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%3Aisrael C10 - Run fe50e27...

Global Dialogues GD4 - Israel (10 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

Efficiency & Succinctness

AI Safety & Robustness

Best Models (Coverage)

1.Claude Sonnet 4.5
74.0%
2.Claude Sonnet 4
72.9%
3.Claude 3.7 Sonnet
72.6%
4.Claude Haiku 4.5
72.3%
5.GPT 5
71.5%

🔀 Least Similar Models

Claude Sonnet 4.5vsGPT 5.1

81.2% similarity

👯 Most Similar Models

GPT 4.1 NanovsGPT 4o Mini

94.5% similarity

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 3.7 Sonnet	Claude Haiku 4.5	Claude Sonnet 4	Claude Sonnet 4.5	Gemini 2.5 Flash	Gemma 3 12b It	Llama 4 Maverick	Mistral Large 2411	Mistral Medium 3	GPT 4.1	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o	GPT 4o Mini	GPT 5	GPT 5.1	GPT OSS 120b	GPT OSS 20b	Qwen3 30b A3B Instruct 2507	Qwen3 32b	Grok 4.1 Fast
Score		3rd 72.6%	4th 72.3%	2nd 72.9%	1st 74.0%	20th 67.0%	16th 68.1%	10th 70.6%	12th 69.1%	13th 69.1%	6th 71.5%	8th 71.2%	18th 68.0%	9th 71.0%	11th 70.2%	5th 71.5%	7th 71.3%	19th 67.1%	21st 64.2%	14th 68.5%	17th 68.1%	15th 68.4%
59.9%		71%	65%	66%	66%	62%	44%	56%	59%	60%	58%	54%	59%	61%	58%	66%	58%	61%	47%	63%	58%	66%
70.0%		70%	69%	71%	80%	70%	64%	76%	77%	71%	61%	82%	74%	73%	74%	65%	66%	61%	58%	74%		65%
78.7%		83%	83%	83%	83%	80%	76%	80%	71%	75%	87%	84%	75%	75%	75%	79%	80%	83%	71%	74%	75%	80%
62.6%		68%	62%	67%	70%	63%	66%	62%	65%	54%	67%	68%	63%	66%	63%	72%	60%	54%	50%	57%	52%	65%
69.3%		83%	73%	73%	79%	75%	59%	75%	70%	73%	73%	70%	65%	74%	64%	76%	71%	61%	59%	64%	56%	63%
73.1%		84%	71%	66%	76%	67%	67%	64%	73%	76%	84%	72%	72%	82%	79%	84%	82%	73%	63%	72%	66%	63%
49.5%		60%	64%	60%	67%	57%	49%	67%	44%	51%	40%	40%	28%	38%	36%	54%	46%	46%	52%	41%	56%	44%
70.8%		64%	68%	67%	55%	66%	81%	75%	75%	72%	73%	75%	66%	71%	73%	74%	76%	68%	56%	71%	79%	82%
78.6%		88%	77%	93%	92%	61%	77%	82%	79%	74%	71%	55%	91%	82%	82%	76%	88%	85%	57%	80%		82%
77.5%		72%	83%	78%	67%	83%	81%	73%	85%	65%	51%	85%	94%	89%	94%	63%	55%	86%	70%	90%		87%
73.5%		78%	75%	74%	80%	62%	75%	68%	74%	68%	80%	75%	73%	77%	74%	84%	77%	77%	69%	72%	60%	71%
71.8%		77%	79%	82%	78%	72%	78%	78%	64%	72%	77%	78%	56%	72%	72%	76%	77%	59%	59%	70%	72%	59%
69.3%		75%	73%	68%	71%	67%	70%	68%	75%	69%	67%	69%	68%	69%	74%	71%	65%	69%	72%	74%	60%	61%
61.3%		71%	71%	71%	71%	57%	53%	64%	54%	62%	59%	66%	47%	51%	53%	63%	74%	56%	59%	66%	48%	71%
65.0%		57%	65%	71%	62%	47%	62%	65%	72%	54%	70%	69%	71%	72%	71%	76%	65%	69%	59%	60%	68%	61%
82.6%		87%	90%	85%	85%	74%	74%	86%	85%	82%	72%	91%	75%	90%	82%	82%	85%	74%	77%	83%	90%	85%
63.3%		61%	59%	57%	57%	61%	64%	65%	70%	69%	65%	65%	61%	70%	70%	58%	59%	73%	58%	65%	68%	54%
81.9%		85%	83%	77%	84%	82%	75%	86%	87%	89%	82%	86%	82%	85%	78%	82%	83%	73%	81%	90%	77%	73%
66.2%		67%	59%	67%	73%	59%	74%	60%	56%	58%	73%	73%	52%	62%	73%	75%	75%	64%	65%	68%	65%	73%
81.2%		82%	87%	82%	82%	85%	63%	86%	87%	70%	78%	77%	89%	81%	83%	81%	82%	82%	79%	87%		81%
71.1%		66%	76%	68%	66%	70%	66%	68%	76%	76%	77%	76%	72%	71%	75%	63%	72%	71%	68%	68%	72%	76%
68.2%		77%	71%	71%	77%	73%	72%	60%	66%	70%	72%	71%	66%	68%	65%	61%	70%	60%	60%	60%	72%	70%
64.4%		72%	55%	61%	61%	68%	62%	58%	69%	67%	72%	50%	60%	77%	58%	79%	72%	51%	64%	72%	53%	72%
37.6%		51%	40%	47%	47%	60%	31%	43%	40%	43%	45%	30%	30%	48%	23%	29%	29%	30%	35%	24%	30%	35%
70.6%		73%	70%	76%	76%	71%	68%	73%	69%	65%	75%	71%	66%	75%	61%	78%	75%	59%	78%	64%	68%	72%
77.9%		84%	63%	78%	92%	81%	78%	76%	67%	81%	84%	75%	81%	84%	81%	76%	75%	70%	62%	81%		89%
67.3%		69%	70%	69%	69%	70%	63%	69%	68%	68%	70%	67%	65%	68%	62%	74%	70%	65%	65%	65%	62%	66%
83.9%		90%	87%	84%	85%	85%	68%	86%	81%	81%	87%	88%	84%	85%	86%	85%	82%	74%	83%	86%	85%	90%
62.0%		65%	62%	68%	64%	63%	58%	68%	62%	59%	61%	62%	63%	65%	53%	62%	63%	62%	53%	60%	71%	58%
85.2%		85%	80%	85%	85%	90%	86%	100%	81%	77%	85%	87%	83%	85%	85%	90%	89%	86%	64%	91%	84%	91%
78.6%		79%	85%	82%	82%	50%	83%	84%	77%	79%	78%	83%	82%	81%	81%	84%	79%	78%	71%	83%	74%	75%
65.0%		65%	66%	64%	64%	66%	62%	60%	65%	54%	71%	64%	70%	65%	65%	62%	60%	70%	66%	65%	66%	76%
78.3%		75%	80%	77%	76%	77%	88%	80%	79%	78%	79%	82%	71%	80%	71%	77%	83%	83%	77%	72%	78%	82%
70.9%		73%	72%	73%	77%	87%	65%	70%	74%	80%	85%	72%	62%	80%	67%	73%	71%	50%	62%	67%	63%	66%
58.5%		48%	85%	64%	60%	67%	66%	66%	55%	59%	41%	52%	66%	59%	62%	50%	53%	50%	44%	66%	64%	52%
67.5%		72%	72%	76%	76%	62%	69%	73%	61%	68%	67%	60%	60%	66%	69%	66%	68%	67%	66%	69%	64%	67%
57.9%		54%	69%	62%	79%	35%	56%	66%	51%	61%	63%	42%	64%	57%	66%	58%	53%	58%	54%	57%	60%	51%
59.2%		58%	67%	69%	70%	46%	56%	49%	71%	53%	63%	66%	39%	53%	63%	72%	66%	54%	46%	67%	49%	66%
74.6%		72%	75%	69%	69%	71%	77%	75%	78%	78%	73%	72%	76%	78%	77%	75%	77%	78%	75%	77%	77%	67%
33.6%		25%	33%	38%	39%	29%	40%	30%	45%	29%	29%	41%	37%	24%	47%	44%	42%	24%	29%	38%	19%	24%
69.7%		71%	71%	71%	80%	63%	59%	71%	70%	72%	80%	76%	53%	72%	62%	78%	73%	72%	57%	71%	69%	72%
59.6%		69%	61%	78%	78%	35%	63%	75%	63%	57%	59%	68%	75%	41%	43%	48%	57%	47%	43%	90%	73%	29%
60.0%		65%	63%	62%	58%	49%	54%	50%	63%	58%	68%	68%	54%	58%	49%	62%	66%	67%	67%	58%		62%
66.7%		67%	71%	66%	68%	70%	67%	77%	80%	68%	75%	60%	65%	72%	65%	60%	62%	60%	52%	71%	71%	54%
78.5%		75%	85%	89%	89%	82%	91%	88%	80%	64%	81%	70%	81%	81%	75%	69%	80%	62%	75%	81%	75%	75%
79.2%		85%	62%	76%	76%	74%	86%	78%	90%	82%	77%	77%	76%	81%	74%	90%	78%	85%	82%	77%	94%	63%
65.3%		59%	65%	60%	64%	58%	79%	61%	75%	69%	60%	66%	70%	69%	72%	65%	66%	64%	69%	72%	43%	65%
92.1%		95%	95%	87%	87%	85%	85%	90%	95%	95%	95%	91%	100%	95%	100%	92%	87%	88%	93%	90%	100%	90%
67.2%		81%	65%	72%	72%	60%	70%	61%	65%	68%	60%	72%	68%	60%	68%	65%	68%	70%	65%	65%	69%	67%
67.0%		70%	64%	70%	70%	74%	70%	60%	44%	62%	75%	73%	55%	59%	74%	76%	75%	70%	60%	67%	68%	70%
76.2%		83%	80%	83%	83%	73%	83%	74%	62%	66%	83%	79%	59%	73%	83%	82%	80%	74%	64%	80%		79%
59.0%		66%	51%	55%	57%	63%	58%	62%	59%	69%	60%	58%	53%	66%	53%	63%	65%	53%	55%	46%	59%	69%
71.3%		78%	71%	78%	80%	79%	64%	65%	76%	70%	76%	71%	62%	70%	72%	70%	71%	70%	70%	71%	65%	68%
67.6%		82%	63%	66%	71%	84%	66%	66%	66%	82%	68%	67%	66%	72%	67%	56%	77%	49%	59%	66%	62%	64%
77.2%		68%	67%	80%	80%	70%	82%	75%	87%	77%	75%	85%	82%	82%	75%	82%	77%	75%	75%	75%	72%	80%
74.6%		93%	71%	82%	82%	73%	70%	63%	74%	85%	77%	62%	68%	74%	62%	86%	86%	75%	69%	68%	62%	85%
57.5%		57%	50%	59%	55%	62%	42%	71%	66%	63%	71%	64%	39%	66%	64%	71%	65%	64%	41%	40%	45%	53%
75.8%		71%	82%	80%	79%	73%	75%	80%	73%	68%	72%	79%	80%	82%	82%	71%	73%	80%	74%	82%	63%	73%
65.2%		70%	68%	63%	84%	84%	46%	68%	63%	70%	82%	67%	48%	70%	56%	75%	76%	56%	39%	56%		63%
67.0%		67%	72%	70%	70%	56%	82%	80%	69%	58%	56%	65%	77%	71%	71%	67%	62%	59%	59%	71%	59%	66%
73.5%		75%	81%	76%	76%	47%	78%	77%	77%	60%	48%	67%	89%	85%	85%	66%	60%	77%	81%	81%	73%	85%
78.1%		78%	79%	80%	80%	76%	62%	75%	71%	78%	77%	73%	79%	80%	79%	82%	84%	83%	82%	84%	78%	80%
80.3%		64%	87%	83%	83%	76%	69%	75%	74%	85%	74%	90%	94%	80%	90%	78%	78%	85%	95%	87%	70%	69%
76.6%		75%	79%	71%	76%	62%	82%	71%	73%	78%	79%	78%	78%	71%	83%	85%	79%	77%	75%	79%	83%	75%
66.8%		72%	63%	67%	72%	62%	65%	62%	61%	70%	72%	63%	68%	76%	62%	77%	72%	56%	62%	68%	65%	67%
71.2%		72%	72%	71%	72%	76%	74%	80%	78%	80%	76%	74%	51%	72%	70%	79%	75%	68%	39%	72%		72%
75.1%		83%	75%	83%	86%	67%	74%	81%	77%	70%	80%	78%	76%	72%	74%	74%	75%	73%	70%	65%	74%	71%
68.0%		69%	84%	77%	75%	66%	78%	64%	63%	61%	71%	69%	56%	70%	63%	78%	70%	62%	68%	70%	54%	59%
57.9%		50%	60%	51%	51%	59%	57%	56%	55%	62%	59%	64%	64%	49%	64%	64%	68%	46%	52%	67%	59%	59%
85.6%		87%	93%	87%	76%	79%	87%	93%	73%	79%	84%	91%	90%	83%	93%	87%	87%	87%	82%	87%	83%	90%
71.6%		75%	75%	77%	77%	51%	80%	82%	68%	69%	75%	67%	72%	73%	85%	75%	77%	63%	65%	70%	60%	67%
62.8%		63%	65%	71%	67%	37%	62%	64%	61%	62%	59%	66%	68%	62%	64%	65%	57%	65%	63%	69%		65%
83.6%		100%	91%	95%	95%	73%	82%	88%	90%	87%	80%	90%	83%	91%	88%	90%	95%	90%	82%	0%	78%	87%
76.9%		89%	85%	82%	86%	69%	79%	87%	80%	78%	88%	67%	60%	79%	82%	74%	71%	74%	62%	77%	71%	74%
66.3%		73%	69%	77%	77%	49%	68%	71%	65%	56%	61%	68%	73%	65%	59%	70%	65%	65%	48%	65%	69%	79%
71.7%		73%	75%	75%	75%	60%	77%	72%	68%	68%	60%	76%	75%	72%	77%	73%	70%	73%	73%	68%	77%	68%
64.2%		61%	77%	74%	74%	60%	74%	69%	61%	51%	69%	60%	54%	70%	65%	65%	60%	57%	58%	65%	66%	58%
86.3%		81%	81%	91%	87%	76%	79%	94%	72%	87%	100%	92%	86%	90%	89%	90%	90%	85%	79%	88%	87%	88%
65.4%		70%	66%	69%	73%	59%	66%	64%	66%	66%	71%	64%	66%	70%	61%	70%	66%	62%	61%	66%	51%	67%
70.2%		71%	68%	73%	73%	70%	73%	70%	65%	63%	80%	70%	69%	68%	74%	74%	74%	67%	66%	72%	70%	64%
86.4%		78%	84%	78%	87%	90%	78%	83%	87%	89%	91%	94%	100%	90%	90%	94%	94%	88%	86%	78%	84%	71%
76.6%		83%	87%	85%	83%	83%	73%	84%	69%	77%	82%	82%	64%	79%	80%	83%	86%	70%	68%	75%	58%	58%
76.8%		83%	79%	82%	84%	69%	70%	84%	74%	75%	76%	79%	73%	83%	73%	79%	83%	78%	67%	73%	74%	74%
74.3%		83%	73%	75%	75%	75%	77%	62%	75%	70%	76%	76%	75%	72%	74%	77%	73%	70%	78%	75%	72%	77%
85.1%		83%	93%	83%	83%	88%	85%	89%	81%	93%	86%	89%	82%	83%	94%	84%	86%	81%	80%	94%	75%	75%
79.7%		85%	85%	85%	82%	73%	84%	81%	80%	78%	78%	84%	79%	82%	78%	72%	78%	75%	65%	82%	89%	78%
62.0%		67%	76%	69%	71%	70%	69%	65%	60%	58%	60%	65%	58%	55%	73%	62%	59%	46%	42%	66%	66%	46%
79.0%		75%	84%	81%	79%	72%	74%	80%	71%	77%	87%	84%	86%	82%	93%	78%	75%	72%	82%	83%	77%	66%
56.1%		67%	63%	67%	63%	68%	43%	54%	63%	59%	59%	54%	40%	59%	50%	59%	59%	45%	35%	62%	59%	50%
76.1%		84%	84%	80%	84%	83%	74%	74%	72%	72%	77%	84%	63%	72%	68%	69%	73%	71%	77%	83%	77%	77%
77.2%		82%	71%	73%	71%	77%	58%	83%	73%	83%	75%	80%	78%	79%	74%	76%	83%	83%	87%	83%	75%	78%
37.2%		47%	55%	59%	59%	16%	11%	24%	29%	33%	42%	55%	27%	27%	24%	51%	47%	16%	48%	27%	31%	53%
63.0%		67%	66%	67%	72%	57%	67%	52%	57%	63%	61%	59%	65%	65%	60%	62%	62%	65%	64%	71%	57%	65%
79.5%		73%	89%	82%	82%	68%	74%	86%	72%	87%	78%	86%	80%	86%	85%	75%	82%	85%	55%	80%	85%	79%
57.6%		55%	71%	66%	67%	63%	66%	63%	60%	55%	53%	55%	60%	60%	60%	49%	51%	49%	45%	60%	49%	53%
64.1%		65%	67%	72%	72%	71%	69%	67%	61%	56%	69%	70%	70%	59%	64%	53%	64%	56%	50%	62%	63%	67%
54.0%		54%	52%	64%	71%	33%	61%	49%	49%	46%	62%	66%	66%	54%	65%	66%	57%	51%	59%	0%	58%	52%
88.0%		90%	87%	95%	95%	73%	82%	100%	87%	87%	78%	93%	88%	91%	88%	78%	95%	95%	86%	90%	88%	82%
74.5%		78%	81%	77%	90%	77%	56%	81%	75%	76%	81%	81%	66%	79%	70%	74%	76%	77%	60%	70%		66%
68.8%		78%	72%	68%	69%	75%	59%	57%	61%	57%	79%	79%	52%	75%	57%	69%	70%	70%	65%	57%	100%	75%
68.7%		74%	69%	73%	74%	26%	71%	67%	76%	78%	79%	65%	66%	73%	74%	67%	70%	77%	66%	54%		75%
78.1%		77%	81%	75%	77%	81%	70%	75%	78%	80%	80%	74%	80%	75%	84%	75%	78%	81%	77%	75%	88%	80%
59.8%		62%	68%	64%	60%	64%	72%	56%	62%	59%	49%	63%	63%	46%	54%	59%	60%	51%	53%	72%	59%	60%
72.1%		71%	73%	66%	66%	70%	55%	57%	64%	67%	75%	75%	75%	75%	75%	68%	71%	77%	72%	62%	100%	100%
73.4%		82%	78%	81%	83%	74%	63%	81%	72%	74%	81%	70%	71%	75%	75%	81%	79%	71%	57%	64%	70%	59%
52.9%		69%	66%	60%	66%	12%	40%	63%	38%	55%	58%	63%	63%	46%	38%	69%	61%	53%	38%	37%	63%	53%
67.1%		79%	71%	61%	75%	70%	53%	62%	63%	75%	73%	61%	53%	62%	65%	76%	81%	62%	71%	57%	67%	73%
72.0%		78%	61%	77%	77%	83%	48%	66%	71%	78%	89%	77%	67%	81%	67%	80%	76%	81%	78%	67%	69%	42%
53.9%		52%	55%	52%	52%	69%	65%	58%	58%	56%	55%	63%	61%	53%	62%	51%	45%	45%	43%	63%	46%	28%
74.8%		79%	77%	80%	79%	80%	73%	67%	76%	77%	80%	76%	69%	77%	70%	80%	79%	75%	46%	72%	79%	80%
68.6%		70%	67%	75%	72%	70%	73%	69%	67%	63%	78%	65%	71%	66%	66%	67%	68%	57%	70%	66%	71%	70%
73.4%		74%	77%	77%	75%	75%	68%	71%	76%	78%	73%	72%	73%	72%	71%	72%	71%	72%	75%	66%	80%	74%
78.2%		90%	69%	78%	81%	76%	76%	82%	85%	73%	80%	72%	81%	88%	73%	77%	81%	76%	82%	66%	81%	76%
88.0%		84%	92%	82%	82%	92%	89%	86%	92%	92%	85%	92%	90%	90%	92%	93%	93%	85%	86%	92%	77%	83%
58.6%		53%	55%	63%	61%	68%	63%	49%	53%	61%	65%	61%	41%	65%	67%	62%	59%	49%	53%	53%	61%	68%
59.1%		57%	69%	68%	57%	69%	68%	62%	51%	51%	62%	63%	54%	62%	68%	48%	55%	57%	64%	60%	52%	45%

Model Similarity Dendrogram

Hierarchical clustering of models based on response similarity. Models grouped closer are more similar.