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%3Amexico C10 - Run 2dbbf4e...

Global Dialogues GD3 - Mexico (10 context Qs)

DTEF: Predict response distributions for Mexico. 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 Sonnet 4
72.4%
2.Qwen3 30b A3B Instruct 2507
72.3%
3.GPT 4.1 Mini
72.2%
4.Claude Sonnet 4.5
70.6%
5.Claude 3.7 Sonnet
70.5%

🔀 Least Similar Models

Claude Sonnet 4.5vsGPT OSS 20b

68.8% similarity

👯 Most Similar Models

GPT 4.1vsGPT 4o

90.5% 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
Score	5th 70.5%	18th 64.6%	1st 72.4%	4th 70.6%	17th 64.9%	14th 67.7%	7th 69.6%	12th 68.3%	8th 68.8%	13th 68.3%	3rd 72.2%	15th 66.4%	11th 68.6%	6th 70.2%	10th 68.7%	9th 68.8%	20th 63.7%	19th 63.9%	2nd 72.3%	16th 65.7%	21st 59.7%
66.0%	67%	65%	80%	67%	73%	62%	74%	65%	67%	80%	67%	46%	72%	72%	63%	63%	44%	50%	80%	72%	58%
63.0%	63%	65%	64%	67%	35%	65%	59%	63%	59%	51%	74%	74%	65%	71%	58%	61%	64%	74%	76%		52%
66.8%	77%	0%	77%	72%	57%	72%	72%	67%	62%	72%	77%	77%	67%	77%	67%	69%	67%	73%	67%	67%	67%
74.5%	74%	83%	82%	83%	89%	79%	75%	74%	74%	62%	76%	64%	64%	59%	74%	78%	76%	72%	82%	65%	80%
77.3%	66%	83%	76%	80%	78%	72%	76%	89%	93%	82%	82%	78%	87%	93%	65%	72%	88%	72%	69%	72%	50%
86.6%	83%	89%	77%	83%	75%	87%	89%	86%	93%	89%	83%	92%	93%	99%	92%	88%	86%	89%	92%	92%	61%
79.0%	80%	89%	83%	79%	69%	79%	76%	74%	74%	89%	75%	84%	87%	84%	77%	79%	82%	66%	74%	84%	76%
78.1%	76%	85%	88%	76%	75%	59%	81%	84%	87%	76%	85%	70%	75%	84%	81%	76%	85%	84%	81%	75%	57%
79.8%	76%	83%	88%	78%	87%	78%	93%	100%	92%	71%	88%	92%	76%	79%	73%	68%	71%	72%	93%	73%	44%
65.4%	63%	73%	77%	66%	64%	64%	58%	66%	64%	69%	59%	79%	64%	64%	66%	58%	62%	58%	64%	64%	72%
66.4%	77%	75%	77%	75%	46%	80%	82%	75%	73%	64%	67%	70%	58%	67%	63%	61%	52%	45%	77%	78%	32%
70.7%	77%	77%	76%	77%	65%	72%	74%	69%	76%	74%	72%	79%	54%	72%	80%	70%	62%	52%	79%	58%	69%
68.7%	58%	85%	76%	86%	77%	85%	70%	66%	73%	64%	83%	75%	77%	79%	65%	54%	46%	51%	81%	46%	46%
60.0%	76%	55%	65%	65%	73%	62%	71%	67%	74%	59%	67%	39%	71%	39%	59%	61%	45%	41%	67%		44%
68.7%	75%	67%	66%	71%	42%	80%	66%	52%	62%	67%	82%	73%	66%	73%	80%	82%	59%	75%	74%	70%	60%
74.2%	77%	79%	75%	69%	69%	73%	82%	79%	79%	86%	79%	56%	83%	73%	74%	75%	64%	68%	80%	74%	65%
69.2%	83%	83%	83%	72%	79%	54%	70%	55%	65%	70%	70%	54%	60%	67%	78%	78%	65%	56%	70%	65%	77%
57.6%	73%	50%	66%	64%	59%	31%	45%	56%	52%	58%	51%	60%	62%	45%	66%	65%	62%	62%	53%	59%	71%
44.5%	42%	42%	34%	34%	63%	23%	41%	42%	42%	52%	41%	34%	58%	49%	60%	74%	41%	39%	20%	52%	51%
78.3%	82%	73%	80%	82%	77%	80%	73%	75%	79%	78%	78%	80%	79%	89%	79%	78%	80%	70%	74%	80%	79%
62.4%	54%	70%	70%	58%	51%	77%	75%	63%	68%	62%	80%	48%	56%	82%	50%	60%	55%	54%	77%	63%	38%
52.3%	45%	59%	45%	45%	49%	81%	52%	51%	57%	47%	74%	66%	52%	66%	42%	52%	49%	32%	74%	32%	29%
57.8%	68%	68%	51%	55%	63%	55%	63%	64%	49%	70%	53%	42%	58%	54%	57%	60%	57%	54%	51%	56%	65%
79.1%	80%	64%	100%	86%	79%	63%	92%	88%	87%	79%	70%	67%	88%	82%	76%	87%	70%	82%	70%	76%	76%
52.5%	52%	52%	57%	52%	75%	56%	68%	61%	64%	52%	78%	37%	52%	37%	53%	50%	30%	49%	65%	37%	25%
61.2%	64%	64%	67%	57%	73%	71%	67%	58%	64%	66%	67%	65%	51%	73%	50%	50%	39%	55%	72%	78%	35%
57.6%	60%	63%	69%	66%	61%	50%	62%	61%	61%	66%	57%	38%	61%	60%	62%	59%	53%	51%	63%	41%	45%
76.2%	81%	79%	79%	88%	54%	58%	82%	74%	70%	94%	72%	69%	82%	72%	78%	94%	75%	60%	69%	79%	92%
73.7%	77%	79%	95%	95%	94%	72%	74%	77%	73%	64%	56%	68%	64%	70%	78%	70%	47%	72%	83%	73%	67%
64.7%	72%	69%	69%	72%	71%	47%	47%	72%	58%	69%	64%	61%	69%	59%	73%	62%	60%	66%	73%	61%
56.0%	57%	50%	54%	47%	49%	66%	45%	42%	52%	38%	72%	62%	45%	62%	54%	49%	60%	75%	69%	73%	55%
55.0%	51%	0%	51%	56%	72%	56%	56%	61%	67%	56%	51%	51%	61%	51%	61%	59%	61%	51%	61%	61%	61%
67.0%	77%	0%	77%	72%	57%	72%	72%	67%	62%	72%	77%	77%	67%	77%	67%	69%	67%	77%	67%	67%	67%
83.2%	93%	83%	88%	88%	55%	84%	73%	90%	83%	83%	87%	80%	83%	80%	93%	93%	87%	94%	67%	80%	83%
60.3%	67%	67%	72%	73%	31%	69%	60%	67%	52%	60%	53%	53%	67%	62%	58%	60%	51%	59%	62%	57%	66%
59.9%	65%	65%	57%	51%	35%	71%	63%	66%	53%	57%	66%	81%	54%	65%	58%	56%	42%	66%	73%	59%	54%
64.0%	76%	60%	65%	65%	59%	75%	56%	41%	56%	49%	86%	72%	56%	72%	61%	66%	70%	68%	71%	56%	65%
84.3%	83%	97%	92%	89%	86%	83%	86%	93%	89%	89%	94%	84%	93%	80%	78%	88%	78%	68%	92%	88%	40%
53.1%	48%	59%	54%	56%	38%	62%	59%	44%	51%	43%	65%	69%	48%	66%	43%	49%	51%	57%	68%	48%	38%
90.1%	89%	0%	89%	94%	89%	94%	94%	100%	95%	94%	89%	89%	100%	89%	100%	98%	100%	89%	100%	100%	100%
74.6%	82%	76%	82%	82%	68%	73%	82%	82%	80%	82%	76%	72%	76%	78%	85%	82%	87%	39%	76%	31%
61.2%	67%	65%	63%	63%	52%	41%	59%	63%	56%	59%	68%	56%	66%	62%	69%	65%	64%	66%	67%	57%	57%
79.0%	77%	88%	77%	78%	77%	79%	77%	49%	73%	72%	94%	73%	83%	83%	88%	72%	83%	94%	88%	73%	80%

Model Similarity Dendrogram

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