DTeval

Loading analysis results...

Please wait while we prepare the detailed comparison.

Loading blueprint versions...

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

Analysis: Gd3 Dtef Global Dialogues Gd3 Country%3Ajapan - Run b0cac0f...

Global Dialogues GD3 - Japan

DTEF: Predict response distributions for Japan. Source: Global Dialogues GD3 (https://github.com/collect-intel/global-dialogues)

TAGS:

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

AI Safety & Robustness

Efficiency & Succinctness

Best Models (Coverage)

1.Claude 3.7 Sonnet
75.8%
2.GPT 4.1 Mini
75.1%
3.Claude Haiku 4.5
74.8%
4.Mistral Large 2411
74.7%
5.Claude Sonnet 4
74.6%

🔀 Least Similar Models

GPT 4.1vsGPT OSS 20b

74.6% similarity

👯 Most Similar Models

Claude Sonnet 4.5vsClaude Sonnet 4

91.5% similarity

View Blueprint

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

	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	1st 75.8%	3rd 74.8%	5th 74.6%	8th 74.1%	12th 71.9%	16th 71.5%	6th 74.5%	4th 74.7%	11th 72.6%	20th 67.1%	2nd 75.1%	21st 67.0%	7th 74.3%	10th 73.8%	13th 71.5%	9th 74.0%	17th 70.0%	19th 68.6%	13th 71.5%	18th 69.5%	15th 71.5%
79.6%	90%	78%	78%	82%	90%	69%	79%	78%	79%	72%	85%	86%	79%	77%	76%	79%	70%	82%	77%	82%	83%
75.2%	78%	74%	82%	78%	64%	73%	79%	70%	56%	76%	78%	77%	84%	75%	82%	80%	74%	75%	80%	66%	79%
51.3%	45%	53%	61%	53%	48%	61%	53%	57%	47%	38%	57%	55%	51%	53%	47%	53%	51%	49%	50%	44%	51%
58.6%	60%	67%	61%	55%	67%	68%	75%	66%	60%	44%	70%	33%	70%	70%	40%	62%	48%	45%	70%	52%	47%
85.2%	94%	87%	90%	84%	95%	86%	88%	80%	91%	86%	81%	81%	82%	81%	82%	87%	90%	63%	81%	88%	93%
80.0%	75%	86%	85%	91%	86%	77%	85%	77%	85%	69%	79%	78%	77%	77%	74%	89%	84%	83%	77%	78%	69%
79.7%	77%	77%	81%	75%	90%	80%	82%	75%	84%	66%	87%	82%	85%	76%	73%	77%	80%	86%	75%	83%	82%
65.5%	69%	63%	68%	65%	71%	56%	75%	69%	68%	56%	68%	74%	63%	74%	61%	67%	54%	69%	54%	70%	61%
69.9%	75%	69%	63%	69%	60%	63%	71%	75%	66%	77%	70%	74%	76%	66%	70%	84%	76%	58%	66%	71%	68%
55.6%	55%	61%	51%	63%	60%	66%	72%	59%	55%	38%	66%	27%	65%	66%	40%	46%	40%	76%	76%	47%	39%
74.6%	76%	78%	79%	88%	68%	84%	72%	84%	79%	67%	75%	75%	74%	76%	82%	73%	53%	44%	80%		85%
42.2%	43%	55%	40%	40%	54%	57%	42%	51%	43%	25%	50%	15%	40%	54%	25%	39%	34%	43%	55%	43%	39%
73.6%	78%	75%	79%	79%	78%	68%	74%	74%	83%	74%	70%	60%	72%	69%	79%	76%	76%	67%	69%	67%	79%
76.8%	73%	75%	72%	73%	81%	74%	74%	78%	79%	74%	77%	75%	80%	83%	78%	79%	81%	80%	76%	73%	77%
72.5%	84%	72%	80%	78%	77%	81%	78%	81%	75%	72%	81%	65%	73%	74%	79%	74%	70%	66%	78%	10%	75%
86.6%	90%	91%	92%	92%	81%	89%	87%	84%	83%	89%	90%	90%	90%	91%	85%	91%	83%	79%	81%	71%	90%
76.5%	84%	78%	84%	84%	84%	72%	76%	72%	71%	70%	76%	77%	70%	77%	85%	78%	69%	71%	78%	77%	74%
57.8%	64%	60%	64%	64%	53%	39%	61%	71%	64%	51%	61%	62%	58%	51%	53%	53%	43%	51%	56%	70%	65%
61.9%	63%	61%	60%	60%	61%	41%	73%	67%	62%	65%	57%	63%	63%	58%	69%	69%	69%	56%	42%	74%	67%
70.6%	73%	62%	59%	67%	81%	76%	78%	78%	76%	67%	76%	69%	74%	74%	63%	59%	68%	73%	65%	81%	64%
72.5%	82%	79%	81%	88%	74%	69%	84%	79%	76%	62%	71%	66%	74%	61%	82%	74%	60%	68%	57%	68%	67%
69.6%	74%	79%	72%	68%	73%	65%	77%	74%	72%	68%	71%	56%	78%	65%	74%	74%	73%	58%	58%	63%	70%
66.0%	74%	70%	63%	63%	75%	68%	66%	63%	71%	62%	75%	40%	68%	63%	63%	75%	72%	67%	68%	60%	59%
78.1%	87%	82%	86%	80%	66%	78%	65%	83%	74%	86%	83%	55%	77%	75%	87%	82%	79%	61%	83%	89%	82%
84.0%	91%	78%	82%	82%	85%	87%	92%	89%	93%	82%	87%	83%	88%	77%	80%	85%	82%	82%	80%	81%	77%
73.3%	70%	77%	86%	89%	76%	71%	80%	69%	73%	68%	74%	71%	73%	69%	79%	71%	67%	59%	72%	69%	76%
62.4%	74%	67%	73%	73%	63%	47%	64%	66%	61%	60%	55%	64%	60%	45%	63%	57%	57%	67%	57%	66%	72%
75.9%	72%	78%	80%	78%	74%	63%	66%	69%	74%	71%	79%	77%	81%	78%	79%	79%	75%	84%	76%	78%	83%
63.3%	64%	72%	64%	64%	64%	50%	74%	75%	55%	39%	70%	30%	71%	70%	60%	72%	63%	60%	75%	79%	58%
63.4%	57%	67%	60%	53%	74%	54%	55%	51%	63%	60%	78%	51%	58%	73%	65%	57%	79%	78%	70%	74%	55%
79.4%	82%	73%	87%	80%	74%	84%	78%	80%	79%	78%	86%	81%	84%	84%	83%	85%	66%	66%	82%	73%	83%
92.0%	98%	92%	82%	81%	98%	82%	92%	86%	98%	90%	86%	89%	94%	91%	98%	96%	94%	96%	95%	98%	95%
63.5%	57%	65%	74%	75%	59%	74%	65%	70%	59%	48%	70%	67%	63%	65%	55%	64%	68%	61%	62%	55%	57%
77.9%	81%	77%	71%	83%	78%	83%	77%	74%	86%	66%	80%	81%	73%	74%	76%	76%	89%	71%	67%	86%	86%
68.1%	75%	81%	82%	63%	53%	75%	45%	77%	70%	63%	82%	34%	82%	91%	61%	70%	69%	65%	73%	70%	49%
61.7%	72%	66%	65%	62%	26%	72%	73%	73%	54%	73%	57%	61%	61%	58%	71%	67%	63%	54%	57%	44%	66%
79.2%	88%	82%	85%	79%	77%	87%	82%	78%	87%	78%	67%	77%	89%	87%	87%	89%	68%	63%	82%	54%	77%
84.6%	82%	84%	90%	85%	87%	85%	88%	87%	85%	88%	95%	74%	87%	91%	85%	87%	75%	79%	74%	79%	89%
81.0%	92%	86%	83%	83%	60%	82%	91%	89%	77%	78%	70%	84%	86%	84%	90%	91%	71%	62%	73%	82%	87%
93.7%	91%	99%	91%	90%	93%	91%	99%	96%	92%	81%	96%	98%	97%	99%	93%	98%	97%	95%	96%	89%	87%
75.4%	75%	76%	74%	79%	68%	76%	75%	75%	68%	78%	75%	81%	75%	79%	75%	74%	79%	76%	78%	67%	80%
68.7%	86%	74%	59%	62%	71%	62%	73%	75%	69%	55%	79%	63%	71%	78%	53%	62%	73%	73%	71%	71%	62%
82.2%	91%	90%	87%	87%	75%	89%	70%	87%	81%	74%	88%	82%	79%	93%	73%	81%	78%	90%	83%	78%	71%

Model Similarity Dendrogram

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