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 f515811...

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.GPT 4.1 Mini
72.9%
2.Claude Sonnet 4
72.7%
3.Claude Haiku 4.5
72.0%
4.Qwen3 30b A3B Instruct 2507
71.3%
5.Claude 3.7 Sonnet
71.0%

🔀 Least Similar Models

Claude Sonnet 4.5vsGPT OSS 20b

69.7% similarity

👯 Most Similar Models

GPT 4.1vsGPT 4o

90.8% 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	5th 71.0%	3rd 72.0%	2nd 72.7%	6th 70.6%	18th 66.0%	15th 67.6%	7th 70.2%	14th 68.1%	10th 68.8%	11th 68.8%	1st 72.9%	16th 67.2%	13th 68.3%	9th 69.6%	12th 68.4%	8th 69.8%	17th 66.9%	21st 63.7%	4th 71.3%	20th 65.3%	19th 65.6%
65.9%	67%	65%	80%	63%	74%	62%	74%	65%	67%	80%	67%	46%	65%	67%	66%	64%	59%	53%	88%	50%	61%
60.8%	65%	65%	64%	67%	35%	63%	64%	63%	59%	48%	74%	74%	48%	71%	61%	56%	59%	53%	76%	63%	48%
70.6%	77%	67%	77%	72%	57%	72%	72%	67%	62%	77%	77%	77%	67%	77%	67%	75%	73%	73%	67%	62%	67%
73.7%	87%	82%	83%	83%	78%	64%	75%	76%	74%	62%	76%	64%	75%	62%	74%	81%	65%	64%	82%	64%	76%
78.7%	69%	83%	69%	80%	89%	64%	76%	83%	93%	88%	80%	78%	88%	83%	75%	81%	83%	85%	66%	74%	66%
88.0%	83%	89%	81%	83%	75%	92%	89%	86%	93%	89%	89%	92%	93%	99%	83%	86%	84%	87%	100%	92%	83%
80.2%	75%	89%	83%	79%	84%	85%	76%	74%	74%	87%	80%	84%	87%	84%	81%	74%	81%	76%	60%	84%	87%
78.0%	81%	85%	88%	76%	70%	59%	81%	84%	87%	75%	84%	85%	75%	89%	69%	78%	71%	79%	81%	65%	75%
82.0%	76%	83%	88%	76%	87%	78%	100%	93%	92%	71%	88%	76%	84%	79%	70%	77%	67%	73%	84%	88%	92%
64.1%	63%	73%	66%	67%	64%	64%	58%	61%	64%	67%	64%	79%	62%	64%	67%	64%	58%	47%	64%	71%	59%
72.2%	77%	75%	80%	75%	79%	80%	82%	73%	67%	64%	75%	70%	58%	56%	69%	63%	66%	60%	94%	82%	72%
73.4%	77%	77%	69%	77%	77%	79%	74%	80%	80%	74%	72%	79%	58%	79%	70%	72%	52%	69%	79%	74%	74%
68.0%	64%	85%	76%	86%	67%	89%	70%	66%	71%	64%	90%	79%	70%	79%	56%	53%	52%	38%	81%	46%	46%
60.4%	76%	55%	65%	63%	73%	60%	71%	63%	74%	63%	67%	39%	74%	39%	60%	59%	66%	43%	67%	47%	44%
69.3%	82%	67%	66%	71%	47%	75%	66%	52%	57%	71%	82%	73%	66%	73%	75%	80%	64%	79%	74%	60%	75%
74.2%	77%	79%	75%	71%	69%	66%	82%	79%	79%	87%	79%	56%	83%	73%	73%	77%	75%	54%	83%	77%	65%
66.8%	83%	83%	83%	70%	49%	53%	70%	55%	65%	60%	70%	54%	59%	67%	76%	70%	69%	43%	70%	65%	88%
57.4%	69%	56%	66%	64%	59%	31%	45%	56%	52%	52%	51%	71%	62%	50%	65%	64%	71%	49%	52%	59%	61%
44.5%	42%	34%	42%	34%	63%	36%	41%	48%	40%	52%	52%	34%	53%	34%	57%	71%	52%	39%	24%	51%	35%
78.5%	77%	73%	80%	88%	80%	80%	73%	77%	79%	79%	77%	80%	79%	86%	78%	78%	78%	73%	74%	80%	80%
62.3%	62%	70%	74%	58%	54%	70%	80%	63%	68%	61%	80%	48%	53%	78%	46%	52%	63%	49%	72%	57%	51%
53.0%	49%	59%	45%	45%	39%	80%	59%	48%	52%	49%	74%	66%	51%	66%	44%	55%	45%	43%	72%	41%	32%
57.5%	68%	68%	51%	65%	61%	50%	63%	57%	60%	63%	53%	39%	55%	54%	57%	53%	60%	58%	53%		62%
80.1%	80%	64%	100%	86%	81%	64%	92%	88%	89%	100%	64%	67%	88%	80%	81%	88%	76%	82%	70%	67%	76%
52.7%	52%	52%	57%	52%	69%	54%	68%	61%	64%	56%	78%	37%	41%	37%	47%	55%	51%	46%	66%	39%	25%
60.9%	63%	73%	67%	57%	67%	71%	72%	58%	64%	66%	66%	69%	53%	73%	58%	51%	41%	51%	72%	51%	36%
59.1%	66%	63%	74%	66%	70%	50%	62%	61%	59%	72%	57%	38%	61%	60%	58%	61%	60%	44%	63%	52%	45%
77.6%	79%	79%	79%	88%	62%	63%	82%	74%	70%	92%	79%	69%	92%	72%	78%	75%	79%	72%	69%	92%	84%
74.6%	77%	87%	95%	95%	89%	68%	74%	77%	73%	68%	56%	68%	64%	68%	79%	76%	69%	70%	77%	73%	63%
66.0%	72%	69%	69%	69%	77%	46%	47%	72%	58%	69%	69%	71%	69%	66%	74%	70%	65%	62%	69%	64%	58%
56.0%	54%	50%	54%	39%	49%	64%	45%	44%	52%	38%	72%	62%	45%	65%	54%	54%	55%	60%	69%	75%	77%
57.1%	51%	61%	51%	56%	72%	56%	56%	61%	67%	51%	51%	51%	61%	51%	61%	53%	55%	51%	61%	61%	61%
70.6%	77%	67%	77%	72%	57%	72%	72%	67%	62%	77%	77%	77%	67%	77%	72%	67%	72%	73%	67%	67%	67%
83.5%	88%	83%	88%	88%	55%	84%	73%	92%	90%	83%	87%	80%	83%	80%	87%	93%	91%	90%	58%	80%	100%
61.5%	67%	72%	72%	68%	31%	64%	60%	67%	52%	60%	53%	61%	67%	62%	61%	72%	63%	49%	62%	52%	76%
60.6%	62%	67%	75%	51%	35%	79%	63%	66%	53%	57%	63%	76%	54%	68%	52%	59%	66%	56%	72%	48%	51%
66.1%	76%	67%	65%	65%	67%	75%	56%	41%	56%	59%	83%	72%	56%	72%	76%	77%	70%	82%	77%	35%	62%
84.8%	83%	92%	89%	92%	86%	96%	86%	93%	89%	89%	88%	78%	93%	80%	84%	89%	80%	67%	83%	67%	77%
54.0%	46%	59%	54%	56%	48%	62%	59%	44%	48%	40%	65%	69%	51%	66%	53%	47%	39%	65%	59%	62%	43%
94.2%	89%	100%	89%	94%	89%	94%	94%	100%	95%	89%	89%	89%	100%	89%	100%	91%	93%	94%	100%	100%	100%
78.2%	82%	76%	82%	82%	68%	73%	82%	79%	79%	82%	76%	72%	82%	78%	79%	82%	88%	80%	76%	72%	72%
61.6%	68%	64%	63%	67%	56%	41%	59%	57%	56%	59%	68%	56%	63%	62%	67%	67%	67%	67%	56%	63%	68%
79.5%	77%	88%	77%	78%	81%	79%	77%	56%	73%	68%	94%	83%	83%	79%	83%	91%	83%	92%	77%	71%	80%

Model Similarity Dendrogram

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