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%3Acanada - Run 19eac49...

Global Dialogues GD3 - Canada

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

TAGS:

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Reasoning

Efficiency & Succinctness

Best Models (Coverage)

1.Claude Haiku 4.5
77.1%
2.Claude 3.7 Sonnet
76.5%
3.Claude Sonnet 4.5
76.5%
4.Claude Sonnet 4
74.8%
5.Grok 4.1 Fast
74.4%

🔀 Least Similar Models

GPT 4.1vsGPT OSS 20b

75.8% 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	2nd 76.5%	1st 77.1%	4th 74.8%	3rd 76.5%	10th 74.0%	18th 70.3%	15th 72.1%	8th 74.1%	17th 71.7%	11th 74.0%	9th 74.1%	21st 67.6%	13th 72.9%	7th 74.2%	12th 73.8%	6th 74.3%	14th 72.4%	19th 68.0%	16th 71.9%	20th 67.9%	5th 74.4%
83.7%	87%	86%	88%	92%	88%	63%	89%	93%	85%	87%	81%	85%	84%	77%	88%	84%	82%	79%	79%	70%	91%
79.7%	85%	81%	85%	85%	73%	85%	83%	82%	65%	84%	82%	77%	82%	81%	80%	78%	81%	69%	78%	80%	77%
67.2%	61%	66%	72%	69%	76%	72%	62%	72%	63%	75%	69%	72%	59%	70%	66%	69%	66%	66%	61%	59%	66%
66.1%	67%	68%	68%	64%	69%	65%	77%	67%	60%	57%	66%	65%	69%	69%	58%	65%	60%	70%	69%	64%	72%
87.4%	90%	90%	97%	98%	84%	77%	94%	88%	88%	91%	81%	85%	81%	82%	91%	81%	74%	90%	86%	90%	98%
90.1%	91%	95%	89%	94%	96%	81%	91%	91%	91%	92%	85%	96%	92%	84%	87%	92%	98%	98%	82%	77%	91%
79.4%	79%	79%	79%	77%	75%	77%	82%	82%	88%	78%	78%	78%	84%	79%	76%	80%	79%	77%	76%	82%	82%
70.0%	85%	73%	71%	70%	85%	51%	71%	69%	70%	80%	65%	65%	71%	71%	74%	78%	71%	62%	55%	68%	64%
80.3%	78%	78%	76%	76%	89%	76%	84%	82%	88%	82%	78%	80%	77%	78%	76%	83%	83%	81%	82%	83%	77%
63.7%	60%	82%	46%	57%	66%	74%	71%	67%	58%	53%	76%	25%	63%	75%	50%	59%	72%	81%	77%	69%	57%
70.6%	75%	74%	72%	65%	73%	72%	72%	68%	76%	73%	70%	68%	76%	74%	72%	70%	65%	57%	71%	72%	68%
49.9%	56%	68%	41%	52%	52%	54%	51%	51%	45%	39%	57%	27%	52%	58%	48%	51%	62%	50%	56%	32%	46%
67.6%	69%	71%	75%	75%	67%	78%	55%	72%	59%	75%	70%	44%	64%	75%	72%	72%	61%	59%	68%	64%	74%
77.0%	78%	84%	77%	82%	73%	82%	80%	77%	71%	75%	81%	78%	77%	78%	79%	80%	66%	69%	78%	72%	80%
58.2%	63%	63%	64%	63%	57%	53%	67%	65%	60%	58%	56%	58%	60%	60%	59%	56%	60%	55%	46%	48%	52%
70.3%	75%	71%	74%	78%	79%	55%	64%	73%	67%	71%	72%	68%	70%	70%	75%	72%	70%	68%	62%	70%	72%
84.4%	86%	92%	86%	86%	84%	86%	69%	73%	88%	89%	79%	86%	81%	82%	92%	96%	88%	71%	86%	78%	94%
59.3%	62%	63%	60%	64%	68%	39%	55%	58%	55%	52%	66%	62%	59%	59%	55%	60%	66%	64%	58%		61%
71.7%	86%	81%	69%	71%	56%	66%	77%	82%	70%	74%	67%	57%	81%	80%	58%	71%	79%	73%	80%	65%	62%
74.9%	82%	77%	81%	85%	74%	80%	73%	77%	65%	79%	74%	78%	73%	74%	77%	78%	64%	56%	71%	79%	75%
70.8%	78%	74%	82%	82%	75%	70%	72%	73%	72%	82%	67%	62%	66%	69%	72%	66%	70%	45%	64%	69%	76%
84.7%	86%	88%	83%	89%	80%	83%	83%	83%	83%	92%	87%	72%	90%	90%	88%	95%	85%	69%	82%	80%	91%
72.0%	80%	75%	80%	84%	72%	70%	62%	76%	69%	68%	81%	58%	67%	67%	80%	74%	69%	57%	79%	60%	83%
63.5%	73%	71%	69%	80%	60%	75%	54%	69%	60%	71%	71%	43%	60%	65%	73%	71%	67%	51%	69%	10%	72%
78.5%	82%	91%	77%	79%	77%	84%	75%	74%	72%	70%	76%	78%	74%	89%	76%	79%	69%	74%	87%	78%	87%
66.1%	71%	60%	66%	68%	69%	67%	58%	57%	65%	78%	74%	56%	66%	73%	75%	73%	69%	58%	69%	53%	64%
67.8%	71%	70%	68%	71%	76%	56%	63%	68%	70%	71%	66%	67%	66%	61%	69%	72%	70%	66%	66%	66%	71%
69.0%	72%	70%	73%	76%	79%	42%	69%	71%	73%	74%	71%	57%	70%	60%	79%	76%	70%	71%	57%	69%	70%
62.7%	68%	72%	64%	71%	64%	58%	56%	60%	47%	53%	71%	43%	62%	68%	64%	64%	63%	65%	71%	66%	66%
67.3%	63%	74%	71%	75%	65%	67%	56%	58%	73%	66%	80%	75%	65%	73%	65%	67%	73%	31%	72%	76%	69%
73.6%	83%	78%	82%	80%	82%	67%	77%	75%	73%	82%	69%	66%	72%	77%	75%	76%	63%	59%	69%	65%	76%
73.8%	75%	75%	69%	72%	65%	69%	79%	69%	78%	66%	72%	69%	82%	71%	72%	72%	75%	75%	80%	82%	82%
66.9%	62%	66%	72%	69%	76%	72%	62%	72%	63%	75%	69%	72%	59%	70%	69%	66%	66%	66%	61%	59%	59%
87.0%	92%	82%	90%	91%	90%	72%	83%	97%	97%	98%	91%	71%	86%	71%	93%	88%	95%	87%	82%	75%	95%
67.4%	73%	78%	69%	69%	55%	62%	57%	65%	64%	57%	69%	60%	78%	78%	60%	64%	65%	85%	79%	72%	56%
59.3%	62%	67%	65%	57%	61%	69%	61%	67%	52%	57%	56%	62%	58%	62%	57%	54%	58%	51%	60%	45%	64%
76.2%	85%	75%	79%	87%	82%	78%	83%	78%	79%	79%	72%	74%	77%	79%	78%	78%	62%	60%	73%	64%	78%
89.2%	87%	95%	93%	93%	90%	94%	87%	91%	94%	91%	88%	79%	91%	91%	97%	96%	84%	85%	83%	74%	91%
69.2%	80%	76%	75%	75%	80%	61%	77%	71%	69%	70%	65%	69%	68%	69%	72%	70%	71%	45%	56%	65%	70%
95.7%	93%	100%	94%	97%	90%	94%	96%	94%	97%	90%	97%	94%	93%	96%	100%	97%	100%	99%	95%	96%	97%
78.0%	83%	82%	80%	75%	66%	77%	76%	84%	73%	82%	84%	76%	82%	79%	79%	76%	77%	75%	74%	76%	82%
59.0%	63%	62%	56%	57%	61%	61%	61%	62%	57%	59%	62%	62%	62%	62%	52%	60%	58%	62%	53%	53%	54%
88.7%	94%	92%	90%	90%	84%	87%	85%	85%	91%	86%	94%	89%	84%	95%	95%	88%	87%	93%	89%	78%	87%

Model Similarity Dendrogram

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