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%3Asingapore C10 - Run 128ae96...

Global Dialogues GD4 - Singapore (10 context Qs)

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

TAGS:

Global Dialogues Gd4

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Efficiency & Succinctness

Social interaction

AI Safety & Robustness

Demographic & Local Knowledge

Best Models (Coverage)

1.Claude Sonnet 4.5
68.1%
2.Claude 3.7 Sonnet
67.2%
3.GPT 4.1
66.9%
4.Claude Sonnet 4
66.4%
5.Claude Haiku 4.5
65.9%

🔀 Least Similar Models

Claude Sonnet 4.5vsGemma 3 12b It

75.8% similarity

👯 Most Similar Models

GPT 4.1vsGPT 4o

94.3% 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		2nd 67.2%	5th 65.9%	4th 66.4%	1st 68.1%	20th 60.1%	16th 62.4%	11th 64.5%	12th 63.3%	15th 62.6%	3rd 66.9%	8th 65.1%	19th 60.3%	6th 65.9%	14th 62.6%	7th 65.8%	10th 64.8%	18th 61.0%	21st 59.0%	17th 61.7%	13th 62.7%	9th 64.9%
58.4%		66%	63%	68%	66%	68%	43%	51%	61%	49%	62%	51%	58%	58%	52%	66%	63%	58%	55%	58%	50%	60%
60.1%		67%	46%	54%	61%	77%	33%	54%	51%	58%	76%	54%	54%	77%	65%	71%	76%	63%	58%	54%	64%	49%
77.7%		78%	81%	81%	91%	54%	74%	79%	72%	68%	91%	82%	72%	91%	72%	88%	78%	81%	72%	72%	72%	82%
58.7%		65%	61%	54%	57%	54%	66%	58%	62%	62%	54%	56%	59%	54%	59%	64%	59%	57%	63%	59%	59%	50%
54.6%		77%	59%	59%	66%	65%	43%	59%	52%	51%	58%	47%	48%	59%	45%	54%	50%	50%	45%	43%	51%	65%
64.2%		73%	64%	73%	73%	37%	64%	59%	71%	57%	80%	73%	71%	73%	71%	70%	70%	56%	38%	71%	38%	66%
76.6%		100%	100%	100%	100%	90%	71%	67%	75%	80%	60%	80%	82%	61%	65%	64%	68%	52%	71%	90%	64%	68%
57.0%		61%	58%	51%	58%	53%	57%	51%	61%	54%	61%	61%	51%	61%	54%	58%	61%	58%	56%	58%	47%	67%
58.5%		61%	67%	55%	55%	64%	58%	61%	61%	68%	61%	67%	43%	43%	58%	50%	47%	66%	68%	66%	71%	39%
70.3%		69%	79%	72%	72%	56%	79%	68%	80%	58%	56%	71%	72%	72%	76%	56%	75%	78%	74%	72%	75%	66%
75.6%		76%	83%	76%	82%	53%	81%	72%	81%	79%	72%	76%	73%	76%	73%	85%	80%	73%	64%	84%	72%	76%
74.7%		86%	82%	86%	86%	73%	83%	71%	71%	73%	86%	82%	58%	73%	82%	78%	77%	61%	53%	70%	56%	82%
50.5%		55%	55%	51%	51%	51%	51%	51%	51%	44%	59%	51%	51%	51%	47%	51%	51%	48%	48%	47%	48%	48%
58.8%		60%	68%	62%	61%	44%	58%	67%	52%	65%	60%	57%	60%	56%	56%	57%	66%	51%	60%	64%	51%	60%
45.0%		51%	41%	53%	35%	37%	29%	39%	43%	31%	51%	44%	46%	47%	49%	66%	41%	32%	40%	48%	53%	68%
50.7%		59%	54%	50%	58%	77%	45%	48%	44%	54%	67%	55%	37%	59%	44%	59%	55%	54%	26%	36%	33%	51%
52.1%		45%	45%	44%	54%	54%	55%	56%	63%	65%	56%	45%	50%	56%	56%	46%	49%	56%	54%	45%	56%	45%
58.2%		58%	62%	55%	62%	63%	62%	54%	63%	58%	58%	45%	51%	58%	59%	63%	51%	59%	60%	58%	51%	73%
72.3%		78%	78%	82%	78%	72%	64%	77%	74%	74%	89%	74%	74%	74%	58%	70%	70%	70%	62%	61%	67%	73%
70.3%		74%	76%	74%	74%	65%	78%	74%	71%	64%	74%	68%	80%	64%	74%	68%	68%	66%	56%	73%	64%	71%
66.9%		60%	72%	67%	67%	51%	65%	60%	81%	76%	63%	69%	66%	69%	66%	65%	70%	77%	62%	81%		51%
83.1%		78%	94%	89%	78%	77%	82%	89%	79%	89%	89%	89%	70%	73%	89%	89%	89%	89%	62%	81%	82%	89%
62.1%		66%	64%	66%	66%	33%	71%	60%	67%	62%	56%	62%	62%	66%	62%	65%	63%	60%	64%	52%	66%	72%
24.5%		30%	22%	37%	22%	37%	13%	30%	22%	30%	30%	13%	18%	30%	18%	18%	20%	22%	30%	13%	30%	30%
54.8%		56%	58%	52%	52%	77%	64%	63%	59%	48%	62%	50%	47%	62%	46%	56%	56%	44%	33%	47%	52%	66%
70.9%		72%	91%	66%	72%	73%	70%	71%	59%	56%	73%	73%	73%	73%	73%	77%	72%	58%	65%	73%	73%	76%
58.3%		61%	65%	61%	72%	51%	58%	61%	51%	51%	56%	61%	59%	55%	61%	57%	56%	56%	56%	54%	58%	65%
67.6%		71%	71%	71%	77%	77%	61%	67%	53%	58%	77%	67%	62%	67%	67%	67%	68%	63%	67%	67%	65%	77%
58.8%		70%	68%	68%	77%	60%	49%	66%	58%	53%	73%	58%	58%	58%	54%	60%	62%	44%	46%	54%	43%	55%
67.8%		73%	70%	72%	77%	65%	70%	69%	62%	51%	73%	60%	63%	73%	69%	72%	70%	64%	61%	63%	73%	73%
76.8%		69%	81%	76%	76%	32%	87%	93%	77%	86%	69%	81%	85%	72%	78%	70%	68%	73%	82%	78%	90%	90%
53.4%		58%	57%	58%	50%	47%	53%	49%	50%	47%	56%	62%	54%	58%	51%	54%	53%	63%	51%	51%	57%	43%
63.4%		73%	66%	65%	67%	67%	65%	62%	60%	62%	67%	58%	67%	65%	57%	72%	73%	62%	57%	45%	66%	55%
46.6%		50%	42%	50%	56%	73%	44%	48%	44%	48%	56%	50%	29%	44%	37%	53%	47%	42%	48%	35%	42%	40%
68.0%		79%	78%	76%	87%	48%	71%	76%	75%	68%	58%	65%	75%	76%	68%	69%	60%	64%	51%	76%	53%	56%
73.3%		71%	79%	81%	81%	81%	67%	69%	60%	69%	81%	81%	56%	81%	79%	77%	72%	60%	77%	81%	80%	57%
65.3%		73%	70%	73%	73%	53%	62%	66%	58%	66%	58%	65%	66%	73%	65%	62%	63%	63%	57%	73%	65%	67%
65.6%		61%	65%	77%	61%	68%	62%	58%	66%	50%	73%	77%	68%	49%	66%	79%	70%	72%	64%	61%	53%	78%
73.6%		64%	80%	77%	77%	33%	74%	90%	77%	79%	67%	77%	81%	71%	79%	67%	62%	68%	79%	77%	100%	67%
60.5%		52%	47%	61%	52%	61%	59%	52%	66%	50%	61%	82%	68%	50%	66%	79%	74%	62%	50%	68%	53%	57%
70.5%		73%	68%	71%	82%	100%	57%	68%	76%	69%	91%	70%	49%	77%	65%	78%	72%	63%	52%	56%	62%	82%
73.8%		82%	82%	78%	82%	35%	91%	82%	88%	82%	63%	78%	82%	52%	82%	63%	63%	63%	52%	91%	82%	77%
77.4%		86%	82%	73%	68%	67%	79%	71%	87%	87%	68%	76%	69%	65%	90%	82%	76%	86%	80%	76%	76%	81%
75.5%		72%	70%	73%	78%	86%	70%	82%	86%	86%	77%	68%	68%	77%	78%	70%	72%	71%	81%	72%	71%	77%
64.9%		66%	65%	66%	69%	66%	61%	66%	66%	59%	77%	68%	62%	66%	62%	65%	68%	65%	61%	66%	56%	63%
69.3%		70%	65%	72%	76%	65%	55%	72%	72%	69%	72%	78%	56%	72%	60%	74%	76%	65%	70%	72%	78%	66%
48.2%		55%	57%	51%	62%	55%	30%	55%	52%	46%	42%	44%	38%	50%	38%	50%	49%	50%	51%	40%	50%	48%
90.8%		90%	86%	81%	86%	94%	94%	100%	95%	90%	100%	95%	100%	90%	90%	81%	77%	86%	88%	94%	90%	100%
61.3%		77%	70%	77%	77%	0%	66%	58%	58%	63%	65%	67%	58%	65%	63%	66%	72%	63%	53%	58%	63%	49%
61.1%		69%	69%	69%	70%	66%	64%	68%	57%	58%	74%	63%	64%	64%	57%	54%	59%	53%	32%	57%	61%	56%
72.0%		75%	76%	82%	89%	71%	70%	76%	76%	75%	68%	71%	76%	76%	60%	74%	74%	61%	65%	46%	80%	70%
54.9%		66%	48%	57%	77%	37%	33%	40%	65%	65%	57%	42%	34%	65%	34%	61%	61%	66%	65%	37%	65%	77%
69.8%		77%	70%	77%	77%	81%	75%	68%	70%	73%	77%	71%	58%	73%	62%	75%	62%	60%	58%	68%	71%	62%
46.5%		56%	40%	42%	42%	74%	42%	42%	53%	51%	42%	38%	46%	42%	38%	51%	48%	46%	33%	42%	61%	48%
72.5%		75%	78%	75%	80%	75%	74%	79%	72%	76%	72%	74%	68%	72%	74%	77%	67%	68%	70%	74%	69%	54%
69.5%		81%	58%	58%	72%	67%	68%	71%	72%	77%	72%	78%	59%	77%	59%	77%	89%	78%	58%	54%	58%	77%
44.3%		43%	29%	48%	40%	67%	29%	50%	50%	40%	57%	30%	27%	50%	57%	63%	63%	34%	32%	30%	57%	35%
59.0%		58%	61%	53%	58%	58%	63%	58%	58%	56%	73%	58%	58%	58%	57%	63%	66%	51%	57%	58%	58%	58%
46.5%		54%	49%	41%	48%	77%	39%	44%	42%	53%	58%	49%	34%	54%	34%	56%	48%	36%	37%	34%	36%	54%
54.7%		55%	58%	60%	60%	16%	62%	64%	61%	48%	54%	58%	61%	52%	61%	52%	57%	52%	46%	64%	49%	58%
70.9%		59%	76%	80%	80%	40%	76%	79%	81%	53%	63%	55%	77%	67%	80%	79%	63%	79%	79%	77%	75%	71%
66.7%		69%	69%	76%	70%	70%	53%	63%	65%	57%	77%	65%	66%	66%	67%	73%	65%	65%	59%	68%	63%	74%
88.1%		81%	95%	88%	93%	88%	86%	88%	93%	91%	88%	95%	76%	100%	91%	90%	90%	76%	60%	93%	100%	88%
88.4%		89%	93%	100%	85%	49%	89%	82%	93%	86%	77%	100%	93%	100%	93%	85%	94%	88%	72%	100%	89%	100%
51.1%		63%	49%	63%	63%	28%	56%	49%	40%	49%	63%	58%	48%	54%	45%	62%	53%	54%	32%	49%	38%	58%
64.8%		59%	63%	58%	67%	74%	76%	65%	64%	63%	77%	72%	44%	74%	59%	62%	68%	57%	61%	63%	61%	74%
63.0%		63%	63%	61%	68%	63%	56%	67%	66%	68%	61%	68%	56%	68%	58%	68%	72%	66%	69%	62%	28%	72%
65.1%		81%	64%	57%	58%	68%	61%	70%	62%	63%	60%	71%	60%	63%	63%	71%	63%	58%	67%	72%	67%	68%
58.3%		52%	57%	51%	51%	58%	51%	46%	56%	62%	49%	70%	72%	46%	60%	73%	64%	58%	61%	64%	56%	68%
88.5%		90%	94%	87%	90%	81%	95%	90%	81%	90%	81%	87%	90%	90%	87%	100%	94%	85%	82%	95%	90%	80%
56.7%		56%	60%	56%	56%	35%	59%	59%	53%	40%	72%	52%	61%	72%	59%	62%	58%	65%	44%	55%	53%	63%
72.4%		86%	81%	80%	86%	56%	84%	82%	65%	59%	64%	83%	69%	86%	79%	62%	71%	72%	64%	72%	50%	70%
77.0%		82%	82%	82%	82%	69%	74%	73%	72%	73%	100%	82%	73%	91%	73%	79%	75%	49%	73%	73%	73%	87%
47.4%		45%	42%	51%	50%	53%	32%	37%	40%	48%	51%	45%	34%	58%	47%	58%	51%	64%	47%	34%	54%	54%
65.3%		60%	67%	63%	60%	72%	71%	71%	63%	65%	63%	63%	65%	63%	65%	64%	67%	72%	73%	65%	79%	41%
62.6%		64%	68%	68%	68%	34%	79%	71%	56%	58%	62%	72%	66%	62%	66%	58%	68%	53%	49%	66%	73%	54%
53.2%		54%	57%	61%	53%	28%	61%	57%	60%	61%	43%	49%	50%	61%	58%	49%	55%	50%	49%	58%	50%	53%
56.0%		57%	55%	61%	55%	58%	50%	58%	56%	50%	58%	55%	50%	55%	55%	54%	50%	61%	63%	52%	55%	67%
80.0%		84%	87%	84%	77%	49%	82%	84%	83%	79%	66%	84%	83%	84%	83%	84%	84%	83%	72%	84%	84%	79%
66.6%		68%	80%	68%	63%	68%	66%	71%	65%	56%	64%	71%	60%	64%	66%	71%	64%	65%	64%	64%	70%	70%
82.5%		88%	85%	85%	88%	79%	78%	88%	85%	86%	81%	85%	81%	81%	88%	82%	85%	81%	69%	78%	88%	71%
67.9%		68%	77%	87%	86%	74%	77%	74%	63%	66%	78%	80%	56%	73%	74%	61%	58%	57%	54%	63%	50%	50%
77.4%		83%	83%	83%	88%	61%	75%	80%	79%	71%	88%	78%	73%	84%	78%	75%	76%	71%	67%	67%	81%	84%
73.5%		82%	76%	75%	82%	69%	73%	67%	77%	74%	73%	77%	67%	63%	77%	69%	70%	82%	74%	63%	77%	77%
52.2%		53%	58%	56%	53%	40%	51%	51%	56%	53%	49%	54%	46%	56%	51%	54%	54%	51%	51%	51%	59%	50%
63.5%		72%	71%	68%	70%	44%	68%	63%	63%	58%	55%	68%	60%	68%	63%	60%	64%	60%	65%	68%	64%	62%
63.2%		61%	63%	64%	65%	67%	68%	74%	58%	59%	58%	63%	56%	58%	65%	56%	66%	62%	52%	63%	72%	78%
48.6%		40%	55%	62%	49%	51%	62%	52%	40%	48%	41%	52%	48%	48%	60%	42%	50%	33%	38%	48%	52%	49%
48.3%		55%	43%	57%	57%	76%	36%	49%	59%	50%	55%	43%	24%	55%	31%	54%	45%	48%	24%	49%	55%	49%
72.5%		73%	84%	77%	73%	77%	70%	67%	75%	66%	77%	77%	74%	66%	66%	70%	70%	74%	70%	77%	66%	73%
68.3%		66%	70%	65%	77%	86%	62%	68%	61%	62%	77%	70%	70%	77%	70%	66%	66%	69%	62%	60%	67%	63%
46.3%		45%	45%	56%	55%	37%	26%	41%	43%	39%	52%	63%	39%	41%	30%	58%	51%	32%	70%	41%	45%	63%
63.1%		76%	65%	58%	82%	37%	71%	50%	54%	66%	57%	57%	71%	82%	65%	56%	73%	53%	71%	66%	58%	57%
67.1%		65%	64%	70%	82%	74%	65%	68%	57%	65%	90%	71%	65%	65%	62%	64%	66%	62%	59%	58%	63%	74%
43.1%		47%	48%	51%	42%	31%	58%	51%	45%	45%	29%	39%	50%	51%	38%	40%	39%	38%	37%	47%	38%	41%
59.0%		61%	61%	66%	66%	37%	54%	66%	49%	49%	73%	65%	62%	66%	53%	60%	61%	51%	62%	66%	49%	61%
59.5%		59%	59%	58%	61%	60%	59%	61%	61%	64%	61%	54%	57%	54%	64%	68%	59%	54%	59%	59%	58%	61%
74.4%		81%	81%	78%	81%	44%	83%	81%	73%	69%	74%	74%	77%	74%	77%	71%	74%	75%	75%	73%	73%	74%
65.2%		71%	65%	65%	76%	62%	37%	72%	55%	58%	76%	70%	54%	76%	55%	77%	71%	55%	77%	54%	66%	77%
59.5%		58%	64%	58%	60%	53%	49%	53%	43%	52%	72%	77%	52%	68%	61%	58%	58%	55%	45%	59%	71%	83%
69.5%		87%	65%	74%	100%	37%	64%	57%	65%	76%	87%	59%	45%	73%	54%	73%	68%	81%	79%	60%	69%	86%
58.3%		56%	53%	63%	63%	70%	54%	50%	56%	59%	56%	56%	63%	56%	61%	60%	52%	58%	60%	59%	63%	57%
72.3%		77%	69%	65%	77%	77%	75%	75%	70%	66%	66%	75%	91%	66%	70%	77%	77%	56%	60%	82%	71%	77%
81.3%		81%	80%	81%	69%	80%	67%	80%	82%	86%	81%	86%	86%	89%	81%	72%	83%	87%	89%	81%	89%	78%
61.2%		69%	69%	66%	74%	51%	58%	69%	61%	61%	73%	59%	61%	64%	59%	58%	56%	58%	54%	43%	58%	64%
63.7%		74%	75%	54%	61%	73%	59%	68%	54%	74%	73%	67%	54%	73%	54%	67%	68%	67%	54%	49%	68%	52%
65.1%		77%	58%	65%	65%	77%	56%	59%	76%	70%	77%	74%	48%	77%	59%	67%	70%	50%	60%	48%	57%	77%
43.9%		51%	36%	42%	58%	59%	22%	36%	40%	51%	58%	44%	36%	58%	37%	59%	54%	44%	48%	36%	30%	22%
45.0%		42%	43%	43%	43%	58%	58%	41%	47%	43%	51%	41%	35%	55%	56%	42%	44%	34%	44%	40%	51%	35%
71.9%		72%	69%	73%	82%	82%	79%	62%	65%	65%	100%	68%	69%	72%	63%	78%	74%	58%	70%	68%	68%	72%
69.2%		68%	63%	74%	71%	74%	70%	74%	68%	60%	70%	67%	59%	74%	70%	68%	74%	66%	57%	67%	88%	71%
62.1%		61%	60%	64%	55%	53%	67%	66%	61%	61%	73%	69%	64%	68%	68%	64%	62%	59%	53%	62%	53%	61%
80.2%		100%	70%	71%	71%	73%	76%	88%	88%	100%	88%	71%	67%	80%	84%	88%	86%	83%	76%	71%		73%
68.9%		70%	76%	70%	69%	55%	74%	71%	70%	72%	58%	66%	68%	70%	68%	73%	72%	68%	68%	73%	66%	70%
65.6%		65%	61%	65%	65%	73%	67%	65%	50%	65%	78%	68%	41%	60%	70%	67%	68%	71%	72%	45%	73%	88%
45.2%		49%	37%	49%	37%	57%	48%	49%	35%	43%	31%	49%	49%	49%	37%	46%	44%	40%	57%	49%	53%	42%

Model Similarity Dendrogram

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