	77%	84%	79%	77%	72%	65%	77%
72.5%		74%	79%	85%	75%	54%	67%	78%	74%	79%	66%	78%	63%	71%
59.5%		71%	64%	41%	25%	66%	58%	59%	60%	81%	25%	59%	82%	83%
56.9%		64%	60%	60%	9%	62%	67%	62%	67%	62%	62%	55%	43%	67%
59.5%		72%	55%	55%	33%	71%	76%	56%	60%	75%	53%	65%	30%	72%
74.2%		76%	80%	77%	68%	76%	87%	74%	71%	68%	65%	70%	76%	77%
84.4%		76%	94%	82%	89%	73%	86%	88%	75%	77%	88%	93%	84%	92%
69.8%		77%	79%	71%	40%	77%	73%	74%	82%	73%	62%	74%	61%	65%
75.2%		80%	80%	80%	70%	59%	74%	75%	87%	84%	72%	75%	62%	80%
61.7%		63%	49%	49%	74%	43%	66%	78%	70%	64%	50%	67%	55%	74%
46.0%		49%	47%	53%	54%	26%	43%	55%	50%	49%	36%	55%	36%	45%
69.5%		62%	73%	62%	69%	80%	70%	70%	73%	73%	59%	70%	70%	73%
70.8%		73%	75%	67%	53%	72%	71%	69%	68%	75%	76%	75%	74%	72%
67.0%		77%	69%	71%	70%	64%	64%	65%	49%	65%	73%	70%	65%	69%
62.0%		67%	73%	70%	56%	44%	69%	72%	76%	65%	64%	60%	58%	32%
83.0%		88%	83%	89%	71%	89%	83%	73%	79%	79%	83%	79%	94%	89%
66.9%		75%	66%	66%	45%	69%	71%	69%	49%	74%	72%	74%	71%	69%
61.2%		53%	56%	67%	77%	73%	69%	60%	60%	55%	38%	65%	67%	55%
50.4%		60%	61%	37%	22%	62%	57%	48%	41%	57%	22%	56%	75%	57%