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%3Akazakhstan C10 - Run 88d6f4f...

Global Dialogues GD4 - Kazakhstan (10 context Qs)

DTEF: Predict response distributions for Kazakhstan. 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

Efficiency & Succinctness

Clarity & Readability

Best Models (Coverage)

1.GPT 4.1
69.0%
2.Claude 3.7 Sonnet
68.9%
3.GPT 4o
68.5%
4.Claude Haiku 4.5
68.3%
5.GPT 5.1
68.2%

🔀 Least Similar Models

Claude Sonnet 4.5vsGPT OSS 20b

74.9% similarity

👯 Most Similar Models

Claude 3.7 SonnetvsClaude Sonnet 4

93.5% 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 68.9%	4th 68.3%	7th 67.6%	9th 67.3%	21st 60.6%	15th 65.3%	10th 67.2%	14th 65.5%	8th 67.4%	1st 69.0%	6th 67.9%	16th 64.8%	3rd 68.5%	12th 66.3%	13th 66.3%	5th 68.2%	19th 61.9%	20th 61.8%	11th 67.0%	17th 64.7%	18th 63.7%
79.0%		90%	84%	86%	86%	81%	52%	80%	86%	86%	77%	72%	76%	84%	74%	79%	84%	85%	71%	66%	84%	75%
66.4%		78%	64%	70%	70%	72%	47%	60%	70%	75%	87%	68%	66%	79%	69%	78%	78%	48%	37%	65%	51%	63%
78.2%		80%	79%	81%	81%	78%	77%	81%	77%	77%	100%	81%	76%	79%	72%	79%	79%	79%	72%	71%	71%	72%
77.7%		77%	80%	78%	78%	79%	79%	76%	83%	81%	73%	78%	83%	76%	83%	80%	76%	83%	74%	81%	63%	70%
46.7%		55%	50%	49%	55%	48%	44%	49%	50%	49%	49%	43%	36%	49%	48%	45%	47%	29%	34%	42%	58%	52%
77.8%		77%	86%	82%	66%	37%	85%	88%	79%	81%	82%	84%	88%	82%	77%	59%	70%	79%	83%	83%	90%	75%
69.5%		70%	79%	79%	79%	64%	65%	76%	65%	64%	67%	63%	66%	67%	63%	67%	69%	68%	68%	72%	70%	78%
76.1%		84%	73%	84%	72%	38%	71%	77%	82%	85%	77%	75%	82%	82%	83%	77%	80%	82%	80%	81%	64%	70%
76.9%		76%	76%	75%	76%	70%	79%	79%	79%	78%	92%	88%	72%	68%	79%	59%	89%	79%	79%	66%	93%	63%
75.4%		79%	78%	84%	62%	16%	87%	75%	78%	88%	71%	91%	94%	82%	91%	55%	74%	66%	76%	93%	72%	72%
68.3%		77%	75%	77%	71%	20%	75%	71%	68%	70%	75%	72%	76%	76%	71%	61%	62%	61%	68%	70%	67%	71%
72.3%		75%	82%	82%	82%	69%	85%	62%	76%	82%	72%	82%	61%	72%	68%	80%	70%	65%	54%	70%	65%	65%
64.6%		70%	62%	68%	68%	61%	64%	67%	61%	62%	63%	70%	62%	66%	68%	63%	66%	54%	57%	67%	70%	67%
70.8%		79%	79%	79%	76%	76%	62%	81%	62%	72%	72%	67%	60%	64%	60%	79%	79%	58%	65%	72%	68%	76%
64.7%		74%	55%	54%	67%	37%	61%	63%	77%	69%	75%	68%	55%	68%	65%	74%	73%	68%	66%	55%	48%	86%
61.1%		67%	61%	61%	67%	63%	52%	61%	61%	67%	74%	61%	56%	62%	60%	71%	64%	59%	61%	56%	54%	45%
47.2%		38%	39%	35%	38%	49%	59%	52%	52%	52%	49%	42%	56%	52%	54%	42%	42%	49%	45%	49%	56%	42%
57.4%		60%	65%	65%	60%	60%	53%	65%	54%	67%	61%	65%	41%	56%	48%	58%	50%	54%	73%	54%	44%	52%
63.2%		59%	63%	59%	62%	66%	84%	56%	54%	57%	61%	74%	66%	66%	75%	56%	56%	66%	79%	71%	49%	49%
84.3%		92%	91%	79%	86%	79%	65%	86%		79%	79%	88%	79%	84%	90%	92%	86%	85%	89%	84%	86%	86%
74.0%		75%	69%	78%	78%	72%	64%	78%	80%	81%	78%	75%	51%	78%	72%	79%	78%	63%	71%	88%	74%	72%
77.2%		72%	85%	82%	73%	78%	75%	80%	81%	79%	73%	80%	81%	74%	81%	72%	81%	70%	65%	73%	92%	74%
61.3%		69%	70%	67%	69%	36%	64%	61%	65%	58%	67%	60%	61%	61%	61%	58%	63%	57%	53%	60%	67%	61%
40.9%		49%	49%	38%	38%	76%	35%	38%	44%	49%	50%	32%	23%	44%	37%	37%	42%	38%	28%	30%	37%	45%
63.1%		69%	64%	59%	64%	65%	72%	78%	55%	68%	64%	51%	61%	68%	51%	65%	79%	52%	38%	53%	70%	80%
86.4%		91%	76%	77%	82%	90%	90%	79%	86%	90%	90%	90%	90%	82%	90%	85%	91%	88%	81%	90%		90%
63.2%		71%	71%	71%	71%	69%	63%	67%	57%	60%	71%	55%	55%	73%	56%	65%	73%	55%	52%	63%	55%	55%
72.6%		69%	78%	85%	76%	61%	70%	75%	69%	69%	73%	85%	85%	69%	87%	72%	69%	60%	64%	81%	69%	59%
47.3%		35%	51%	52%	52%	32%	65%	42%	33%	41%	48%	62%	56%	36%	58%	33%	40%	47%	41%	65%	47%	57%
72.4%		76%	72%	69%	69%	62%	76%	78%	72%	72%	72%	78%	81%	72%	82%	67%	68%	75%	71%	70%	71%	67%
70.5%		73%	76%	73%	66%	33%	81%	74%	75%	73%	79%	72%	75%	75%	70%	63%	65%	69%	72%	70%		76%
81.5%		89%	71%	91%	92%	64%	78%	77%	86%	82%	78%	78%	84%	91%	84%	86%	91%	82%	73%	78%	64%	92%
74.8%		90%	73%	78%	87%	71%	71%	74%	73%	78%	82%	74%	65%	73%	65%	82%	84%	82%	81%	62%	61%	64%
64.7%		69%	65%	65%	69%	71%	52%	65%	65%	69%	73%	65%	60%	69%	64%	69%	65%	54%	75%	57%	59%	58%
45.0%		46%	56%	45%	44%	22%	46%	52%	51%	46%	44%	43%	49%	41%	49%	43%	42%	44%	37%	53%	48%	44%
66.4%		70%	68%	68%	60%	37%	69%	69%	72%	67%	68%	75%	77%	63%	61%	58%	65%	59%	73%	68%	70%	78%
65.9%		66%	66%	70%	70%	58%	62%	63%	65%	70%	67%	62%	66%	63%	70%	68%	68%	62%	66%	70%	56%	76%
50.4%		50%	45%	56%	47%	46%	54%	46%	55%	42%	51%	51%	56%	41%	59%	52%	48%	40%	54%	69%	56%	41%
61.7%		62%	64%	62%	54%	31%	64%	69%	59%	63%	63%	62%	68%	63%	58%	56%	54%	54%	85%	63%	78%	63%
40.5%		38%	30%	38%	32%	35%	50%	32%	47%	32%	32%	51%	43%	32%	57%	54%	52%	50%	20%	58%	29%	38%
71.0%		70%	64%	70%	90%	76%	53%	74%	71%	71%	90%	67%	63%	90%	62%	90%	84%	46%	78%	53%	61%	69%
61.2%		65%	72%	71%	70%	54%	71%	65%	54%	61%	59%	59%	70%	52%	54%	70%	62%	44%	47%	74%	64%	47%
71.4%		79%	74%	74%	74%	56%	67%	74%	67%	79%	75%	68%	68%	65%	72%	75%	78%	73%	80%	66%	65%	71%
73.0%		69%	70%	69%	69%	80%	67%	86%	86%	69%	78%	59%	66%	85%	74%	66%	67%	69%	77%	75%	75%	76%
43.8%		48%	47%	48%	48%	44%	46%	45%	46%	41%	48%	44%	47%	38%	45%	41%	44%	33%	40%	53%	38%	35%
72.1%		81%	67%	68%	68%	78%	66%	77%	74%	81%	75%	71%	61%	75%	63%	65%	69%	82%	87%	68%	65%	73%
75.6%		68%	89%	78%	67%	64%	80%	75%	81%	81%	71%	82%	73%	78%	73%	76%	78%	69%	66%	79%	85%	75%
91.9%		100%	100%	82%	82%	86%	84%	100%	96%	93%	100%	94%	93%	100%	97%	88%	77%	88%	77%	100%	100%	93%
77.8%		78%	92%	79%	76%	32%	78%	90%	75%	84%	73%	75%	84%	82%	80%	76%	82%	75%	76%	75%	88%	84%
59.2%		51%	54%	54%	54%	61%	68%	51%	38%	54%	62%	70%	62%	60%	62%	53%	54%	62%	66%	68%	63%	77%
83.6%		92%	84%	82%	88%	85%	93%	82%	75%	80%	76%	92%	81%	92%	86%	85%	87%	90%	76%	85%	80%	64%
66.0%		75%	53%	64%	64%	42%	48%	79%	62%	80%	79%	56%	47%	75%	52%	77%	75%	77%	69%	55%	77%	80%
77.7%		79%	79%	79%	82%	67%	73%	75%	79%	79%	85%	79%	72%	79%	74%	78%	87%	82%	75%	79%	79%	71%
61.4%		69%	69%	62%	51%	88%	53%	69%	64%	69%	62%	59%	59%	74%	59%	69%	69%	36%	57%	50%	56%	46%
59.9%		67%	76%	59%	59%	63%	63%	63%	55%	62%	63%	66%	54%	54%	65%	66%	64%	44%	50%	73%	54%	37%
62.7%		73%	59%	67%	73%	64%	55%	55%	70%	67%	55%	60%	55%	68%	55%	64%	75%	63%	68%	61%	55%	55%
37.2%		34%	29%	40%	29%	81%	20%	34%	35%	41%	40%	29%	16%	40%	38%	57%	48%	34%	51%	22%	29%	34%
51.3%		53%	51%	51%	51%	37%	55%	53%	45%	45%	49%	48%	58%	61%	57%	46%	50%	48%	60%	60%	51%	49%
56.1%		60%	55%	57%	73%	90%	43%	55%	55%	60%	74%	57%	33%	60%	52%	71%	73%	41%	33%	36%	44%	57%
67.0%		69%	73%	71%	71%	47%	79%	81%	77%	64%	72%	69%	73%	69%	72%	60%	64%	42%	50%	72%	64%	68%
68.0%		71%	73%	64%	71%	66%	59%	68%	74%	70%	75%	74%	58%	57%	58%	73%	69%	71%	61%	67%	72%	76%
64.7%		57%	59%	63%	56%	70%	79%	72%	59%	59%	70%	87%	71%	71%	78%	58%	55%	55%	55%	73%	59%	52%
65.6%		71%	67%	73%	67%	67%	68%	71%	67%	61%	73%	65%	57%	73%	66%	73%	74%	55%	44%	67%	53%	66%
64.0%		70%	67%	67%	65%	58%	63%	62%	62%	60%	67%	63%	66%	67%	59%	58%	60%	67%	64%	64%	67%	67%
69.3%		74%	77%	70%	64%	64%	68%	68%	71%	66%	69%	73%	74%	74%	69%	63%	65%	71%	62%	73%		70%
65.6%		61%	74%	77%	59%	35%	72%	64%	62%	57%	58%	72%	80%	72%	76%	59%	55%	72%	72%	77%	70%	54%
63.3%		73%	67%	67%	73%	66%	61%	67%	61%	61%	67%	64%	64%	67%	60%	64%	67%	50%	42%	49%	73%	66%
63.0%		69%	74%	69%	69%	63%	62%	54%	62%	69%	63%	71%	56%	61%	65%	65%	72%	64%	54%	62%	41%	57%
58.0%		55%	55%	51%	42%	52%	66%	59%	69%	55%	66%	61%	73%	60%	54%	58%	69%	51%	50%	57%	59%	55%
86.0%		88%	89%	86%	84%	93%	88%	88%	74%	83%	83%	85%	86%	87%	84%	84%	93%	88%	88%	85%		84%
65.5%		69%	69%	69%	69%	49%	77%	71%	69%	65%	69%	68%	71%	68%	71%	68%	65%	60%	52%	73%	54%	49%
74.8%		78%	76%	72%	76%	59%	76%	66%	76%	71%	79%	81%	70%	78%	70%	81%	79%	76%	70%	67%	92%	77%
80.5%		82%	87%	80%	91%	61%	79%	75%	80%	87%	78%	80%	73%	87%	75%	82%	87%	76%	90%	86%	67%	87%
66.5%		66%	72%	76%	68%	77%	66%	68%	79%	81%	78%	61%	34%	77%	73%	66%	65%	62%	58%	45%	57%	68%
43.6%		53%	43%	43%	33%	31%	47%	53%	41%	31%	45%	45%	50%	50%	38%	33%	39%	33%	33%	50%	71%	53%
88.8%		88%	92%	93%	93%	74%	92%	100%	93%	92%	79%	93%	90%	92%	95%	78%	86%	94%	73%	87%	95%	85%
74.1%		83%	75%	76%	81%	60%	71%	74%	74%	79%	75%	75%	74%	74%	70%	79%	74%	74%	69%	76%	64%	79%
81.3%		78%	80%	86%	84%	75%	81%	89%	80%	84%	86%	84%	87%	85%	86%	79%	81%	70%	68%	92%	85%	68%
55.9%		62%	62%	64%	61%	18%	55%	62%	49%	62%	55%	52%	57%	62%	57%	45%	57%	49%	53%	66%	67%	58%
63.4%		74%	65%	57%	57%	71%	74%	63%	66%	66%	62%	64%	54%	64%	67%	66%	56%	45%	71%	57%	66%	66%
75.0%		75%	80%	77%	82%	61%	75%	75%	75%	68%	75%	83%	78%	76%	77%	90%	83%	64%	73%	79%	68%	62%
58.4%		50%	66%	66%	67%	54%	74%	49%	56%	56%	63%	61%	54%	66%	68%	49%	63%	56%	49%	61%	49%	49%
59.7%		61%	64%	60%	60%	51%	63%	57%	57%	53%	71%	64%	59%	66%	59%	56%	58%	64%	52%	57%	71%	51%
87.0%		82%	91%	83%	88%	87%	87%	80%	84%	91%	80%	91%	93%	92%	92%	91%	93%	80%	84%	85%	87%	87%
70.9%		68%	79%	68%	68%	65%	70%	72%	68%	77%	75%	75%	77%	65%	77%	70%	72%	78%	61%	75%		58%
52.8%		57%	57%	57%	52%	37%	50%	53%	51%	55%	48%	52%	57%	52%	51%	54%	56%	54%	54%	59%	55%	47%
52.9%		53%	53%	53%	53%	47%	56%	53%	51%	58%	55%	58%	58%	49%	64%	49%	54%	37%	33%	67%	57%
53.5%		48%	64%	48%	48%	55%	75%	54%	50%	50%	51%	65%	59%	55%	66%	51%	50%	37%	43%	59%	58%	38%
55.3%		63%	50%	68%	62%	73%	49%	55%	54%	55%	65%	55%	44%	62%	51%	60%	59%	26%	45%	68%	36%	62%
71.8%		73%	73%	81%	81%	79%	60%	70%	70%	65%	73%	73%	72%	67%	67%	67%	60%	63%	83%	87%	67%	76%
70.3%		73%	67%	67%	67%	80%	58%	71%	63%	76%	64%	65%	77%	76%	68%	73%	76%	81%	80%	65%	71%	59%
66.2%		75%	68%	85%	81%	78%	38%	79%	58%	57%	72%	81%	53%	69%	49%	83%	86%	44%	43%	53%	78%	60%
55.2%		59%	65%	64%	70%	38%	49%	55%	52%	38%	52%	38%	57%	59%	38%	58%	64%	64%	64%	60%	64%	52%
52.3%		47%	51%	57%	50%	53%	66%	47%	42%	57%	57%	68%	61%	53%	68%	39%	46%	41%	37%	69%	54%	36%
35.1%		34%	41%	41%	35%	22%	41%	38%	37%	41%	33%	33%	37%	41%	37%	34%	33%	19%	30%	41%		33%
79.6%		79%	85%	85%	85%	66%	77%	70%	84%	81%	77%	78%	83%	85%	82%	83%	85%	70%	82%	85%	72%	78%
46.6%		51%	41%	46%	59%	22%	51%	40%	38%	44%	49%	62%	55%	44%	57%	44%	39%	58%	41%	51%	52%	34%
76.8%		80%	78%	80%	80%	62%	73%	80%	80%	78%	65%	74%	81%	78%	81%	73%	80%	78%	75%	87%	71%	78%
61.3%		65%	62%	58%	75%	94%	39%	62%	58%	65%	75%	62%	41%	65%	59%	70%	76%	51%	67%	53%	61%	29%
52.7%		60%	60%	56%	49%	71%	50%	46%	56%	51%	64%	60%	39%	60%	41%	46%	46%	54%	38%	59%	51%	50%
70.0%		74%	76%	82%	76%	27%	65%	70%	82%	82%	82%	73%	49%	82%	62%	83%	77%	74%	67%	68%	44%	76%
71.8%		66%	71%	71%	78%	55%	71%	71%	73%	81%	67%	77%	73%	75%	74%	69%	68%	76%	77%	78%	68%	68%
76.3%		100%	78%	73%	78%	87%	74%	73%	75%	76%	70%	79%	75%	70%	62%	78%	81%	78%	62%	79%		79%
81.8%		80%	83%	79%	81%	88%	57%	76%	76%	77%	100%	81%	81%	88%	77%	83%	80%	88%	91%	76%	90%	86%
58.5%		54%	67%	51%	51%	55%	75%	52%	56%	59%	60%	72%	56%	60%	64%	51%	67%	57%	50%	75%	40%	57%
83.9%		79%	93%	62%	75%	87%	87%	82%	81%	93%	91%	93%	84%	91%	92%	93%	90%	75%	63%	82%	84%	84%
45.5%		67%	56%	37%	51%	61%	30%	43%	33%	51%	51%	39%	33%	56%	42%	51%	46%	43%	43%	33%	42%	48%
64.7%		73%	59%	64%	73%	87%	41%	61%	56%	73%	87%	65%	59%	71%	61%	74%	92%	67%	34%	58%	70%	34%
75.5%		74%	78%	75%	75%	81%	83%	92%	78%	63%	81%	72%	79%	75%	67%	75%	74%	67%	71%	81%	81%	63%
74.0%		81%	74%	74%	76%	71%	71%	73%	74%	86%	72%	66%	72%	74%	74%	76%	77%	73%	79%	71%	64%	76%
70.2%		73%	73%	69%	64%	75%	67%	67%	70%	69%	63%	73%	75%	69%	72%	77%	75%	66%	77%	75%	69%	56%
45.0%		40%	43%	47%	44%	44%	44%	47%	42%	47%	47%	47%	44%	51%	48%	42%	48%	44%	41%	42%	50%	44%
88.3%		100%	75%	82%	82%	91%	86%	100%	92%	92%	100%	82%	90%	100%	79%	93%	93%	86%	80%	77%	90%	84%
68.5%		75%	76%	75%	69%	22%	68%	79%	71%	73%	67%	71%	81%	76%	68%	55%	61%	59%	59%	72%	81%	80%
67.5%		63%	68%	63%	70%	76%	71%	63%	61%	76%	72%	68%	59%	58%	69%	76%	72%	68%	52%	58%	74%	81%
56.9%		56%	63%	63%	56%	54%	68%	60%	48%	60%	63%	60%	57%	63%	59%	51%	63%	47%	42%	64%	48%	50%

Model Similarity Dendrogram

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