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 C5 Dtef Global Dialogues Gd3 Country%3Abrazil C5 - Run c064915...

Global Dialogues GD3 - Brazil (5 context Qs)

DTEF: Predict response distributions for Brazil. 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
78.3%
2.Claude 3.7 Sonnet
77.9%
3.GPT 4.1 Mini
77.6%
4.Claude Haiku 4.5
77.4%
5.GPT 5
76.8%

🔀 Least Similar Models

Claude Haiku 4.5vsClaude Sonnet 4.5

66.1% similarity

👯 Most Similar Models

GPT 4.1 NanovsGPT 4o Mini

91.0% 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 77.9%	4th 77.4%	1st 78.3%	6th 76.7%	9th 75.6%	18th 71.3%	11th 74.0%	16th 72.1%	13th 73.6%	8th 75.8%	3rd 77.6%	17th 71.5%	9th 75.6%	14th 73.4%	5th 76.8%	7th 76.4%	19th 70.3%	21st 65.2%	12th 73.7%	20th 69.1%	15th 72.5%
75.8%	72%	78%	82%	71%	77%	64%	84%	85%	80%	77%	83%	74%	77%	83%	76%	72%	75%	58%	76%	66%	82%
71.5%	70%	75%	71%	71%	67%	69%	73%	65%	69%	70%	76%	70%	76%	71%	72%	72%	72%	76%	75%	73%	69%
74.6%	77%	68%	78%	77%	70%	72%	68%	70%	70%	77%	78%	74%	74%	70%	79%	68%	89%	74%	58%	100%	75%
89.3%	95%	90%	89%	89%	85%	86%	90%	86%	86%	95%	97%	95%	89%	85%	89%	90%	90%	91%	78%	85%	95%
86.5%	92%	89%	85%	92%	93%	89%	93%	85%	94%	85%	84%	87%	90%	85%	85%	94%	87%	74%	89%	72%	72%
85.8%	96%	92%	93%	93%	88%	86%	83%	81%	80%	87%	90%	80%	83%	77%	89%	92%	81%	75%	85%	81%	90%
84.3%	93%	94%	90%	91%	96%	80%	91%	92%	96%	88%	88%	89%	87%	82%	88%	86%	79%	46%	89%	49%	77%
77.0%	83%	81%	74%	89%	77%	47%	76%	90%	87%	81%	77%	80%	80%	76%	86%	87%	49%	62%	75%	72%	88%
80.7%	87%	84%	85%	92%	77%	68%	82%	75%	76%	81%	88%	83%	92%	88%	84%	77%	76%	69%	84%	88%	58%
90.7%	86%	91%	95%	92%	89%	93%	92%	87%	92%	97%	93%	95%	92%	87%	92%	97%	79%	83%	93%		90%
78.0%	92%	82%	82%	87%	67%	93%	85%	88%	82%	66%	74%	71%	67%	68%	79%	72%	62%	62%	90%	88%	81%
83.8%	96%	85%	80%	93%	86%	85%	84%	83%	78%	84%	87%	86%	85%	81%	86%	86%	82%	70%	80%	78%	85%
68.0%	59%	75%	64%	72%	72%	80%	65%	60%	70%	66%	76%	52%	73%	68%	68%	66%	65%	50%	81%	75%	71%
59.5%	69%	64%	57%	55%	65%	71%	66%	60%	60%	59%	65%	66%	74%	64%	60%	52%	45%	47%	67%	33%	51%
68.9%	76%	74%	69%	67%	71%	72%	63%	56%	60%	72%	68%	55%	66%	68%	79%	80%	74%	73%	72%	55%	77%
78.2%	78%	83%	84%	81%	81%	62%	79%	81%	79%	82%	79%	73%	82%	79%	80%	78%	78%	70%	78%	75%	80%
59.8%	66%	79%	81%	63%	42%	53%	60%	48%	59%	58%	60%	43%	51%	51%	69%	73%	51%	57%	60%	64%	68%
66.0%	75%	66%	75%	80%	73%	39%	54%	72%	65%	72%	58%	59%	70%	55%	72%	72%	73%	57%	61%	68%	71%
42.9%	50%	31%	51%	43%	60%	27%	42%	38%	43%	44%	45%	34%	36%	41%	68%	71%	37%	34%	29%	35%	41%
72.0%	77%	82%	75%	73%	67%	77%	78%	61%	68%	69%	83%	71%	68%	71%	78%	74%	53%	67%	80%	75%	64%
74.0%	77%	80%	82%	74%	80%	74%	81%	66%	77%	77%	84%	78%	76%	79%	68%	67%	66%	61%	78%	73%	55%
68.7%	67%	75%	78%	65%	67%	75%	66%	64%	68%	75%	77%	61%	71%	72%	63%	63%	76%	61%	76%	71%	51%
71.6%	67%	71%	71%	64%	82%	74%	66%	74%	75%	66%	77%	79%	77%	79%	72%	68%	68%	69%	68%	73%	63%
79.8%	84%	86%	86%	74%	88%	75%	77%	77%	83%	89%	84%	71%	85%	84%	84%	85%	81%	62%	76%	84%	60%
56.0%	56%	69%	58%	46%	61%	71%	56%	47%	56%	54%	70%	51%	59%	63%	50%	48%	46%	44%	66%	61%	43%
65.7%	64%	66%	62%	69%	75%	71%	62%	60%	70%	68%	68%	81%	72%	69%	53%	68%	52%	70%	70%	49%	61%
72.1%	76%	74%	82%	81%	73%	53%	65%	74%	68%	80%	69%	73%	75%	69%	78%	78%	67%	65%	69%	73%	73%
79.8%	91%	80%	84%	85%	90%	54%	82%	81%	87%	87%	74%	76%	76%	69%	90%	86%	82%	76%	73%	73%	80%
73.6%	85%	85%	83%	95%	73%	66%	81%	65%	69%	68%	77%	70%	68%	72%	73%	75%	66%	63%	72%	69%	71%
70.0%	79%	75%	83%	83%	82%	42%	57%	74%	70%	75%	74%	59%	68%	69%	70%	75%	68%	59%	72%	68%	69%
55.3%	56%	53%	55%	49%	63%	68%	48%	47%	49%	49%	62%	42%	53%	58%	59%	63%	60%	61%	64%	35%	67%
61.1%	56%	67%	56%	57%	64%	62%	66%	64%	64%	57%	56%	60%	60%	64%	54%	62%	60%	60%	77%	59%	59%
83.3%	86%	77%	88%	86%	79%	82%	77%	79%	79%	86%	88%	83%	83%	79%	83%	85%	97%	90%	66%	90%	86%
74.6%	74%	78%	82%	77%	80%	75%	83%	86%	75%	85%	81%	73%	81%	70%	80%	81%	45%	45%	66%	74%	75%
77.0%	75%	63%	82%	70%	86%	78%	87%	87%	78%	74%	84%	60%	77%	77%	87%	87%	84%	76%	54%	81%	70%
74.4%	72%	80%	77%	73%	56%	81%	71%	70%	76%	72%	70%	83%	79%	81%	63%	71%	83%	67%	80%	78%	79%
76.5%	86%	79%	79%	70%	83%	85%	68%	53%	70%	85%	83%	61%	77%	76%	87%	79%	76%	72%	76%	75%	86%
85.5%	100%	93%	96%	95%	82%	98%	89%	93%	87%	94%	88%	73%	95%	68%	96%	94%	64%	63%	93%	43%	92%
72.0%	79%	76%	80%	80%	71%	68%	74%	66%	68%	79%	71%	70%	72%	68%		73%	67%	69%	67%	66%	76%
91.0%	98%	88%	99%	97%	90%	93%	88%	90%	90%	97%	99%	94%	94%	90%	96%	88%	91%	94%	77%	79%	79%
81.2%	90%	91%	90%	87%	81%	85%	86%	90%	80%	79%	87%	86%	87%	89%	83%	78%	85%	47%	83%	45%	77%
77.5%	80%	83%	80%	80%	72%	55%	77%	76%	70%	81%	87%	78%	83%	89%	81%	78%	78%	62%	80%		80%
70.9%	64%	76%	74%	70%	71%	67%	65%	53%	61%	73%	76%	76%	72%	74%	77%	76%	63%	72%	67%	81%	81%

Model Similarity Dendrogram

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