DTeval

A Collective Intelligence Project

Loading blueprint versions...

Please wait while we gather all the unique runs for this blueprint.

Analysis: Gd4 Ctx Dtef Global Dialogues Gd4 Gender%3Afemale Ctx - Run 9d1932f...

Global Dialogues GD4 - Female (with context)

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

TAGS:

Global Dialogues Gd4

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Social interaction

AI Safety & Robustness

Best Models (Coverage)

1.Claude Sonnet 4.5
87.2%
2.Gemini 2.5 Flash
86.9%
3.Claude Sonnet 4
86.5%
4.GPT 4.1
85.9%
5.Claude Haiku 4.5
85.3%

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		5th 85.3%	3rd 86.5%	1st 87.2%	2nd 86.9%	11th 79.6%	7th 83.4%	6th 85.1%	4th 85.9%	9th 83.0%	13th 77.8%	10th 81.6%	12th 78.9%	8th 83.2%
82.4%		80%	89%	83%	76%	81%	83%	81%	84%	85%	82%	79%	84%	84%
75.3%		93%	80%	91%	94%	60%	70%	94%	94%	75%	55%	53%	63%	57%
78.5%		82%	81%	87%	85%	72%	66%	85%	86%	83%	62%	83%	74%	75%
85.8%		90%	74%	96%	88%	85%	91%	84%	89%	82%	82%	82%	86%	87%
74.1%		75%	81%	87%	81%	64%	73%	78%	79%	70%	70%	68%	67%	70%
90.5%		88%	93%	93%	91%	90%	88%	89%	93%	93%	89%	89%	88%	92%
68.6%		90%	81%	82%	72%	59%	60%	66%	63%	59%	59%	63%	62%	76%
84.7%		83%	85%	82%	88%	81%	84%	85%	88%	89%	91%	85%	81%	79%
85.4%		93%	96%	96%	79%	88%	91%	79%	93%	74%	65%	83%	84%	89%
64.3%		63%	63%	63%	52%	80%	63%	85%	63%	55%	52%	66%	62%	69%
92.2%		85%	96%	97%	95%	90%	94%	94%	98%	86%	92%	91%	86%	94%
89.5%		82%	80%	85%	93%	90%	92%	89%	94%	91%	93%	92%	93%	89%
85.8%		86%	86%	86%	86%	84%	86%	86%	86%	86%	86%	86%	86%	86%
65.8%		70%	87%	58%	79%	64%	52%	58%	57%	72%	71%	60%	61%	67%
83.9%		80%	87%	82%	90%	72%	81%	91%	87%	86%	74%	75%	93%	93%
84.2%		95%	93%	91%	90%	78%	95%	92%	93%	90%	43%	87%	55%	92%
84.1%		92%	85%	87%	97%	77%	88%	87%	79%	79%	78%	88%	74%	82%
89.8%		86%	84%	88%	89%	95%	85%	93%	90%	93%	84%	91%	94%	95%
90.6%		90%	93%	92%	91%	92%	89%	89%	88%	90%	90%	94%	90%	90%
74.2%		75%	75%	72%	72%	62%	78%	79%	74%	74%	70%	86%	75%	73%
91.8%		93%	92%	94%	94%	87%	95%	93%	93%	92%	80%	93%	94%	94%
95.3%		97%	96%	99%	97%	89%	94%	97%	94%	96%	96%	96%	92%	96%
93.7%		92%	96%	96%	96%	88%	89%	96%	96%	93%	93%	90%	96%	97%
70.7%		83%	73%	87%	87%	55%	72%	67%	83%	86%	54%	63%	45%	64%
84.5%		79%	85%	85%	89%	90%	90%	82%	87%	84%	79%	79%	81%	88%
84.5%		92%	84%	90%	91%	78%	83%	78%	87%	51%	91%	91%	91%	91%
88.4%		86%	88%	95%	91%	86%	81%	95%	94%	81%	92%	87%	81%	92%
72.0%		57%	71%	80%	74%	66%	67%	77%	83%	74%	70%	68%	75%	74%
83.0%		81%	93%	92%	91%	78%	79%	79%	95%	91%	74%	82%	71%	73%
85.4%		72%	89%	90%	86%	87%	84%	94%	93%	92%	60%	90%	80%	93%
93.0%		95%	91%	91%	92%	96%	96%	89%	92%	94%	93%	97%	93%	90%
93.2%		98%	98%	97%	92%	90%	89%	95%	95%	92%	90%	91%	90%	94%
81.5%		87%	86%	94%	89%	72%	81%	88%	94%	87%	87%	67%	53%	75%
82.8%		88%	88%	95%	93%	73%	90%	94%	96%	90%	38%	91%	49%	91%
86.4%		92%	91%	91%	92%	86%	76%	91%	81%	77%	85%	84%	91%	86%
94.5%		97%	96%	94%	96%	90%	92%	95%	97%	93%	93%	93%	96%	97%
90.2%		94%	90%	94%	92%	88%	89%	94%	93%	78%	87%	89%	90%	94%
92.2%		92%	91%	91%	93%	93%	93%	93%	91%	89%	93%	93%	93%	93%
91.6%		92%	92%	91%	88%	93%	92%	87%	91%	91%	93%	97%	95%	89%
92.6%		93%	94%	87%	93%	93%	93%	93%	93%	93%	93%	93%	93%	93%
82.4%		96%	93%	78%	87%	74%	90%	95%	88%	94%	41%	82%	58%	95%
83.8%		92%	79%	94%	92%	71%	88%	80%	75%	91%	92%	70%	91%	75%
85.2%		90%	89%	89%	93%	78%	85%	91%	92%	86%	91%	64%	79%	81%
79.3%		82%	84%	84%	72%	79%	88%	78%	86%	74%	82%	83%	71%	68%
76.7%		85%	89%	81%	86%	83%	83%	65%	88%	62%	53%	76%	59%	87%
81.8%		77%	90%	89%	84%	69%	93%	83%	89%	79%	72%	73%	82%	83%
81.5%		83%	86%	80%	83%	88%	79%	80%	85%	83%	79%	77%	80%	76%
89.9%		97%	98%	98%	90%	81%	94%	88%	84%	86%	72%	96%	97%	88%
93.2%		93%	86%	92%	97%	92%	96%	94%	88%	97%	97%	96%	87%	96%
92.2%		92%	94%	96%	90%	96%	95%	92%	94%	92%	90%	90%	87%	91%
90.1%		92%	91%	87%	89%	92%	90%	91%	90%	90%	89%	89%	88%	93%
73.2%		71%	78%	92%	89%	68%	69%	66%	87%	71%	67%	76%	54%	64%
77.7%		81%	83%	87%	88%	72%	77%	78%	74%	75%	72%	72%	79%	72%
69.2%		77%	76%	83%	89%	61%	63%	64%	72%	73%	65%	72%	47%	57%
90.9%		91%	91%	91%	91%	90%	91%	91%	91%	91%	91%	91%	91%	91%
84.2%		86%	87%	85%	90%	82%	80%	89%	87%	87%	81%	77%	78%	85%
61.3%		64%	72%	66%	90%	42%	70%	65%	68%	51%	27%	70%	54%	58%
86.0%		86%	86%	86%	86%	86%	86%	86%	86%	86%	86%	86%	86%	86%
79.1%		85%	85%	91%	90%	68%	89%	77%	90%	84%	53%	87%	38%	91%
82.7%		84%	87%	89%	66%	77%	87%	89%	82%	83%	84%	88%	68%	91%
84.9%		92%	88%	84%	75%	84%	79%	85%	90%	80%	77%	91%	87%	92%
81.3%		65%	90%	86%	86%	87%	88%	86%	81%	80%	69%	85%	81%	73%
80.3%		82%	86%	84%	71%	80%	86%	81%	94%	76%	76%	76%	76%	76%
91.8%		85%	93%	95%	95%	93%	84%	97%	93%	87%	99%	90%	87%	96%
93.9%		92%	95%	95%	95%	90%	90%	96%	96%	93%	94%	94%	95%	96%
76.6%		68%	90%	85%	94%	64%	83%	87%	80%	88%	60%	62%	57%	78%
72.8%		76%	75%	74%	94%	67%	78%	75%	84%	72%	62%	62%	62%	66%
78.2%		89%	77%	77%	84%	80%	71%	73%	75%	87%	69%	70%	75%	90%
81.5%		86%	87%	76%	84%	84%	78%	85%	82%	81%	79%	76%	77%	85%
83.0%		93%	78%	75%	68%	87%	80%	87%	75%	93%	87%	90%	78%	88%
79.2%		79%	79%	82%	79%	79%	79%	79%	79%	79%	79%	79%	79%	79%
78.2%		94%	88%	83%	53%	84%	80%	57%	83%	69%	79%	80%	73%	93%
86.6%		89%	97%	92%	84%	78%	86%	89%	89%	86%	79%	95%	86%	76%
77.6%		83%	78%	87%	90%	65%	80%	94%	79%	83%	65%	77%	61%	67%
82.9%		84%	85%	84%	82%	85%	80%	81%	82%	81%	85%	82%	85%	82%
89.8%		92%	94%	91%	94%	92%	97%	85%	85%	85%	85%	93%	89%	86%
85.3%		87%	91%	82%	91%	85%	81%	87%	79%	77%	75%	87%	92%	95%
87.7%		90%	89%	89%	91%	88%	87%	87%	86%	89%	85%	84%	90%	85%
89.8%		83%	94%	94%	95%	88%	86%	91%	95%	84%	92%	87%	83%	95%
91.0%		91%	91%	91%	91%	91%	91%	91%	91%	91%	91%	91%	91%	91%
79.9%		76%	87%	91%	76%	76%	83%	82%	88%	76%	76%	76%	76%	76%
93.0%		96%	96%	91%	97%	87%	95%	97%	94%	92%	93%	87%	92%	92%
82.8%		91%	91%	85%	74%	75%	85%	93%	89%	87%	73%	78%	73%	83%
91.9%		92%	92%	94%	97%	92%	92%	96%	82%	86%	97%	96%	82%	97%
85.3%		93%	84%	81%	84%	85%	80%	88%	85%	87%	80%	87%	85%	90%
91.8%		94%	92%	93%	84%	93%	91%	91%	95%	88%	94%	94%	90%	95%
79.7%		85%	86%	80%	86%	86%	85%	87%	81%	89%	66%	66%	70%	69%
79.8%		92%	80%	81%	82%	69%	80%	71%	75%	85%	86%	74%	86%	76%
80.3%		94%	87%	94%	92%	58%	76%	83%	79%	79%	81%	69%	69%	83%
82.2%		86%	81%	81%	81%	62%	76%	83%	89%	90%	84%	87%	83%	85%
71.6%		69%	74%	76%	92%	74%	72%	79%	73%	80%	47%	72%	64%	59%
77.4%		82%	79%	93%	82%	71%	59%	89%	91%	89%	82%	63%	63%	63%
71.6%		90%	79%	78%	75%	72%	55%	53%	59%	70%	41%	76%	95%	88%
87.5%		84%	81%	92%	91%	82%	87%	86%	93%	89%	89%	87%	89%	88%
59.8%		60%	62%	63%	66%	69%	71%	48%	51%	57%	45%	47%	69%	70%
84.6%		76%	87%	87%	79%	84%	92%	95%	95%	79%	89%	79%	79%	79%
89.1%		92%	94%	92%	78%	91%	95%	79%	92%	98%	78%	81%	93%	95%
85.1%		81%	88%	86%	89%	87%	86%	84%	85%	83%	72%	90%	90%	85%
81.0%		94%	93%	83%	90%	58%	91%	97%	95%	73%	65%	77%	67%	70%
81.1%		92%	94%	98%	93%	73%	75%	88%	79%	79%	72%	63%	72%	76%
79.1%		75%	86%	89%	90%	71%	88%	81%	88%	84%	63%	79%	64%	70%
81.6%		74%	82%	88%	84%	76%	76%	86%	81%	79%	93%	94%	69%	79%
85.5%		94%	93%	95%	92%	85%	89%	78%	78%	70%	92%	74%	85%	87%
81.4%		82%	80%	77%	92%	68%	80%	80%	93%	87%	91%	75%	71%	82%
90.3%		87%	87%	90%	91%	91%	88%	93%	88%	92%	89%	94%	93%	91%
83.9%		90%	84%	93%	86%	73%	85%	90%	82%	83%	87%	86%	66%	86%
78.7%		93%	70%	88%	92%	59%	67%	89%	92%	91%	65%	77%	63%	77%
72.9%		62%	79%	93%	95%	58%	78%	95%	94%	60%	50%	68%	61%	55%
78.6%		67%	84%	76%	88%	76%	81%	80%	86%	80%	59%	82%	81%	82%
89.3%		93%	97%	93%	95%	78%	92%	91%	92%	95%	91%	78%	92%	74%
88.6%		91%	94%	91%	93%	88%	77%	95%	83%	83%	88%	89%	90%	90%
89.5%		83%	91%	82%	93%	88%	93%	90%	90%	94%	79%	92%	94%	94%
89.2%		82%	95%	97%	97%	78%	97%	94%	91%	86%	91%	75%	90%	86%
91.8%		87%	91%	93%	95%	92%	91%	91%	91%	85%	99%	97%	86%	96%
87.0%		91%	91%	92%	88%	77%	92%	92%	92%	88%	84%	73%	83%	88%
82.5%		79%	84%	84%	79%	89%	78%	82%	79%	79%	92%	79%	89%	79%