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%3Asouth Africa C10 - Run 01e41f8...

Global Dialogues GD4 - South Africa (10 context Qs)

DTEF: Predict response distributions for South Africa. 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

Knowledge, learning and memory

Best Models (Coverage)

1.Claude Sonnet 4.5
68.0%
2.GPT 4.1
67.5%
3.Claude Sonnet 4
65.3%
4.Claude Haiku 4.5
64.7%
5.GPT 4.1 Mini
64.4%

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 64.7%	3rd 65.3%	1st 68.0%	11th 59.1%	13th 58.0%	9th 60.8%	6th 64.2%	2nd 67.5%	5th 64.4%	8th 61.9%	7th 63.5%	10th 60.7%	12th 58.2%
40.2%		41%	47%	58%	56%	16%	30%	39%	58%	41%	41%	37%	24%	35%
41.0%		29%	46%	40%	58%	19%	34%	47%	57%	41%	41%	44%	36%	41%
76.1%		78%	78%	93%	78%	70%	73%	76%	93%	77%	64%	73%	66%	70%
57.7%		56%	58%	58%	47%	56%	60%	57%	69%	58%	55%	64%	54%	58%
63.1%		68%	67%	70%	41%	61%	71%	63%	67%	62%	60%	60%	67%	63%
60.5%		51%	68%	68%	77%	54%	51%	57%	82%	64%	54%	74%	57%	29%
72.4%		78%	78%	98%	79%	47%	77%	77%	63%	45%	79%	71%	79%	70%
54.9%		46%	44%	44%	89%	52%	40%	54%	63%	80%	46%	55%	55%	46%
66.5%		57%	58%	67%	70%	74%	65%	69%	73%	96%	64%	62%	56%	54%
68.3%		70%	79%	58%	20%	71%	78%	57%	44%	73%	88%	85%	83%	82%
56.3%		55%	58%	58%	77%	41%	40%	55%	66%	58%	58%	69%	49%	48%
71.3%		73%	76%	76%	70%	70%	81%	74%	70%	73%	70%	71%	61%	62%
58.4%		57%	58%	67%	82%	58%	48%	56%	72%	58%	54%	55%	48%	46%
60.2%		86%	73%	66%	0%	48%	68%	57%	73%	66%	44%	58%	73%	71%
62.7%		63%	61%	59%	0%	66%	68%	61%	56%	72%	76%	76%	81%	76%
63.4%		60%	60%	70%	76%	60%	64%	68%	70%	64%	47%	62%	59%	64%
66.2%		71%	71%	71%	78%	67%	56%	58%	64%	69%	64%	58%	64%	69%
74.6%		82%	79%	83%	75%	72%	73%	80%	73%	72%	65%	65%	74%	77%
76.3%		85%	82%	74%	82%	57%	85%	92%	75%	83%	85%	76%	58%	58%
81.2%		92%	81%	81%	77%	51%	84%	77%	78%	90%	87%	90%	86%	81%
63.4%		73%	64%	76%	52%	68%	53%	62%	72%	65%	62%	62%	62%	53%
68.3%		71%	77%	76%	24%	74%	80%	70%	70%	70%	63%	70%	63%	80%
60.8%		58%	58%	75%	78%	48%	58%	62%	94%	58%	47%	73%	64%	17%
70.6%		66%	74%	69%	68%	68%	83%	80%	74%	61%	74%	58%	60%	83%
65.1%		59%	70%	69%	47%	63%	66%	55%	71%	77%	64%	68%	67%	70%
84.2%		85%	79%	100%	85%	85%	71%	85%	79%	85%	85%	85%	85%	85%
64.7%		58%	65%	60%	64%	72%	46%	70%	58%	71%	70%	72%	68%	67%
64.5%		67%	68%	75%	68%	38%	64%	73%	75%	70%	64%	63%	57%	57%
49.1%		49%	45%	45%	86%	37%	56%	48%	58%	49%	51%	35%	38%	41%
64.3%		71%	69%	74%	53%	52%	64%	71%	73%	64%	64%	59%	58%	64%
76.6%		75%	85%	85%	47%	71%	75%	85%	85%	75%	84%	90%	89%	50%
60.3%		54%	54%	60%	41%	71%	52%	66%	64%	66%	64%	68%	70%	54%
66.2%		70%	68%	96%	78%	60%	66%	64%	73%	73%	51%	65%	43%	54%
52.8%		50%	51%	54%	78%	50%	50%	65%	54%	54%	36%	51%	44%	49%
52.2%		44%	58%	57%	34%	50%	40%	59%	78%	58%	40%	56%	51%	54%
68.2%		67%	73%	73%	46%	68%	67%	74%	73%	69%	69%	74%	74%	59%
50.5%		44%	47%	47%	88%	48%	30%	41%	57%	64%	47%	56%	40%	47%
41.8%		46%	43%	43%	43%	39%	45%	48%	40%	37%	39%	46%	37%	37%
55.8%		54%	59%	59%	42%	53%	59%	62%	59%	62%	54%	70%	60%	33%
67.3%		78%	67%	83%	67%	66%	67%	10%	67%	69%	74%	69%	83%	75%
68.6%		72%	80%	80%	60%	60%	73%	71%	77%	80%	54%	72%	50%	63%
61.2%		63%	62%	52%	53%	73%	62%	59%	50%	52%	75%	52%	79%	64%
53.6%		61%	44%	67%	66%	45%	45%	57%	61%	50%	42%	61%	48%	50%
67.8%		64%	64%	64%	69%	76%	67%	73%	64%	63%	70%	74%	72%	62%
67.5%		72%	73%	73%	56%	56%	57%	69%	84%	70%	67%	69%	61%	70%
77.5%		73%	78%	78%	78%	75%	73%	80%	80%	84%	70%	79%	83%	77%
57.5%		67%	55%	70%	66%	60%	65%	52%	55%	55%	46%	48%	56%	53%
76.8%		84%	95%	95%	57%	57%	65%	74%	95%	79%	65%	99%	85%	48%
51.6%		53%	56%	48%	24%	56%	60%	57%	47%	47%	53%	55%	53%	62%
70.1%		73%	69%	61%	60%	69%	73%	76%	81%	61%	81%	68%	69%	70%
60.5%		66%	51%	51%	61%	56%	67%	76%	62%	53%	69%	58%	65%	52%
58.6%		65%	69%	78%	0%	58%	56%	74%	68%	65%	59%	58%	65%	47%
64.0%		73%	65%	82%	64%	44%	47%	69%	70%	98%	52%	64%	56%	48%
63.4%		58%	58%	66%	54%	61%	65%	73%	71%	59%	69%	69%	63%	58%
45.8%		51%	46%	58%	40%	33%	33%	44%	58%	58%	49%	39%	49%	38%
69.8%		71%	71%	71%	52%	69%	75%	71%	71%	70%	70%	72%	76%	69%
64.3%		69%	75%	69%	19%	60%	75%	69%	75%	64%	72%	63%	57%	69%
45.5%		46%	47%	47%	70%	40%	36%	46%	58%	47%	41%	43%	35%	36%
52.5%		50%	44%	67%	72%	48%	50%	57%	67%	50%	41%	47%	40%	50%
76.1%		84%	84%	78%	51%	84%	81%	68%	64%	84%	81%	66%	85%	79%
69.8%		66%	76%	68%	55%	76%	72%	73%	72%	77%	71%	70%	69%	63%
58.4%		66%	69%	77%	59%	38%	56%	71%	69%	39%	66%	51%	54%	44%
67.7%		62%	71%	71%	70%	80%	71%	71%	71%	68%	59%	59%	64%	63%
65.6%		69%	70%	70%	54%	60%	58%	69%	67%	71%	67%	71%	66%	61%
57.4%		56%	56%	72%	68%	51%	56%	62%	72%	56%	47%	69%	62%	19%
55.3%		56%	53%	60%	89%	53%	56%	75%	51%	43%	38%	55%	44%	46%
54.7%		69%	58%	58%	67%	45%	62%	61%	63%	43%	48%	41%	49%	47%
59.8%		70%	64%	49%	41%	63%	70%	72%	52%	51%	72%	67%	59%	48%
61.3%		67%	69%	69%	54%	59%	63%	53%	63%	59%	60%	64%	61%	56%
68.4%		80%	79%	71%	58%	62%	67%	58%	71%	75%	63%	67%	67%	71%
64.1%		63%	67%	73%	66%	66%	60%	56%	74%	61%	59%	64%	63%	61%
65.8%		66%	70%	76%	46%	74%	66%	66%	83%	64%	56%	64%	72%	52%
73.3%		76%	77%	94%	77%	67%	62%	76%	97%	73%	62%	62%	64%	66%
59.8%		64%	58%	67%	42%	68%	58%	58%	57%	45%	62%	67%	73%	58%
52.2%		57%	58%	58%	61%	48%	43%	55%	58%	51%	55%	54%	48%	32%
63.1%		64%	66%	61%	41%	71%	68%	59%	54%	66%	66%	66%	65%	73%
77.3%		74%	75%	75%	59%	69%	81%	100%	67%	81%	81%	78%	84%	81%
71.3%		75%	72%	70%	59%	67%	73%	75%	70%	77%	72%	74%	66%	77%
52.8%		52%	53%	53%	77%	40%	37%	52%	66%	57%	54%	54%	44%	47%
60.9%		65%	66%	70%	52%	53%	53%	61%	62%	65%	64%	66%	61%	54%
69.8%		74%	70%	63%	73%	66%	63%	69%	70%	70%	76%	75%	56%	83%
57.3%		63%	55%	69%	63%	42%	63%	63%	71%	53%	66%	42%	49%	46%
58.2%		63%	62%	61%	89%	51%	64%	52%	76%	55%	47%	47%	44%	45%
65.5%		68%	73%	63%	67%	65%	73%	67%	51%	73%	58%	63%	58%	73%
74.5%		80%	80%	82%	74%	67%	72%	84%	76%	80%	67%	72%	81%	54%
53.1%		55%	58%	58%	61%	48%	43%	55%	62%	43%	51%	53%	48%	55%
59.0%		62%	62%	67%	62%	60%	51%	52%	67%	62%	55%	68%	54%	45%
76.5%		84%	78%	70%	67%	70%	80%	75%	84%	83%	76%	70%	83%	74%
68.8%		77%	71%	78%	48%	54%	78%	75%	64%	83%	68%	80%	60%	59%
67.2%		77%	73%	73%	74%	55%	53%	65%	68%	71%	84%	57%	68%	56%
56.5%		50%	51%	65%	61%	50%	54%	61%	63%	54%	61%	61%	49%	54%
69.9%		70%	67%	64%	67%	60%	83%	74%	66%	70%	74%	72%	70%	72%
49.9%		67%	64%	64%	0%	52%	42%	42%	48%	40%	61%	49%	68%	52%
47.4%		57%	52%	52%	53%	30%	52%	51%	51%	59%	57%	43%	20%	39%
74.9%		76%	76%	83%	60%	69%	72%	82%	66%	78%	76%	78%	80%	78%
52.8%		45%	53%	53%	78%	51%	38%	65%	53%	56%	49%	62%	45%	39%
73.2%		74%	80%	80%	42%	79%	76%	67%	85%	67%	77%	77%	68%	79%
51.2%		49%	55%	43%	31%	55%	55%	51%	48%	58%	55%	55%	55%	55%
62.6%		62%	63%	71%	59%	49%	70%	62%	79%	62%	60%	64%	51%	62%
52.8%		51%	51%	62%	42%	58%	51%	56%	46%	51%	54%	59%	57%	49%
43.5%		49%	49%	53%	0%	45%	46%	46%	46%	49%	45%	38%	51%	49%
55.8%		46%	53%	53%	77%	62%	39%	60%	59%	57%	61%	62%	49%	47%
76.9%		81%	75%	82%	85%	70%	72%	73%	72%	69%	85%	69%	82%	85%
52.1%		58%	58%	58%	59%	26%	39%	39%	64%	58%	55%	59%	52%	52%
47.3%		52%	52%	45%	73%	26%	44%	57%	70%	36%	59%	41%	25%	35%
64.5%		63%	80%	77%	59%	46%	68%	64%	70%	73%	52%	57%	52%	77%
73.5%		79%	77%	94%	47%	75%	75%	78%	87%	97%	57%	70%	69%	50%
42.5%		30%	46%	48%	64%	21%	40%	43%	63%	43%	36%	42%	34%	43%
61.1%		57%	60%	54%	68%	70%	54%	60%	61%	63%	59%	63%	63%	62%
64.7%		69%	77%	77%	78%	74%	50%	61%	73%	57%	53%	67%	55%	50%
54.7%		57%	52%	52%	56%	50%	42%	56%	52%	58%	54%	67%	56%	59%
62.1%		70%	66%	83%	65%	50%	57%	67%	77%	66%	51%	51%	51%	53%
77.7%		66%	75%	79%	85%	74%	77%	75%	77%	71%	85%	82%	82%	82%
78.4%		86%	89%	89%	49%	87%	71%	86%	77%	86%	85%	86%	76%	52%
76.5%		85%	76%	77%	70%	62%	72%	75%	76%	76%	97%	67%	79%	83%
81.8%		89%	89%	89%	67%	73%	83%	75%	78%	89%	83%	82%	80%	86%