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%3Apakistan C10 - Run 1d5c164...

Global Dialogues GD4 - Pakistan (10 context Qs)

DTEF: Predict response distributions for Pakistan. 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

Efficiency & Succinctness

Social interaction

General Knowledge

Best Models (Coverage)

1.Claude Sonnet 4
73.8%
2.GPT 4.1
73.8%
3.Mistral Medium 3
73.6%
4.Claude Haiku 4.5
73.3%
5.Llama 4 Maverick
72.5%

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 73.3%	1st 73.8%	6th 72.5%	13th 65.9%	11th 68.3%	5th 72.5%	3rd 73.6%	2nd 73.8%	7th 71.9%	10th 68.9%	9th 69.6%	12th 67.3%	8th 69.6%
59.4%		66%	69%	77%	64%	46%	59%	60%	55%	51%	66%	47%	56%	56%
72.3%		77%	72%	83%	77%	52%	60%	86%	81%	71%	70%	73%	69%	69%
76.3%		78%	81%	78%	67%	72%	84%	75%	82%	83%	72%	71%	71%	78%
84.7%		89%	87%	82%	67%	81%	81%	86%	89%	92%	92%	87%	91%	77%
58.7%		62%	62%	63%	71%	44%	56%	62%	61%	63%	50%	53%	53%	63%
69.1%		65%	79%	79%	72%	65%	69%	71%	74%	65%	70%	78%	69%	42%
75.4%		83%	81%	89%	72%	70%	81%	76%	67%	76%	72%	65%	76%	72%
77.2%		80%	73%	74%	80%	71%	80%	82%	69%	82%	77%	85%	73%	78%
70.5%		79%	63%	58%	52%	77%	78%	78%	64%	78%	77%	81%	56%	75%
72.5%		74%	81%	81%	66%	76%	84%	76%	85%	78%	77%	66%	60%	39%
81.4%		86%	88%	79%	58%	83%	85%	81%	86%	85%	83%	82%	88%	74%
68.7%		69%	71%	73%	70%	70%	72%	71%	78%	66%	58%	70%	60%	65%
83.8%		88%	92%	81%	57%	86%	85%	79%	88%	81%	100%	88%	82%	83%
50.3%		65%	65%	63%	52%	41%	58%	58%	46%	54%	33%	49%	0%	70%
59.9%		69%	56%	59%	63%	58%	66%	75%	70%	52%	53%	49%	53%	56%
59.8%		54%	58%	63%	72%	52%	67%	77%	73%	63%	51%	50%	45%	52%
63.1%		70%	64%	70%	64%	56%	59%	64%	66%	64%	64%	58%	51%	70%
71.2%		72%	68%	77%	70%	72%	68%	73%	71%	68%	65%	71%	77%	74%
85.7%		85%	90%	77%	100%	83%	83%	87%	90%	80%	89%	86%	86%	78%
65.6%		68%	66%	61%	65%	66%	69%	67%	75%	59%	62%	68%	66%	61%
80.1%		83%	81%	81%	81%	83%	81%	82%	81%	81%	59%	74%	90%	84%
83.3%		85%	90%	84%	46%	94%	83%	87%	74%	90%	90%	85%	85%	90%
65.9%		75%	70%	63%	43%	70%	70%	75%	66%	71%	60%	75%	67%	52%
40.8%		46%	45%	42%	47%	23%	44%	53%	51%	37%	28%	44%	24%	47%
67.5%		69%	72%	74%	58%	65%	75%	63%	78%	64%	69%	70%	56%	65%
80.1%		79%	84%	88%	79%	79%	76%	79%	82%	79%	79%	79%	79%	79%
71.1%		72%	74%	74%	76%	67%	78%	68%	71%	67%	65%	64%	78%	70%
64.0%		65%	70%	87%	10%	49%	74%	79%	75%	58%	68%	64%	70%	63%
70.1%		77%	72%	75%	76%	72%	67%	71%	78%	67%	71%	57%	63%	65%
72.4%		68%	75%	72%	70%	68%	71%	72%	75%	72%	71%	76%	72%	79%
79.4%		83%	92%	74%	48%	93%	87%	85%	87%	79%	72%	87%	94%	51%
78.2%		90%	90%	87%	54%	62%	89%	86%	82%	70%	70%	77%	76%	83%
60.2%		60%	61%	68%	67%	51%	63%	64%	77%	75%	59%	51%	39%	48%
68.8%		61%	68%	75%	88%	62%	76%	82%	87%	72%	59%	64%	46%	55%
66.3%		74%	70%	53%	70%	63%	70%	66%	53%	52%	64%	75%	74%	78%
79.0%		88%	84%	64%	49%	85%	94%	81%	76%	90%	83%	87%	81%	65%
75.6%		83%	79%	79%	79%	75%	57%	79%	72%	75%	82%	78%	78%	67%
69.5%		65%	67%	61%	63%	77%	65%	68%	78%	73%	67%	84%	68%	68%
67.0%		69%	71%	58%	37%	75%	70%	67%	68%	71%	76%	71%	73%	65%
60.8%		51%	62%	54%	46%	82%	54%	57%	59%	61%	77%	70%	56%	62%
67.5%		70%	68%	75%	75%	50%	69%	71%	77%	76%	53%	70%	56%	68%
71.5%		79%	79%	67%	0%	90%	81%	75%	73%	64%	93%	64%	82%	83%
69.8%		71%	78%	84%	68%	65%	65%	81%	63%	57%	88%	59%	58%	70%
70.3%		66%	66%	66%	80%	67%	72%	72%	77%	66%	75%	75%	70%	62%
79.0%		86%	83%	87%	80%	72%	72%	82%	77%	83%	87%	85%	80%	53%
76.8%		69%	80%	85%	75%	70%	84%	78%	80%	81%	73%	71%	68%	84%
55.4%		62%	60%	56%	55%	58%	49%	55%	62%	58%	57%	51%	49%	48%
90.5%		85%	73%	73%	100%	92%	90%	95%	90%	100%	100%	85%	100%	94%
78.9%		79%	87%	78%	41%	87%	89%	78%	73%	84%	84%	78%	78%	90%
71.5%		70%	73%	79%	68%	72%	76%	73%	69%	67%	64%	74%	72%	72%
64.5%		64%	67%	73%	60%	69%	68%	66%	64%	62%	67%	59%	63%	57%
55.9%		51%	56%	60%	74%	52%	62%	71%	66%	57%	39%	57%	30%	52%
74.9%		78%	78%	89%	83%	72%	74%	78%	77%	72%	65%	57%	78%	73%
49.5%		50%	45%	50%	81%	34%	50%	57%	57%	50%	45%	41%	41%	43%
76.5%		69%	83%	80%	82%	79%	79%	73%	82%	82%	64%	77%	71%	73%
71.1%		68%	78%	84%	79%	69%	72%	75%	72%	72%	65%	65%	60%	65%
55.4%		41%	52%	47%	81%	35%	58%	58%	69%	58%	58%	62%	38%	63%
81.4%		86%	84%	72%	65%	88%	83%	73%	86%	85%	90%	86%	85%	75%
54.8%		58%	50%	67%	81%	34%	55%	69%	67%	54%	43%	49%	35%	50%
79.7%		84%	83%	73%	66%	84%	75%	75%	76%	79%	83%	82%	88%	88%
75.9%		82%	83%	83%	66%	71%	77%	80%	72%	76%	82%	67%	77%	71%
62.2%		63%	67%	67%	63%	58%	59%	59%	71%	56%	63%	59%	65%	58%
81.0%		78%	83%	79%	83%	90%	92%	94%	88%	79%	63%	74%	71%	79%
75.5%		79%	79%	68%	51%	74%	76%	77%	77%	76%	79%	79%	85%	81%
74.1%		82%	75%	66%	68%	72%	77%	76%	79%	79%	73%	81%	78%	57%
65.8%		74%	66%	71%	0%	60%	80%	80%	78%	75%	82%	64%	47%	78%
54.0%		59%	61%	64%	49%	49%	64%	59%	53%	51%	50%	50%	40%	53%
66.7%		75%	72%	67%	67%	70%	69%	65%	63%	68%	54%	64%	58%	75%
65.5%		68%	67%	67%	72%	61%	56%	68%	72%	68%	54%	64%	60%	75%
86.1%		89%	87%	90%	81%	86%	87%	81%	79%	85%	87%	87%	87%	93%
68.5%		58%	62%	60%	69%	64%	71%	66%	72%	74%	74%	76%	73%	72%
73.8%		76%	81%	87%	35%	82%	79%	71%	77%	78%	76%	79%	81%	58%
81.5%		94%	86%	89%	69%	82%	76%	89%	89%	77%	76%	76%	81%	75%
66.5%		71%	73%	73%	75%	59%	73%	79%	84%	58%	37%	75%	43%	65%
71.4%		77%	78%	68%	32%	78%	79%	63%	82%	79%	76%	68%	74%	74%
83.2%		88%	88%	80%	59%	94%	80%	78%	79%	92%	78%	90%	85%	90%
76.3%		79%	83%	81%	56%	76%	80%	77%	78%	72%	71%	75%	83%	81%
80.4%		80%	78%	82%	76%	72%	73%	82%	83%	80%	84%	82%	86%	87%
67.2%		75%	77%	62%	38%	69%	69%	65%	64%	72%	72%	66%	72%	73%
66.9%		69%	70%	63%	71%	69%	68%	66%	62%	74%	58%	65%	65%	70%
77.3%		78%	75%	75%	78%	71%	82%	84%	81%	78%	78%	73%	78%	74%
79.2%		79%	84%	80%	80%	88%	76%	74%	71%	84%	65%	83%	82%	83%
56.5%		61%	66%	64%	39%	47%	64%	59%	64%	59%	54%	51%	55%	52%
76.5%		88%	76%	74%	76%	73%	71%	75%	81%	76%	78%	74%	76%	76%
71.1%		81%	79%	69%	81%	76%	71%	73%	80%	73%	38%	70%	77%	56%
76.8%		81%	87%	76%	47%	78%	78%	77%	81%	78%	81%	76%	83%	75%
61.7%		62%	63%	66%	59%	60%	60%	60%	60%	69%	59%	61%	61%	62%
63.4%		63%	62%	57%	65%	65%	63%	58%	58%	63%	67%	73%	61%	69%
70.8%		71%	76%	73%	83%	54%	68%	75%	71%	61%	76%	63%	67%	82%
83.0%		78%	82%	78%	82%	88%	95%	94%	91%	86%	82%	82%	59%	82%
66.7%		68%	63%	73%	71%	56%	72%	72%	57%	63%	70%	70%	69%	63%
57.4%		54%	79%	67%	52%	26%	76%	53%	60%	81%	42%	38%	44%	74%
65.0%		70%	69%	80%	32%	77%	51%	66%	61%	61%	67%	61%	71%	79%
78.1%		78%	74%	74%	73%	82%	79%	79%	81%	80%	73%	84%	77%	81%
56.8%		57%	60%	55%	57%	59%	60%	56%	54%	58%	43%	51%	60%	68%
80.0%		82%	82%	82%	82%	74%	85%	79%	84%	79%	76%	77%	81%	77%
78.7%		86%	85%	85%	51%	80%	82%	77%	86%	74%	75%	77%	79%	86%
82.2%		91%	91%	91%	65%	76%	71%	87%	85%	93%	91%	71%	77%	80%
74.9%		88%	78%	78%	82%	53%	75%	90%	83%	73%	60%	70%	62%	82%
80.7%		86%	80%	69%	93%	74%	75%	75%	91%	87%	68%	82%	81%	88%
53.5%		61%	60%	63%	39%	52%	54%	69%	77%	51%	45%	43%	40%	42%
84.0%		82%	82%	88%	78%	85%	82%	91%	83%	78%	93%	91%	83%	76%
82.9%		86%	87%	86%	87%	74%	81%	87%	73%	83%	87%	73%	87%	87%
69.0%		74%	65%	68%	73%	53%	67%	77%	72%	70%	74%	69%	68%	67%
82.9%		87%	87%	87%	95%	73%	83%	82%	89%	76%	87%	83%	72%	77%
64.7%		71%	75%	71%	64%	53%	73%	65%	58%	73%	59%	44%	54%	81%
69.1%		76%	75%	72%	74%	62%	71%	78%	39%	78%	81%	64%	58%	70%
55.2%		50%	59%	59%	76%	33%	55%	61%	73%	59%	37%	61%	42%	52%
70.9%		66%	66%	72%	75%	74%	82%	71%	79%	74%	57%	57%	74%	75%
65.8%		77%	68%	73%	81%	62%	54%	74%	77%	68%	76%	54%	49%	43%
86.4%		92%	94%	89%	90%	85%	92%	79%	90%	89%	73%	85%	86%	79%
68.0%		70%	67%	58%	63%	67%	76%	72%	77%	76%	66%	67%	63%	62%
75.1%		74%	75%	80%	83%	67%	76%	83%	83%	71%	79%	73%	65%	67%
74.1%		78%	76%	63%	69%	78%	78%	69%	72%	78%	79%	72%	74%	77%
77.7%		79%	71%	65%	71%	96%	81%	81%	78%	81%	86%	86%	69%	66%
59.6%		57%	62%	57%	62%	60%	60%	57%	60%	64%	42%	62%	62%	70%