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 79939ab...

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

Efficiency & Succinctness

AI Safety & Robustness

Social interaction

Best Models (Coverage)

1.GPT 5.1
74.9%
2.Claude 3.7 Sonnet
74.6%
3.Claude Sonnet 4
74.0%
4.GPT 5
73.4%
5.Claude Haiku 4.5
73.3%

🔀 Least Similar Models

Gemini 2.5 FlashvsGPT OSS 20b

76.7% similarity

👯 Most Similar Models

Mistral Medium 3vsGPT 4o

91.3% 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 74.6%	5th 73.3%	3rd 74.0%	11th 72.4%	21st 65.6%	17th 68.3%	9th 72.9%	6th 73.2%	8th 73.1%	7th 73.1%	12th 71.2%	18th 68.3%	10th 72.9%	15th 69.5%	4th 73.4%	1st 74.9%	16th 69.0%	20th 66.0%	19th 67.9%	13th 70.7%	14th 69.9%
60.0%		77%	66%	69%	77%	64%	44%	56%	69%	61%	59%	51%	66%	65%	47%	65%	58%	57%	76%	57%	37%	39%
75.9%		88%	77%	78%	83%	79%	52%	60%	73%	87%	78%	71%	66%	85%	78%	84%	88%	72%	77%	69%	78%	71%
76.4%		82%	72%	81%	78%	67%	78%	78%	75%	75%	92%	82%	64%	83%	71%	72%	81%	82%	67%	71%		77%
87.7%		85%	94%	87%	82%	85%	90%	90%	91%	86%	90%	92%	89%	92%	93%	88%	86%	90%	80%	87%	84%	81%
57.3%		72%	62%	63%	63%	52%	50%	56%	59%	62%	59%	63%	50%	60%	53%	65%	61%	48%	38%	48%	52%	68%
70.7%		85%	65%	79%	79%	58%	65%	69%	74%	72%	78%	66%	53%	83%	73%	77%	77%	58%	77%	69%	66%	61%
75.4%		79%	79%	81%	89%	72%	70%	81%	79%	76%	65%	71%	72%	68%	65%	89%	81%	67%	71%	76%	75%	78%
74.1%		74%	80%	78%	71%	34%	71%	80%	85%	73%	74%	79%	77%	83%	82%	90%	79%	76%	76%	73%	68%	54%
67.4%		69%	79%	63%	58%	39%	78%	74%	63%	75%	72%	73%	77%	67%	70%	33%	74%	78%	75%	56%	75%	68%
74.4%		77%	85%	81%	81%	17%	76%	84%	88%	73%	83%	84%	77%	81%	66%	71%	81%	86%	78%	62%	82%	50%
80.7%		88%	86%	91%	79%	53%	85%	82%	87%	78%	88%	86%	82%	82%	78%	84%	84%	70%	76%	88%	68%	79%
71.9%		73%	73%	71%	76%	84%	66%	72%	60%	72%	77%	70%	63%	77%	67%	71%	80%	70%	71%	63%	70%	84%
82.5%		88%	88%	92%	81%	70%	86%	84%	84%	76%	81%	84%	89%	88%	88%	85%	87%	84%	68%	82%	86%	61%
50.3%		63%	65%	65%	63%	44%	41%	58%	41%	58%	43%	54%	46%	45%	44%	55%	67%	33%	37%	39%	62%	34%
60.7%		66%	64%	56%	63%	35%	58%	66%	71%	75%	58%	63%	53%	74%	49%	84%	67%	66%	58%	53%	32%	63%
63.1%		65%	67%	58%	63%	72%	52%	63%	63%	77%	70%	63%	47%	67%	64%	74%	73%	62%	66%	44%	53%	63%
63.3%		64%	70%	64%	70%	70%	56%	59%	78%	64%	64%	68%	66%	63%	58%	57%	57%	58%	63%	61%	56%	64%
72.8%		77%	72%	68%	77%	70%	79%	68%	73%	71%	71%	69%	65%	71%	72%	81%	74%	70%	69%	77%	74%	80%
86.6%		89%	85%	90%	77%	93%	92%	83%	82%	87%	90%	80%	89%	94%	86%	86%	87%	86%	85%	86%	92%	80%
66.0%		62%	62%	66%	68%	75%	66%	70%	58%	67%	66%	55%	61%	74%	75%	69%	63%	64%	70%	62%		67%
76.9%		81%	83%	81%	81%	77%	83%	81%	76%	79%	74%	82%	59%	83%	68%	81%	79%	67%	72%	76%	75%	76%
85.0%		87%	80%	91%	90%	47%	94%	83%	90%	90%	87%	93%	90%	72%	85%	84%	87%	88%	93%	85%	79%	90%
67.9%		64%	74%	70%	63%	41%	74%	70%	74%	75%	66%	69%	69%	70%	75%	60%	68%	72%	76%	52%	76%	68%
44.7%		50%	46%	45%	42%	59%	23%	45%	41%	53%	54%	33%	33%	51%	39%	54%	58%	51%	23%	24%	54%	61%
70.0%		80%	69%	63%	77%	74%	74%	75%	74%	69%	76%	69%	58%	82%	70%	77%	80%	62%	39%	54%	69%	78%
78.8%		79%	81%	84%	88%	79%	79%	76%	72%	79%	76%	79%	79%	79%	79%	79%	89%	67%	81%	79%	79%	72%
71.9%		74%	72%	74%	74%	81%	69%	78%	70%	68%	74%	67%	65%	74%	64%	78%	83%	66%	62%	76%	65%	76%
71.2%		80%	64%	70%	87%	70%	49%	74%	86%	82%	66%	58%	74%	79%	64%	77%	79%	83%	83%	50%	47%	74%
68.0%		75%	74%	69%	75%	70%	72%	64%	66%	67%	74%	67%	71%	74%	58%	69%	68%	60%	54%	59%	69%	72%
70.5%		72%	67%	74%	75%	72%	68%	71%	70%	69%	66%	72%	71%	79%	67%	74%	75%	68%	70%	72%	69%	60%
80.2%		78%	82%	92%	74%	45%	89%	94%	80%	84%	91%	77%	67%	92%	85%	81%	87%	62%	64%	87%		94%
78.9%		67%	90%	81%	87%	78%	62%	86%	78%	86%	78%	76%	75%	76%	77%	86%	87%	68%	92%	76%	76%	74%
63.4%		72%	63%	61%	68%	71%	51%	65%	70%	60%	73%	63%	70%	55%	50%	73%	68%	69%	63%	39%	69%	59%
71.5%		77%	61%	68%	75%	88%	62%	73%	68%	82%	79%	72%	51%	79%	64%	76%	79%	72%	75%	51%	76%	73%
58.3%		58%	74%	78%	53%	41%	59%	70%	66%	66%	49%	54%	54%	58%	74%	59%	48%	41%	48%	70%	66%	39%
80.2%		73%	94%	84%	64%	40%	85%	94%	91%	81%	76%	86%	83%	84%	76%	73%	76%	86%	88%	85%	83%	82%
78.0%		84%	83%	79%	79%	79%	76%	74%	85%	83%	72%	73%	76%	72%	87%	85%	80%	77%	66%	83%	75%	71%
66.0%		70%	67%	67%	61%	68%	79%	61%	76%	10%	77%	73%	65%	61%	83%	72%	79%	57%	61%	66%	58%	74%
67.4%		59%	72%	71%	58%	63%	73%	70%	69%	61%	68%	73%	72%	61%	71%	64%	60%	72%	66%	73%	70%	70%
61.0%		67%	51%	56%	54%	58%	76%	54%	76%	57%	64%	60%	80%	50%	72%	83%	80%	53%	44%	61%	43%	42%
68.3%		70%	69%	68%	74%	63%	50%	68%	68%	71%	77%	74%	53%	70%	68%	77%	74%	71%	70%	51%	71%	78%
71.6%		79%	79%	79%	73%	52%	87%	81%	79%	73%	68%	64%	88%	61%	79%	70%	74%	58%	49%	82%	83%	46%
73.6%		92%	74%	78%	78%	70%	65%	65%	67%	78%	76%	63%	75%	69%	58%	84%	88%	78%	70%	58%	86%	73%
71.3%		69%	67%	62%	66%	71%	66%	77%	80%	72%	76%	64%	74%	76%	75%	70%	61%	79%	78%	66%		78%
81.4%		89%	87%	83%	87%	80%	65%	75%	80%	83%	75%	80%	86%	91%	85%	84%	74%	86%	83%	72%	86%	78%
76.8%		89%	69%	80%	85%	75%	67%	85%	81%	78%	80%	70%	73%	84%	72%	81%	81%	84%	58%	81%	73%	67%
55.8%		57%	62%	56%	56%	55%	58%	49%	62%	56%	56%	54%	66%	55%	55%	57%	51%	44%	51%	55%	51%	66%
86.4%		81%	85%	73%	69%	90%	92%	85%	100%	95%	85%	85%	100%	85%	83%	73%	81%	77%	97%	100%	85%	94%
78.1%		87%	79%	84%	81%	43%	87%	89%	85%	78%	66%	84%	84%	76%	78%	76%	75%	76%	63%	78%	87%	85%
69.5%		69%	70%	73%	79%	60%	72%	76%	72%	75%	76%	63%	64%	70%	70%	69%	79%	68%	61%	69%	63%	62%
63.6%		58%	64%	67%	73%	57%	69%	68%	65%	65%	66%	62%	76%	66%	61%	61%	66%	58%	57%	54%	67%	56%
62.4%		71%	57%	56%	57%	53%	52%	62%	45%	71%	71%	57%	54%	75%	48%	76%	74%	71%	71%	39%	73%	77%
71.8%		80%	73%	78%	89%	81%	72%	74%	77%	78%	73%	70%	65%	78%	40%	82%	81%	61%	54%	78%	68%	56%
52.5%		63%	52%	45%	50%	76%	34%	50%	47%	57%	61%	45%	45%	57%	42%	63%	69%	56%	44%	41%	50%	56%
76.0%		75%	69%	83%	80%	82%	82%	79%	76%	73%	83%	75%	74%	76%	77%	77%	77%	57%	68%	81%	75%	76%
74.6%		87%	69%	78%	84%	67%	69%	67%	74%	75%	71%	65%	65%	74%	65%	85%	85%	83%	84%	79%	65%	76%
53.1%		63%	39%	52%	45%	56%	35%	58%	58%	64%	66%	58%	27%	56%	54%	83%	82%	41%	40%	38%	54%	46%
81.0%		78%	79%	83%	72%	76%	88%	83%	76%	73%	79%	85%	85%	84%	84%	79%	76%	82%	86%	83%	79%	90%
56.1%		60%	58%	53%	67%	81%	45%	55%	58%	69%	74%	54%	39%	55%	48%	65%	67%	45%	32%	37%	49%	67%
78.9%		75%	78%	83%	75%	66%	84%	76%	84%	76%	75%	79%	84%	83%	87%	76%	82%	70%	66%	92%	84%	82%
76.5%		83%	81%	85%	83%	52%	71%	80%	82%	75%	74%	76%	71%	73%	67%	84%	72%	82%	67%	84%	80%	84%
62.7%		64%	63%	67%	67%	63%	58%	59%	63%	63%	68%	66%	63%	66%	64%	62%	63%	65%	58%	64%	66%	44%
82.8%		87%	78%	83%	79%	92%	92%	92%	94%	94%	94%	79%	79%	92%	74%	79%	79%	68%	54%	79%	78%	92%
77.3%		77%	82%	79%	71%	51%	74%	76%	83%	79%	77%	76%	79%	90%	82%	78%	83%	67%	74%	86%		81%
72.4%		68%	82%	75%	59%	43%	73%	80%	82%	75%	76%	76%	73%	75%	81%	68%	70%	77%	69%	64%	78%	77%
72.0%		78%	74%	66%	71%	81%	58%	80%	76%	80%	78%	71%	53%	75%	60%	83%	93%	75%	35%	65%	73%	88%
54.0%		67%	59%	61%	64%	56%	49%	64%	61%	59%	55%	51%	47%	55%	42%	66%	61%	49%	36%	41%	56%	35%
65.9%		72%	75%	76%	67%	62%	70%	66%	58%	65%	63%	68%	55%	66%	63%	68%	66%	59%	63%	65%	68%	69%
64.5%		63%	68%	67%	67%	63%	57%	56%	56%	70%	71%	68%	54%	54%	64%	67%	67%	71%	67%	59%	63%	83%
85.0%		94%	87%	87%	90%	82%	86%	87%	87%	81%	78%	89%	87%	78%	87%	87%	86%	87%	87%	89%	81%	69%
64.3%		55%	58%	62%	65%	46%	64%	71%	59%	64%	67%	77%	66%	70%	75%	64%	66%	68%	58%	72%	57%	66%
76.6%		78%	79%	83%	87%	35%	82%	79%	77%	71%	73%	79%	75%	78%	76%	79%	83%	81%	78%	75%	79%	81%
85.3%		83%	94%	86%	89%	69%	82%	76%	95%	94%	86%	81%	76%	86%	81%	92%	83%	86%	92%	86%	90%	84%
69.5%		63%	67%	73%	69%	84%	48%	68%	82%	87%	83%	58%	37%	73%	72%	79%	76%	73%	68%	44%	78%	77%
72.2%		76%	73%	78%	65%	44%	79%	79%	70%	63%	70%	80%	73%	76%	76%	74%	78%	71%	74%	74%	71%	73%
78.5%		90%	77%	88%	80%	59%	94%	90%	82%	73%	65%	92%	83%	82%	82%	68%	74%	75%	57%	84%	86%	68%
77.0%		79%	81%	83%	83%	62%	76%	80%	84%	77%	79%	72%	73%	81%	75%	78%	79%	72%	73%	85%	74%	72%
77.6%		77%	80%	78%	82%	71%	72%	73%	82%	82%	83%	80%	84%	74%	82%	78%	85%	87%	55%	86%	83%	55%
67.2%		79%	75%	70%	62%	29%	71%	69%	72%	65%	62%	65%	72%	69%	69%	64%	65%	72%	72%	70%	69%	71%
64.2%		70%	69%	70%	65%	68%	68%	68%	62%	66%	63%	67%	59%	63%	73%	70%	55%	59%	61%	65%	55%	53%
79.5%		80%	78%	82%	75%	76%	71%	82%	84%	86%	81%	78%	78%	81%	73%	73%	84%	86%	70%	82%	86%	84%
76.0%		70%	79%	80%	80%	77%	88%	76%	77%	74%	72%	84%	74%	78%	83%	82%	82%	65%	60%	84%	65%	65%
58.3%		67%	61%	66%	64%	49%	47%	64%	67%	59%	69%	59%	44%	59%	50%	67%	65%	55%	49%	49%	58%	57%
75.6%		72%	88%	74%	74%	76%	72%	71%	76%	75%	81%	81%	84%	70%	74%	81%	75%	75%	61%	75%	76%	76%
73.8%		72%	81%	81%	69%	73%	76%	73%	74%	73%	77%	73%	66%	75%	70%	80%	69%	67%	75%	73%	75%	77%
80.3%		86%	81%	87%	76%	81%	78%	78%	83%	78%	84%	78%	78%	83%	76%	85%	84%	78%	70%	79%	79%	84%
60.1%		69%	62%	65%	62%	54%	58%	58%	56%	64%	59%	65%	64%	60%	64%	62%	59%	54%	46%	64%	57%	60%
61.3%		56%	68%	62%	57%	70%	65%	59%	56%	58%	61%	61%	67%	62%	76%	55%	67%	72%	66%	63%	55%	31%
69.6%		79%	71%	76%	76%	83%	50%	68%	71%	75%	68%	68%	76%	68%	63%	76%	74%	64%	40%	73%	68%	75%
75.4%		91%	86%	82%	75%	71%	87%	95%	88%	91%	88%	86%	44%	83%	90%	48%	49%	61%	57%	82%	70%	59%
67.4%		86%	68%	63%	73%	78%	51%	72%	60%	72%	60%	57%	75%	67%	65%	60%	73%	70%	76%	66%	63%	60%
61.4%		60%	54%	79%	67%	69%	26%	77%	57%	53%	63%	81%	26%	67%	39%	68%	73%	69%	70%	44%	66%	82%
65.4%		78%	70%	78%	80%	32%	77%	51%	70%	66%	61%	61%	67%	61%	62%	72%	67%	64%	65%	65%	60%	67%
75.6%		70%	78%	79%	74%	84%	87%	79%	69%	79%	73%	78%	79%	79%	82%	74%	72%	76%	62%	77%	79%	57%
53.6%		52%	57%	60%	55%	51%	61%	60%	58%	56%	59%	51%	52%	52%	51%	47%	58%	50%	50%	58%	41%	47%
80.1%		77%	83%	82%	82%	82%	73%	85%	76%	79%	83%	79%	77%	81%	77%	86%	86%	83%	77%	78%	77%	80%
76.3%		81%	86%	85%	86%	49%	81%	82%	86%	77%	77%	81%	70%	82%	86%	86%	75%	55%	48%	79%	87%	64%
83.1%		91%	91%	91%	91%	65%	76%	71%	85%	87%	81%	90%	88%	93%	71%	82%	87%	81%	79%	77%	87%	82%
77.9%		88%	88%	78%	78%	82%	51%	80%	65%	84%	83%	68%	65%	85%	76%	88%	91%	81%	79%	64%	78%	84%
80.9%		81%	86%	80%	69%	86%	74%	75%	80%	75%	82%	87%	68%	93%	76%	77%	89%	72%	88%	76%	94%	90%
62.0%		70%	58%	60%	63%	39%	50%	65%	68%	68%	73%	51%	49%	59%	50%	73%	74%	76%	67%	42%	72%	76%
87.1%		85%	82%	82%	82%	80%	89%	82%	92%	91%	83%	78%	93%	82%	91%	86%	93%	92%	93%	83%	100%	91%
81.3%		89%	87%	87%	86%	93%	81%	81%	95%	87%	73%	79%	87%	62%	67%	74%	79%	81%	64%	86%	87%	82%
73.3%		68%	83%	70%	68%	77%	53%	68%	68%	77%	83%	70%	74%	68%	68%	81%	73%	77%	89%	72%	74%	78%
81.5%		83%	81%	81%	87%	79%	72%	83%	79%	89%	84%	74%	87%	84%	83%	87%	87%	82%	76%	76%	71%	87%
65.3%		69%	71%	81%	71%	52%	51%	77%	62%	65%	65%	73%	75%	62%	59%	75%	66%	48%	45%	54%	75%	76%
64.9%		78%	70%	75%	72%	60%	63%	71%	74%	75%	51%	78%	57%	50%	64%	71%	74%	60%	74%	50%	62%	34%
58.2%		67%	52%	59%	59%	82%	22%	55%	50%	61%	70%	48%	46%	67%	61%	64%	69%	60%	64%	41%	63%	62%
70.2%		72%	66%	69%	69%	74%	69%	73%	72%	71%	78%	69%	57%	71%	57%	82%	72%	76%	63%	71%	74%	69%
67.4%		80%	78%	68%	73%	80%	62%	68%	62%	77%	85%	64%	49%	67%	50%	75%	79%	58%	53%	46%	74%	68%
85.6%		81%	85%	90%	89%	87%	85%	100%	90%	85%	89%	89%	92%	84%	85%	91%	88%	84%	64%	94%	81%	65%
67.2%		61%	70%	67%	55%	63%	67%	76%	77%	67%	76%	76%	64%	67%	74%	64%	60%	61%	72%	60%	62%	72%
76.8%		76%	73%	84%	80%	79%	67%	76%	79%	83%	83%	83%	79%	84%	68%	80%	83%	64%	75%	65%	73%	79%
72.8%		70%	78%	76%	60%	38%	78%	78%	77%	72%	70%	78%	79%	78%	74%	63%	72%	74%	82%	74%	80%	77%
76.0%		78%	78%	71%	65%	84%	96%	81%	75%	81%	78%	81%	83%	80%	88%	0%	84%	74%	63%	78%	93%	86%
57.4%		57%	57%	62%	54%	57%	57%	60%	60%	59%	60%	57%	57%	57%	62%	59%	60%	54%	42%	63%	48%	64%

Model Similarity Dendrogram

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