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 Environment%3Asuburban C10 - Run ccf5043...

Global Dialogues GD4 - Suburban (10 context Qs)

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

TAGS:

Global Dialogues Gd4

Factual Accuracy & Hallucination

Instruction Following & Prompt Adherence

Social interaction

AI Safety & Robustness

Efficiency & Succinctness

Knowledge, learning and memory

Best Models (Coverage)

1.GPT 4.1
84.3%
2.Claude Sonnet 4.5
84.0%
3.Claude Sonnet 4
83.1%
4.Claude Haiku 4.5
82.8%
5.GPT 4.1 Mini
82.3%

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		4th 82.8%	3rd 83.1%	2nd 84.0%	6th 81.6%	12th 78.9%	8th 80.9%	7th 81.2%	1st 84.3%	5th 82.3%	13th 76.6%	9th 80.4%	11th 79.3%	10th 80.2%
71.2%		73%	79%	83%	71%	61%	64%	68%	68%	69%	73%	67%	79%	71%
64.5%		61%	66%	72%	83%	40%	55%	67%	87%	69%	60%	65%	58%	56%
83.4%		81%	84%	91%	96%	83%	88%	82%	82%	86%	80%	80%	76%	75%
81.5%		83%	85%	83%	77%	84%	81%	80%	86%	84%	79%	81%	75%	82%
65.6%		72%	74%	71%	70%	58%	67%	67%	67%	59%	56%	63%	60%	69%
79.3%		75%	79%	87%	90%	77%	78%	82%	90%	86%	58%	92%	80%	57%
70.3%		84%	77%	87%	73%	60%	71%	63%	64%	69%	73%	58%	65%	70%
80.2%		78%	72%	62%	80%	79%	80%	82%	82%	89%	88%	83%	87%	81%
84.8%		89%	79%	79%	78%	92%	92%	78%	97%	89%	78%	87%	83%	81%
73.8%		66%	69%	59%	44%	90%	78%	68%	69%	69%	88%	92%	84%	83%
82.9%		86%	79%	84%	86%	86%	78%	80%	87%	80%	76%	82%	83%	91%
87.5%		95%	91%	90%	89%	92%	78%	81%	88%	93%	71%	88%	89%	93%
81.8%		87%	81%	83%	81%	81%	74%	88%	83%	83%	86%	78%	84%	75%
68.4%		75%	76%	75%	68%	70%	72%	69%	66%	63%	52%	58%	70%	75%
74.7%		64%	77%	76%	52%	76%	69%	65%	87%	84%	83%	85%	74%	79%
79.3%		80%	86%	94%	86%	71%	84%	88%	91%	80%	65%	69%	65%	72%
85.9%		91%	84%	91%	93%	91%	87%	87%	86%	83%	74%	75%	84%	91%
89.5%		92%	87%	91%	93%	90%	88%	95%	93%	91%	81%	76%	89%	98%
84.6%		80%	80%	82%	85%	85%	80%	81%	84%	86%	92%	89%	87%	89%
75.8%		79%	72%	72%	73%	67%	80%	77%	78%	76%	81%	80%	78%	73%
86.0%		87%	88%	88%	86%	84%	91%	89%	93%	86%	73%	71%	89%	93%
88.7%		91%	91%	92%	90%	92%	80%	90%	93%	85%	84%	88%	86%	91%
74.2%		72%	82%	78%	91%	80%	76%	83%	87%	74%	61%	80%	52%	49%
71.1%		67%	85%	85%	88%	55%	74%	68%	76%	57%	73%	65%	54%	77%
85.5%		83%	85%	91%	87%	93%	90%	79%	94%	86%	77%	75%	82%	90%
90.8%		91%	93%	92%	92%	96%	84%	86%	87%	92%	92%	92%	92%	92%
86.6%		89%	92%	85%	92%	83%	93%	83%	93%	84%	82%	82%	84%	84%
77.6%		84%	79%	78%	82%	55%	78%	87%	86%	78%	81%	75%	73%	73%
84.5%		88%	92%	92%	87%	78%	91%	86%	91%	83%	70%	80%	76%	85%
85.5%		87%	91%	93%	88%	79%	81%	87%	89%	81%	83%	79%	84%	89%
83.3%		84%	90%	89%	85%	87%	83%	81%	96%	83%	65%	91%	88%	61%
83.9%		91%	76%	76%	74%	83%	80%	86%	88%	90%	88%	91%	91%	77%
72.0%		75%	73%	87%	92%	70%	70%	70%	79%	73%	62%	63%	66%	56%
70.5%		68%	77%	84%	87%	66%	74%	82%	75%	65%	59%	61%	54%	64%
81.2%		81%	82%	84%	82%	82%	84%	83%	74%	71%	83%	81%	84%	85%
77.5%		81%	78%	86%	85%	80%	76%	73%	90%	77%	66%	84%	69%	62%
85.2%		88%	80%	72%	70%	87%	85%	86%	90%	87%	89%	92%	92%	90%
84.5%		86%	86%	81%	86%	85%	78%	74%	83%	86%	87%	83%	93%	90%
84.0%		86%	87%	86%	87%	86%	86%	86%	89%	87%	70%	90%	91%	61%
77.8%		67%	77%	79%	77%	81%	68%	66%	75%	84%	93%	82%	77%	85%
87.0%		87%	91%	90%	86%	79%	91%	92%	92%	91%	73%	89%	79%	91%
84.5%		86%	85%	89%	81%	87%	86%	84%	75%	87%	90%	87%	80%	82%
74.3%		70%	66%	67%	70%	76%	79%	77%	81%	75%	78%	76%	75%	76%
78.3%		76%	89%	88%	79%	71%	82%	83%	86%	66%	82%	78%	76%	62%
86.2%		88%	91%	92%	79%	85%	86%	84%	90%	86%	85%	83%	84%	88%
83.5%		81%	86%	85%	87%	75%	94%	85%	87%	89%	72%	72%	86%	87%
81.9%		92%	89%	74%	87%	79%	87%	82%	81%	82%	73%	83%	79%	77%
88.0%		94%	93%	97%	79%	77%	87%	88%	98%	88%	77%	94%	88%	84%
88.0%		90%	89%	91%	86%	91%	81%	95%	84%	92%	89%	83%	79%	94%
89.2%		87%	90%	91%	91%	90%	89%	90%	89%	92%	86%	89%	85%	91%
87.8%		88%	93%	90%	88%	84%	89%	88%	90%	91%	82%	87%	83%	88%
70.6%		73%	83%	81%	28%	64%	80%	86%	73%	70%	71%	76%	65%	68%
77.5%		87%	78%	82%	89%	75%	63%	80%	78%	78%	68%	67%	85%	77%
70.2%		71%	72%	68%	94%	63%	71%	66%	71%	68%	69%	73%	64%	62%
83.9%		77%	87%	84%	72%	86%	79%	88%	89%	89%	81%	88%	93%	78%
85.8%		86%	90%	93%	88%	83%	83%	88%	96%	84%	82%	82%	79%	81%
63.3%		64%	72%	67%	70%	53%	65%	73%	84%	59%	45%	61%	49%	61%
89.4%		93%	88%	90%	93%	95%	84%	89%	90%	93%	84%	89%	88%	86%
68.4%		62%	73%	82%	96%	55%	72%	74%	78%	68%	54%	60%	56%	59%
81.1%		81%	84%	88%	84%	94%	79%	71%	76%	81%	87%	78%	75%	76%
81.9%		85%	91%	91%	49%	80%	92%	87%	84%	92%	69%	80%	80%	85%
74.1%		78%	77%	81%	75%	63%	70%	74%	80%	67%	77%	71%	78%	72%
89.1%		87%	93%	92%	80%	93%	91%	98%	95%	89%	82%	87%	85%	86%
87.5%		90%	85%	85%	92%	92%	84%	87%	91%	90%	75%	93%	86%	87%
75.2%		74%	77%	80%	84%	81%	79%	85%	90%	77%	63%	79%	58%	50%
84.2%		87%	85%	88%	91%	80%	85%	78%	90%	87%	74%	79%	82%	89%
76.7%		90%	77%	84%	92%	65%	80%	80%	80%	77%	69%	63%	70%	70%
77.0%		82%	76%	75%	81%	86%	75%	79%	70%	84%	69%	76%	65%	83%
81.5%		77%	75%	79%	82%	89%	80%	87%	82%	82%	82%	79%	81%	84%
82.5%		83%	81%	73%	74%	87%	84%	75%	77%	97%	84%	86%	84%	88%
87.4%		89%	91%	94%	86%	90%	88%	82%	90%	92%	76%	82%	85%	91%
83.3%		90%	86%	81%	63%	91%	87%	72%	84%	86%	83%	93%	88%	79%
87.5%		92%	92%	80%	85%	89%	87%	87%	86%	97%	89%	90%	85%	78%
78.0%		84%	85%	84%	85%	62%	82%	88%	80%	77%	61%	82%	67%	77%
80.9%		80%	83%	87%	80%	82%	83%	80%	85%	81%	77%	76%	80%	78%
76.8%		75%	76%	67%	62%	85%	82%	75%	66%	82%	80%	85%	74%	90%
88.5%		92%	95%	92%	91%	92%	87%	85%	86%	90%	79%	89%	86%	87%
86.8%		88%	88%	89%	86%	72%	87%	89%	87%	90%	89%	84%	88%	92%
83.8%		87%	74%	84%	89%	87%	78%	79%	88%	86%	82%	89%	85%	81%
85.4%		83%	92%	89%	76%	86%	86%	84%	84%	88%	82%	83%	92%	85%
87.1%		89%	80%	84%	85%	81%	84%	85%	97%	89%	92%	91%	80%	95%
89.6%		94%	91%	93%	89%	93%	82%	91%	90%	91%	79%	88%	89%	95%
80.8%		81%	90%	85%	64%	87%	85%	79%	80%	79%	80%	82%	79%	80%
87.7%		92%	77%	89%	92%	85%	78%	92%	93%	81%	90%	87%	88%	96%
84.9%		93%	89%	85%	86%	84%	89%	87%	86%	87%	73%	87%	81%	77%
84.2%		87%	79%	86%	84%	88%	80%	82%	87%	85%	82%	88%	81%	86%
81.8%		84%	88%	89%	79%	77%	82%	71%	70%	86%	79%	82%	87%	89%
73.0%		75%	72%	75%	73%	72%	67%	71%	74%	74%	66%	78%	75%	77%
82.8%		89%	92%	91%	90%	75%	88%	81%	84%	72%	65%	73%	84%	92%
87.5%		98%	94%	97%	95%	74%	77%	81%	92%	96%	71%	77%	95%	91%
69.8%		69%	63%	68%	81%	61%	70%	75%	68%	69%	66%	73%	73%	72%
72.0%		91%	89%	92%	91%	47%	60%	67%	80%	82%	60%	51%	59%	67%
67.3%		82%	63%	78%	48%	60%	61%	62%	60%	62%	62%	66%	93%	78%
88.5%		88%	90%	87%	93%	82%	92%	93%	88%	94%	86%	92%	81%	85%
72.3%		74%	83%	70%	72%	75%	74%	73%	66%	67%	68%	69%	73%	76%
83.5%		78%	78%	76%	81%	84%	81%	86%	88%	88%	87%	89%	88%	82%
85.0%		82%	92%	91%	61%	92%	81%	66%	88%	91%	88%	91%	90%	92%
85.5%		76%	86%	88%	61%	91%	97%	83%	81%	85%	90%	90%	86%	97%
76.6%		76%	83%	90%	90%	54%	81%	82%	93%	82%	63%	68%	61%	73%
85.0%		90%	89%	91%	87%	78%	81%	82%	90%	88%	73%	79%	85%	92%
77.5%		74%	82%	83%	71%	81%	79%	70%	87%	77%	68%	83%	72%	80%
87.4%		83%	83%	85%	84%	92%	82%	91%	88%	88%	92%	96%	88%	84%
85.2%		89%	88%	93%	92%	88%	82%	82%	68%	78%	92%	79%	86%	91%
78.6%		77%	77%	77%	76%	62%	74%	78%	91%	82%	83%	89%	79%	77%
87.5%		89%	85%	85%	88%	82%	90%	89%	89%	92%	86%	89%	86%	88%
86.1%		96%	75%	79%	86%	70%	96%	92%	98%	92%	86%	79%	79%	91%
81.5%		91%	87%	92%	94%	62%	78%	88%	93%	83%	56%	86%	74%	75%
62.9%		57%	62%	76%	82%	35%	64%	66%	84%	65%	56%	59%	53%	59%
77.6%		74%	74%	84%	79%	82%	82%	73%	76%	83%	65%	75%	81%	81%
82.0%		85%	88%	89%	87%	79%	80%	84%	88%	85%	82%	79%	74%	66%
88.1%		95%	87%	80%	65%	94%	87%	90%	94%	90%	89%	93%	92%	89%
82.9%		88%	84%	86%	92%	83%	79%	85%	88%	88%	73%	83%	79%	70%
89.8%		82%	94%	94%	97%	82%	94%	93%	95%	91%	92%	82%	89%	83%
86.8%		91%	86%	87%	90%	93%	85%	82%	87%	90%	81%	89%	91%	77%
91.8%		98%	95%	93%	86%	89%	96%	95%	95%	95%	80%	91%	87%	93%
83.5%		84%	90%	82%	85%	86%	82%	81%	76%	84%	81%	81%	86%	87%