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%3Aisrael C5 - Run b08e256...

Global Dialogues GD4 - Israel (5 context Qs)

DTEF: Predict response distributions for Israel. 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

Demographic Processes

Economics & Finance

Best Models (Coverage)

1.Claude Sonnet 4
72.9%
2.Claude Sonnet 4.5
72.7%
3.Claude Haiku 4.5
72.1%
4.Gemini 2.5 Flash
71.5%
5.GPT 4.1 Mini
70.9%

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 72.1%	1st 72.9%	2nd 72.7%	4th 71.5%	10th 68.3%	7th 69.9%	13th 68.0%	6th 70.7%	5th 70.9%	11th 68.3%	9th 69.6%	8th 69.9%	12th 68.2%
58.6%		62%	66%	66%	57%	46%	52%	65%	65%	56%	65%	54%	52%	56%
73.6%		72%	80%	80%	80%	53%	75%	66%	68%	81%	76%	76%	76%	74%
78.2%		75%	83%	83%	81%	79%	80%	75%	78%	84%	75%	75%	75%	74%
65.0%		69%	71%	70%	63%	65%	67%	57%	65%	63%	63%	63%	63%	66%
67.9%		72%	72%	71%	73%	47%	71%	73%	69%	70%	70%	60%	64%	71%
71.5%		73%	76%	66%	72%	71%	69%	79%	80%	72%	72%	79%	72%	49%
51.1%		65%	60%	60%	62%	44%	61%	44%	46%	47%	37%	36%	51%	51%
70.7%		76%	67%	55%	71%	78%	80%	64%	74%	63%	74%	73%	71%	73%
79.1%		77%	83%	83%	88%	77%	84%	56%	72%	63%	89%	79%	88%	89%
81.2%		86%	78%	90%	90%	90%	75%	65%	51%	85%	90%	94%	90%	72%
73.1%		71%	69%	82%	72%	70%	74%	74%	75%	75%	74%	74%	77%	63%
73.8%		80%	82%	80%	75%	75%	68%	72%	77%	80%	56%	72%	71%	71%
71.3%		72%	64%	70%	67%	72%	70%	72%	68%	74%	72%	74%	74%	78%
66.9%		69%	87%	72%	78%	62%	64%	57%	63%	66%	53%	57%	71%	71%
59.4%		48%	73%	73%	43%	59%	10%	61%	53%	72%	71%	71%	62%	76%
81.8%		90%	85%	85%	74%	83%	86%	82%	72%	91%	75%	82%	82%	77%
64.5%		59%	57%	57%	62%	64%	65%	65%	70%	65%	70%	70%	65%	69%
81.8%		80%	81%	79%	84%	75%	84%	84%	72%	85%	88%	85%	84%	82%
66.9%		72%	73%	76%	69%	73%	57%	52%	68%	68%	54%	68%	68%	72%
80.9%		84%	82%	82%	81%	76%	86%	80%	86%	69%	88%	79%	82%	77%
72.8%		75%	66%	65%	75%	68%	74%	79%	68%	77%	76%	76%	76%	72%
66.1%		67%	58%	71%	66%	72%	62%	69%	69%	71%	60%	65%	60%	69%
64.2%		59%	61%	63%	77%	62%	65%	77%	79%	60%	55%	73%	67%	37%
37.2%		40%	47%	47%	48%	26%	43%	43%	40%	30%	30%	23%	27%	40%
70.2%		68%	76%	73%	73%	69%	73%	71%	80%	66%	67%	61%	68%	67%
75.3%		78%	76%	80%	74%	78%	76%	69%	81%	73%	81%	71%	71%	71%
68.0%		63%	67%	69%	70%	65%	68%	68%	64%	70%	69%	70%	73%	68%
86.1%		91%	85%	85%	88%	79%	100%	80%	93%	84%	82%	86%	82%	84%
62.8%		65%	68%	64%	59%	62%	66%	63%	69%	62%	63%	62%	53%	60%
87.5%		90%	85%	82%	90%	77%	91%	85%	80%	91%	91%	86%	89%	100%
80.0%		85%	82%	82%	83%	87%	83%	79%	78%	75%	82%	81%	83%	60%
61.2%		67%	49%	51%	62%	70%	64%	56%	63%	65%	70%	65%	65%	49%
76.9%		81%	77%	76%	85%	82%	82%	70%	81%	79%	67%	71%	71%	78%
69.7%		64%	73%	73%	80%	65%	77%	80%	76%	72%	62%	62%	60%	62%
63.7%		85%	82%	63%	68%	59%	64%	59%	42%	50%	64%	62%	64%	66%
66.5%		72%	76%	76%	69%	72%	64%	66%	72%	60%	60%	66%	69%	42%
63.5%		68%	77%	84%	66%	52%	63%	57%	50%	66%	66%	60%	57%	60%
58.4%		65%	69%	70%	46%	56%	57%	53%	62%	66%	39%	56%	52%	68%
73.2%		74%	69%	68%	76%	75%	75%	78%	74%	72%	78%	77%	78%	58%
36.3%		32%	39%	39%	24%	40%	34%	29%	34%	48%	37%	40%	38%	38%
70.5%		71%	71%	80%	80%	59%	71%	79%	87%	70%	55%	60%	62%	72%
70.8%		78%	78%	80%	63%	80%	57%	64%	63%	63%	62%	56%	90%	87%
55.2%		56%	58%	58%	49%	58%	50%	57%	62%	54%	54%	54%	54%	54%
66.4%		69%	66%	66%	70%	68%	73%	70%	58%	56%	76%	65%	65%	61%
82.7%		94%	89%	92%	91%	84%	90%	62%	88%	80%	83%	60%	81%	81%
75.5%		54%	76%	78%	72%	86%	78%	77%	77%	81%	76%	74%	76%	77%
67.4%		66%	60%	59%	68%	72%	69%	71%	59%	63%	82%	71%	76%	60%
89.6%		99%	95%	87%	85%	85%	93%	82%	95%	90%	90%	91%	95%	78%
66.6%		66%	72%	72%	65%	68%	60%	73%	66%	70%	60%	68%	65%	61%
68.2%		70%	70%	70%	86%	66%	60%	62%	75%	64%	53%	70%	74%	67%
76.2%		84%	83%	86%	80%	83%	67%	59%	82%	76%	59%	76%	80%	76%
56.8%		53%	54%	56%	61%	54%	60%	57%	58%	57%	51%	58%	53%	67%
71.7%		71%	74%	76%	79%	61%	65%	72%	73%	71%	80%	72%	71%	67%
66.9%		70%	61%	71%	83%	57%	65%	74%	67%	67%	66%	66%	63%	60%
76.0%		69%	72%	82%	70%	70%	77%	76%	80%	77%	82%	75%	85%	73%
83.6%		83%	84%	85%	94%	74%	84%	94%	82%	83%	83%	80%	80%	81%
49.5%		36%	59%	55%	64%	40%	49%	55%	67%	49%	45%	52%	33%	40%
76.9%		82%	80%	69%	73%	76%	82%	67%	69%	82%	79%	80%	79%	82%
63.4%		68%	63%	82%	84%	47%	68%	70%	68%	70%	48%	51%	56%	49%
71.2%		74%	79%	70%	71%	75%	72%	55%	63%	73%	71%	71%	72%	80%
72.2%		70%	76%	76%	45%	84%	79%	60%	47%	63%	89%	89%	76%	84%
77.8%		82%	82%	82%	80%	61%	76%	78%	79%	75%	78%	77%	83%	79%
82.4%		87%	73%	73%	73%	78%	67%	85%	74%	90%	95%	94%	87%	95%
76.4%		77%	71%	71%	77%	85%	75%	78%	79%	77%	77%	83%	79%	64%
65.7%		66%	67%	67%	72%	71%	62%	67%	74%	63%	67%	68%	67%	43%
74.7%		73%	71%	72%	83%	81%	77%	76%	76%	74%	68%	70%	72%	78%
75.8%		81%	79%	89%	71%	68%	81%	66%	83%	74%	70%	74%	74%	76%
70.9%		79%	75%	75%	73%	82%	62%	65%	71%	73%	51%	63%	70%	83%
59.8%		60%	51%	52%	59%	59%	53%	59%	63%	68%	63%	64%	67%	60%
85.2%		82%	87%	87%	79%	87%	81%	79%	87%	86%	79%	93%	87%	93%
74.4%		71%	80%	68%	77%	91%	67%	58%	75%	67%	77%	77%	80%	79%
68.2%		69%	71%	71%	65%	67%	70%	61%	65%	70%	68%	68%	72%	69%
86.3%		93%	95%	95%	73%	78%	83%	91%	76%	93%	89%	88%	88%	80%
77.1%		74%	85%	89%	76%	87%	87%	75%	79%	67%	58%	75%	73%	77%
67.0%		77%	77%	77%	69%	61%	71%	48%	68%	65%	66%	59%	65%	68%
72.8%		75%	75%	75%	60%	80%	73%	72%	60%	74%	77%	77%	75%	74%
65.3%		72%	74%	70%	65%	69%	69%	54%	62%	60%	56%	65%	65%	68%
89.1%		94%	91%	87%	90%	80%	88%	88%	93%	88%	92%	87%	92%	88%
65.0%		66%	59%	69%	67%	70%	59%	67%	73%	64%	66%	66%	66%	53%
69.6%		71%	73%	75%	61%	70%	70%	65%	73%	70%	69%	70%	74%	64%
87.1%		97%	78%	78%	81%	80%	83%	86%	94%	94%	94%	90%	83%	94%
78.6%		86%	87%	81%	79%	68%	82%	77%	85%	80%	68%	83%	73%	73%
78.3%		80%	84%	84%	69%	77%	85%	75%	83%	83%	76%	73%	73%	76%
70.4%		71%	59%	66%	70%	80%	62%	73%	76%	75%	70%	70%	70%	73%
88.8%		83%	89%	83%	94%	85%	94%	92%	83%	89%	94%	94%	94%	80%
79.9%		81%	82%	89%	78%	83%	80%	82%	80%	77%	78%	78%	82%	69%
65.8%		66%	66%	75%	70%	64%	60%	61%	57%	65%	59%	70%	66%	76%
80.9%		83%	75%	79%	84%	77%	79%	77%	85%	79%	89%	81%	81%	83%
57.7%		54%	75%	67%	77%	52%	54%	51%	63%	54%	28%	42%	63%	70%
71.4%		82%	71%	71%	66%	68%	68%	68%	74%	81%	77%	65%	83%	54%
77.0%		71%	70%	71%	75%	72%	83%	87%	80%	80%	83%	74%	79%	76%
35.8%		59%	71%	59%	27%	16%	24%	40%	42%	55%	24%	24%	24%	0%
63.7%		66%	68%	68%	60%	67%	60%	60%	67%	60%	64%	65%	61%	62%
83.2%		88%	81%	77%	86%	77%	88%	85%	85%	90%	80%	85%	80%	80%
62.9%		66%	75%	70%	63%	70%	68%	46%	53%	60%	60%	60%	60%	67%
65.0%		69%	68%	72%	72%	61%	68%	52%	69%	64%	70%	64%	64%	52%
57.8%		60%	61%	63%	46%	63%	49%	37%	54%	62%	66%	66%	62%	62%
86.6%		91%	95%	95%	71%	83%	83%	87%	73%	93%	89%	88%	89%	89%
73.8%		80%	77%	78%	86%	51%	81%	75%	77%	81%	64%	66%	66%	77%
67.2%		78%	79%	69%	83%	53%	61%	47%	79%	74%	55%	52%	57%	87%
69.8%		64%	78%	78%	76%	63%	67%	74%	73%	66%	64%	74%	62%	69%
77.4%		75%	71%	73%	81%	73%	81%	78%	77%	81%	77%	81%	81%	77%
64.0%		66%	62%	69%	65%	72%	63%	55%	60%	63%	63%	58%	72%	64%
67.5%		70%	57%	62%	75%	55%	62%	62%	75%	75%	77%	75%	75%	58%
73.0%		74%	81%	82%	75%	63%	78%	71%	78%	77%	66%	75%	60%	69%
53.6%		55%	60%	64%	38%	40%	67%	55%	58%	63%	38%	55%	38%	66%
58.6%		65%	61%	27%	72%	53%	62%	75%	73%	60%	48%	57%	61%	48%
70.8%		71%	77%	77%	79%	48%	74%	78%	81%	80%	58%	67%	66%	64%
52.8%		48%	55%	55%	64%	64%	51%	53%	44%	47%	39%	59%	54%	54%
72.8%		74%	74%	76%	73%	72%	67%	79%	79%	76%	70%	70%	67%	70%
66.5%		59%	71%	69%	60%	71%	68%	58%	73%	62%	71%	66%	65%	71%
71.6%		79%	77%	75%	75%	70%	68%	73%	73%	73%	73%	71%	65%	59%
73.4%		70%	78%	78%	77%	66%	77%	78%	80%	67%	81%	73%	66%	63%
85.7%		87%	82%	82%	90%	93%	87%	79%	83%	93%	92%	92%	90%	64%
57.7%		49%	63%	61%	65%	63%	65%	65%	53%	61%	37%	60%	55%	53%
61.5%		69%	69%	60%	69%	68%	62%	50%	60%	60%	54%	62%	60%	56%