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 Religion%3Aislam C5 - Run df1c323...

Global Dialogues GD4 - Islam (5 context Qs)

DTEF: Predict response distributions for Islam. 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

Social interaction

Best Models (Coverage)

1.Claude Sonnet 4
81.8%
2.Claude Sonnet 4.5
81.4%
3.Claude Haiku 4.5
81.4%
4.GPT 4.1
81.3%
5.GPT 4.1 Mini
80.9%

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 81.4%	1st 81.8%	2nd 81.4%	11th 76.4%	12th 74.5%	7th 80.1%	6th 80.1%	4th 81.3%	5th 80.9%	13th 73.2%	8th 78.6%	9th 77.6%	10th 77.3%
66.4%		68%	77%	86%	82%	50%	62%	64%	66%	62%	49%	60%	70%	67%
73.3%		73%	77%	79%	91%	49%	65%	80%	87%	80%	64%	71%	64%	73%
78.8%		77%	83%	76%	56%	82%	83%	80%	81%	87%	79%	79%	75%	87%
84.5%		90%	92%	92%	69%	92%	86%	74%	87%	86%	87%	76%	77%	90%
70.5%		72%	80%	71%	75%	53%	77%	73%	69%	71%	67%	68%	64%	76%
82.5%		86%	80%	92%	92%	76%	82%	85%	92%	88%	66%	96%	88%	50%
69.8%		91%	79%	84%	87%	64%	69%	65%	61%	65%	59%	63%	60%	60%
75.3%		80%	67%	63%	61%	73%	81%	81%	70%	81%	81%	81%	83%	77%
83.8%		90%	64%	65%	79%	92%	96%	84%	74%	93%	81%	92%	85%	94%
85.3%		81%	91%	85%	94%	88%	79%	70%	78%	95%	95%	87%	88%	78%
85.2%		88%	84%	91%	88%	81%	85%	85%	86%	76%	88%	85%	85%	86%
85.0%		94%	88%	91%	72%	88%	79%	85%	91%	91%	71%	91%	81%	83%
84.8%		90%	88%	89%	88%	85%	79%	87%	81%	81%	84%	87%	78%	85%
64.5%		69%	86%	72%	66%	55%	67%	63%	68%	66%	35%	54%	69%	69%
71.2%		63%	79%	73%	36%	71%	77%	74%	74%	79%	76%	73%	74%	77%
74.8%		74%	70%	87%	93%	58%	84%	76%	91%	80%	62%	69%	61%	67%
80.4%		82%	79%	79%	80%	85%	80%	87%	80%	85%	69%	82%	75%	82%
81.4%		87%	81%	77%	80%	84%	84%	76%	71%	89%	73%	86%	87%	83%
83.5%		86%	89%	79%	82%	88%	82%	81%	79%	88%	75%	87%	78%	91%
74.9%		82%	75%	79%	71%	63%	72%	72%	82%	72%	74%	84%	76%	72%
79.9%		86%	81%	76%	78%	75%	86%	74%	67%	88%	73%	84%	86%	85%
85.0%		96%	86%	85%	83%	86%	80%	85%	90%	81%	71%	80%	88%	94%
76.8%		81%	85%	92%	88%	76%	78%	87%	93%	74%	73%	83%	42%	47%
62.0%		67%	75%	75%	86%	40%	71%	69%	70%	58%	44%	42%	45%	64%
82.8%		82%	86%	88%	81%	80%	88%	81%	89%	81%	79%	76%	83%	82%
84.4%		85%	81%	83%	87%	84%	82%	82%	86%	86%	89%	83%	85%	84%
85.5%		83%	92%	87%	82%	85%	89%	82%	79%	92%	73%	91%	93%	84%
79.6%		80%	78%	91%	82%	50%	89%	93%	81%	78%	83%	80%	71%	79%
85.0%		87%	94%	95%	85%	73%	94%	82%	96%	82%	85%	82%	70%	80%
81.7%		81%	90%	81%	77%	68%	83%	74%	88%	88%	82%	78%	82%	90%
84.5%		91%	89%	86%	90%	82%	86%	88%	87%	86%	77%	87%	89%	61%
73.3%		77%	70%	73%	30%	69%	83%	83%	83%	78%	73%	77%	78%	79%
70.9%		75%	71%	83%	82%	58%	73%	86%	75%	68%	71%	57%	64%	59%
71.8%		71%	67%	69%	92%	56%	85%	80%	84%	79%	60%	63%	63%	64%
79.7%		82%	69%	80%	78%	79%	90%	78%	77%	81%	78%	79%	83%	82%
82.5%		89%	88%	83%	87%	79%	83%	88%	90%	84%	69%	84%	93%	56%
84.5%		88%	64%	86%	87%	82%	84%	87%	87%	76%	83%	85%	93%	96%
71.5%		60%	74%	68%	61%	82%	65%	56%	78%	60%	88%	78%	85%	74%
84.3%		90%	92%	88%	89%	78%	86%	88%	91%	85%	75%	91%	86%	57%
55.1%		41%	51%	55%	49%	71%	45%	49%	53%	53%	66%	64%	67%	52%
79.9%		87%	87%	91%	61%	65%	93%	94%	93%	87%	62%	67%	64%	88%
84.9%		94%	95%	95%	78%	90%	82%	82%	76%	90%	82%	72%	80%	88%
70.1%		84%	69%	69%	69%	71%	76%	67%	77%	63%	77%	63%	64%	62%
69.6%		58%	71%	73%	65%	67%	82%	79%	65%	65%	81%	68%	68%	63%
86.2%		89%	87%	91%	79%	84%	87%	80%	90%	88%	90%	81%	84%	90%
83.7%		82%	83%	90%	93%	70%	90%	91%	90%	84%	68%	82%	83%	82%
81.5%		86%	85%	85%	87%	76%	82%	82%	77%	85%	83%	75%	82%	75%
88.2%		98%	90%	90%	85%	81%	91%	81%	98%	88%	81%	89%	94%	81%
87.8%		96%	90%	90%	83%	85%	81%	86%	92%	92%	79%	84%	93%	90%
87.2%		91%	90%	93%	87%	78%	95%	89%	89%	89%	83%	81%	79%	89%
87.9%		94%	94%	87%	94%	82%	88%	90%	94%	88%	88%	86%	73%	85%
64.8%		69%	67%	67%	30%	64%	71%	72%	78%	65%	61%	75%	60%	64%
74.8%		85%	82%	94%	86%	51%	70%	82%	68%	73%	57%	78%	80%	66%
60.6%		65%	64%	55%	91%	42%	65%	70%	62%	59%	54%	58%	53%	50%
85.8%		82%	97%	87%	82%	88%	86%	87%	88%	92%	74%	90%	92%	71%
84.8%		93%	90%	77%	75%	81%	88%	93%	83%	89%	72%	86%	88%	88%
53.4%		45%	70%	51%	85%	42%	63%	54%	50%	49%	41%	61%	37%	46%
85.1%		86%	88%	79%	76%	93%	84%	72%	80%	92%	81%	89%	92%	94%
66.8%		65%	74%	78%	83%	44%	72%	70%	83%	72%	57%	58%	47%	66%
75.8%		79%	82%	80%	44%	83%	81%	73%	70%	80%	74%	76%	86%	78%
85.3%		89%	85%	96%	38%	79%	90%	94%	97%	97%	87%	84%	85%	88%
74.4%		82%	86%	89%	85%	52%	70%	72%	78%	63%	79%	60%	74%	77%
89.5%		93%	93%	97%	87%	93%	92%	89%	97%	93%	76%	74%	89%	91%
83.9%		88%	87%	81%	83%	82%	82%	82%	87%	79%	88%	86%	83%	83%
73.5%		72%	83%	90%	39%	80%	75%	83%	90%	76%	59%	82%	85%	41%
82.3%		83%	83%	84%	71%	80%	87%	86%	89%	81%	76%	79%	82%	89%
78.4%		90%	81%	92%	80%	59%	93%	89%	81%	72%	82%	67%	56%	77%
83.9%		92%	87%	83%	85%	85%	77%	87%	81%	84%	76%	78%	88%	88%
73.3%		72%	72%	65%	74%	77%	69%	79%	75%	77%	72%	73%	75%	73%
79.8%		97%	78%	83%	92%	74%	66%	75%	78%	87%	61%	84%	80%	82%
82.7%		80%	86%	72%	85%	84%	83%	75%	84%	91%	75%	74%	90%	96%
86.3%		97%	95%	95%	67%	85%	89%	87%	92%	92%	75%	85%	82%	81%
85.0%		88%	91%	78%	60%	88%	85%	89%	81%	91%	91%	92%	90%	81%
69.6%		67%	88%	84%	92%	61%	10%	91%	84%	65%	60%	75%	56%	72%
79.5%		77%	86%	77%	72%	86%	85%	68%	77%	87%	85%	76%	82%	75%
83.2%		84%	88%	75%	58%	90%	88%	85%	65%	77%	93%	94%	90%	94%
85.5%		91%	92%	85%	87%	84%	84%	80%	87%	89%	76%	87%	92%	77%
83.8%		88%	91%	84%	89%	72%	85%	81%	84%	86%	73%	83%	79%	94%
89.1%		93%	89%	92%	89%	84%	85%	89%	91%	86%	92%	93%	90%	85%
82.2%		82%	90%	81%	78%	83%	83%	79%	84%	86%	65%	84%	87%	87%
90.3%		94%	85%	93%	95%	84%	89%	97%	93%	88%	92%	88%	87%	89%
83.1%		86%	88%	80%	82%	84%	82%	83%	87%	91%	64%	84%	85%	84%
78.5%		82%	93%	92%	66%	68%	82%	83%	86%	79%	76%	70%	67%	77%
89.5%		96%	81%	95%	89%	86%	85%	91%	97%	94%	85%	82%	89%	94%
77.5%		70%	76%	80%	75%	75%	87%	80%	78%	81%	80%	80%	75%	71%
83.5%		88%	84%	87%	86%	81%	83%	83%	84%	81%	84%	86%	84%	75%
74.2%		72%	88%	83%	73%	67%	75%	68%	62%	81%	58%	70%	84%	83%
69.9%		74%	72%	60%	56%	74%	68%	66%	64%	77%	70%	77%	75%	76%
78.8%		89%	91%	88%	83%	60%	82%	84%	79%	80%	44%	68%	87%	90%
83.6%		93%	99%	88%	77%	71%	80%	71%	92%	78%	78%	82%	98%	80%
70.8%		71%	68%	72%	81%	56%	74%	86%	63%	70%	70%	68%	72%	69%
68.9%		86%	77%	83%	40%	45%	91%	80%	88%	90%	52%	52%	56%	56%
68.3%		74%	73%	72%	37%	77%	58%	67%	84%	55%	64%	88%	69%	70%
85.0%		91%	88%	87%	81%	80%	88%	85%	82%	86%	84%	88%	75%	90%
59.0%		62%	68%	56%	57%	68%	62%	51%	66%	48%	49%	57%	61%	62%
83.7%		88%	88%	84%	74%	81%	83%	87%	88%	89%	81%	86%	90%	69%
78.1%		72%	75%	76%	76%	91%	62%	58%	73%	83%	94%	92%	88%	75%
86.8%		82%	88%	90%	62%	88%	96%	92%	80%	90%	91%	90%	86%	94%
78.9%		85%	88%	87%	83%	51%	87%	84%	91%	90%	44%	85%	65%	86%
80.2%		83%	81%	67%	87%	75%	76%	77%	91%	91%	68%	74%	86%	87%
71.7%		74%	83%	81%	31%	79%	68%	75%	86%	75%	63%	79%	64%	74%
83.8%		80%	87%	87%	95%	72%	85%	94%	74%	87%	68%	84%	91%	86%
86.3%		88%	86%	87%	94%	90%	82%	86%	82%	87%	94%	80%	79%	87%
75.8%		81%	75%	79%	79%	63%	71%	74%	86%	86%	61%	86%	71%	73%
84.2%		87%	83%	82%	90%	76%	88%	90%	83%	89%	82%	90%	77%	77%
80.8%		69%	69%	89%	75%	75%	92%	87%	97%	94%	63%	72%	75%	94%
76.7%		72%	70%	65%	74%	74%	81%	84%	58%	80%	77%	83%	91%	88%
63.7%		65%	65%	66%	80%	41%	72%	75%	81%	70%	34%	62%	54%	63%
73.8%		64%	65%	69%	92%	83%	86%	67%	69%	78%	59%	89%	73%	65%
75.8%		84%	74%	78%	70%	78%	84%	85%	84%	68%	73%	71%	69%	67%
89.3%		93%	91%	91%	85%	89%	78%	87%	92%	95%	88%	84%	94%	94%
79.8%		84%	83%	86%	92%	71%	77%	83%	86%	82%	75%	93%	63%	63%
84.7%		78%	89%	85%	87%	80%	89%	95%	87%	87%	89%	82%	78%	75%
82.6%		88%	88%	87%	39%	89%	88%	90%	81%	91%	80%	88%	89%	76%
84.2%		72%	76%	84%	92%	98%	89%	92%	88%	88%	74%	92%	77%	72%
74.0%		77%	78%	72%	70%	76%	74%	68%	75%	86%	65%	72%	75%	74%