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 C10 Dtef Global Dialogues Gd3 Country%3Aegypt C10 - Run 232651b...

Global Dialogues GD3 - Egypt (10 context Qs)

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

TAGS:

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Efficiency & Succinctness

Reasoning

Best Models (Coverage)

1.Claude 3.7 Sonnet
72.9%
2.Claude Sonnet 4
72.9%
3.GPT 4.1 Mini
70.8%
4.GPT 4.1
70.7%
5.GPT 4o
70.6%

🔀 Least Similar Models

Claude Sonnet 4.5vsGPT OSS 20b

66.2% similarity

👯 Most Similar Models

Mistral Large 2411vsGPT 4o

92.7% 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
Score	1st 72.9%	6th 70.5%	2nd 72.9%	9th 69.6%	20th 63.2%	17th 65.8%	10th 69.5%	13th 68.3%	11th 69.3%	4th 70.7%	3rd 70.8%	19th 63.2%	5th 70.6%	15th 66.7%	12th 69.3%	7th 70.2%	16th 66.2%	21st 62.9%	8th 69.9%	14th 68.0%	18th 63.7%
60.4%	66%	66%	71%	56%	46%	52%	64%	64%	61%	59%	64%	71%	61%	63%	55%	63%	52%	64%	67%	55%	48%
65.3%	63%	64%	67%	63%	39%	76%	55%	71%	66%	55%	76%	80%	76%	76%	55%	56%	66%	70%	90%	52%	55%
90.9%	100%	92%	100%	92%	78%	89%	92%	92%	78%	92%	100%	92%	85%	86%	92%	90%	85%	100%	92%	85%	96%
80.4%	89%	70%	70%	76%	76%	70%	87%	89%	89%	89%	89%	76%	89%	66%	70%	100%	72%	82%	89%	76%	75%
65.5%	72%	57%	80%	72%	76%	70%	80%	69%	69%	61%	61%	55%	61%	59%	58%	61%	61%	48%	72%	58%	76%
67.0%	69%	70%	69%	69%	79%	70%	62%	77%	62%	70%	70%	62%	62%	60%	69%	69%	70%	67%	62%	57%	62%
80.0%	87%	87%	87%	77%	84%	78%	80%	87%	88%	88%	84%	68%	84%	77%	77%	79%	87%	51%	76%	80%	75%
56.4%	58%	58%	66%	66%	46%	41%	54%	58%	58%	72%	63%	54%	54%	56%	56%	59%	58%	45%	52%	56%	55%
71.0%	69%	69%	69%	69%	69%	56%	61%	77%	69%	69%	77%	77%	77%	63%	76%	78%	76%	65%	73%	69%	84%
72.9%	76%	76%	79%	79%	76%	76%	66%	42%	76%	79%	76%	76%	76%	76%	67%	79%	63%	63%	76%	76%	78%
58.1%	62%	58%	60%	49%	61%	72%	67%	56%	56%	49%	60%	58%	56%	60%	60%	41%	82%	32%	92%	63%	26%
74.1%	73%	80%	80%	73%	80%	73%	68%	89%	89%	68%	75%	77%	64%	75%	68%	68%	62%	71%	89%	72%	62%
47.5%	42%	52%	56%	56%	46%	62%	48%	37%	48%	48%	67%	39%	54%	59%	37%	37%	37%	37%	62%	37%	37%
77.5%	83%	83%	84%	74%	78%	77%	82%	84%	89%	79%	83%	58%	81%	58%	79%	79%	75%	79%	84%	79%	60%
74.6%	76%	84%	73%	63%	76%	81%	66%	58%	67%	84%	92%	59%	76%	90%	71%	75%	74%	74%	92%	90%	46%
59.9%	58%	61%	62%	56%	67%	56%	63%	61%	55%	69%	62%	58%	61%	60%	67%	68%	56%	49%	53%	60%	55%
56.7%	72%	72%	68%	58%	72%	41%	56%	43%	56%	56%	58%	26%	56%	45%	63%	66%	56%	37%	56%	67%	67%
78.3%	81%	76%	76%	90%	100%	55%	66%	76%	74%	88%	72%	74%	74%	68%	92%	81%	90%	69%	59%	92%	92%
66.3%	76%	57%	72%	57%	38%	41%	76%	78%	75%	84%	76%	34%	90%	50%	76%	78%	75%	62%	57%	77%	64%
76.4%	83%	80%	80%	80%	64%	79%	75%	73%	82%	80%	73%	64%	90%	64%	83%	80%	73%	72%	75%	64%	90%
58.3%	58%	64%	70%	50%	36%	60%	70%	56%	70%	64%	72%	70%	62%	67%	49%	49%	48%	40%	60%	59%	51%
57.8%	63%	62%	62%	70%	63%	47%	62%	63%	61%	56%	47%	58%	62%	49%	60%	70%	62%	51%	42%	42%	61%
61.5%	53%	66%	53%	53%	53%	64%	66%	66%	66%	58%	58%	50%	66%	77%	66%	58%	66%	60%	66%	69%	58%
50.8%	52%	56%	56%	50%	58%	70%	52%	42%	52%	45%	56%	42%	52%	56%	37%	48%	42%	51%	66%	42%	42%
73.9%	74%	79%	85%	76%	78%	81%	85%	74%	85%	76%	83%	46%	78%	48%	72%	71%	77%	72%	78%	75%	58%
50.3%	54%	55%	55%	53%	42%	44%	49%	55%	51%	51%	44%	51%	51%	57%	40%	59%	54%	52%	50%	51%	38%
69.5%	81%	75%	79%	81%	66%	45%	70%	75%	71%	71%	44%	70%	75%	65%	77%	77%	67%	68%	60%	72%	70%
60.9%	67%	62%	62%	64%	41%	58%	65%	62%	49%	69%	70%	67%	62%	56%	67%	61%	62%	49%	48%	69%	69%
81.1%	92%	92%	83%	72%	83%	75%	79%	92%	100%	65%	85%	60%	75%	69%	83%	92%	75%	81%	100%	67%	83%
66.9%	76%	59%	76%	72%	61%	61%	77%	69%	56%	70%	75%	58%	70%	61%	69%	76%	58%	66%	59%	70%	65%
67.7%	68%	80%	75%	77%	40%	66%	77%	66%	75%	79%	63%	49%	75%	75%	77%	74%	72%	64%	61%	66%	42%
66.2%	57%	64%	57%	64%	78%	67%	64%	64%	78%	64%	57%	64%	71%	70%	71%	66%	71%	57%	64%	78%	64%
72.3%	81%	73%	81%	73%	59%	70%	73%	73%	59%	73%	81%	73%	66%	67%	66%	71%	66%	81%	73%	100%	59%
66.1%	71%	67%	71%	73%	62%	58%	64%	64%	68%	61%	64%	64%	64%	64%	80%	70%	69%	67%	53%	64%	71%
69.8%	77%	58%	69%	73%	44%	71%	64%	69%	67%	82%	64%	80%	77%	80%	77%	66%	69%	65%	62%	72%	80%
56.5%	62%	61%	66%	63%	35%	63%	59%	61%	47%	57%	61%	60%	61%	61%	51%	52%	51%	55%	59%		46%
73.8%	75%	72%	75%	63%	63%	81%	69%	53%	69%	81%	75%	63%	72%	84%	75%	75%	75%	83%	88%	91%	67%
73.8%	100%	67%	85%	78%	76%	91%	89%	85%	85%	83%	71%	56%	85%	61%	83%	83%	56%	60%	78%	39%	39%
64.6%	74%	74%	69%	70%	37%	67%	67%	67%	67%	69%	62%	69%	65%	67%	70%	70%	56%	53%	67%	59%	58%
89.7%	100%	92%	100%	92%	78%	89%	92%	92%	78%	92%	100%	92%	85%	86%	92%	90%	85%	100%	92%	78%	78%
73.8%	84%	81%	75%	84%	55%	74%	84%	80%	79%	84%	77%	69%	84%	69%	84%	81%	45%	37%	60%	80%	84%
79.2%	81%	83%	81%	88%	88%	48%	81%	81%	73%	81%	83%	73%	81%	94%	83%	78%	80%	76%	72%	83%	76%
72.4%	79%	79%	79%	79%	69%	63%	63%	49%	67%	70%	76%	77%	70%	74%	79%	73%	70%	79%	79%	67%	79%

Model Similarity Dendrogram

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