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%3Apakistan C5 - Run e91e4ea...

Global Dialogues GD3 - Pakistan (5 context Qs)

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

TAGS:

Instruction Following & Prompt Adherence

Reasoning

Efficiency & Succinctness

Factual Accuracy & Hallucination

Best Models (Coverage)

1.Claude 3.7 Sonnet
74.6%
2.Claude Sonnet 4
74.6%
3.Gemini 2.5 Flash
73.7%
4.Claude Sonnet 4.5
73.7%
5.GPT 5.1
73.1%

🔀 Least Similar Models

Claude Haiku 4.5vsClaude Sonnet 4.5

57.5% similarity

👯 Most Similar Models

Mistral Medium 3vsGPT 4o

89.0% 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	1st 74.6%	13th 70.6%	2nd 74.6%	4th 73.7%	3rd 73.7%	19th 66.9%	9th 72.0%	7th 72.5%	8th 72.4%	6th 72.8%	11th 71.7%	15th 68.1%	10th 71.9%	17th 67.7%	12th 70.6%	5th 73.1%	20th 66.3%	21st 65.1%	18th 67.1%	16th 67.9%	14th 69.3%
75.1%	77%	76%	77%	75%	72%	77%	79%	74%	76%	74%	76%	77%	77%	79%	73%	74%	74%	69%	72%	74%	75%
69.3%	77%	74%	73%	73%	64%	78%	73%	82%	64%	71%	78%	73%	72%	75%	75%	64%	47%	43%	73%	68%	58%
70.8%	70%	67%	81%	76%	74%	76%	70%	82%	70%	74%	72%	57%	77%	68%	67%	70%	67%	81%	63%	62%	62%
74.7%	80%	69%	76%	74%	72%	71%	76%	76%	80%	76%	72%	69%	80%	71%	82%	82%	73%	78%	58%	79%	74%
87.0%	94%	89%	90%	90%	87%	90%	90%	91%	92%	85%	87%	88%	87%	85%	82%	87%	91%	78%	96%	67%	82%
66.1%	68%	68%	66%	72%	73%	66%	63%	72%	66%	65%	73%	61%	66%	59%	66%	66%	55%	77%	62%	57%	68%
83.3%	91%	78%	89%	83%	80%	74%	85%	86%	86%	89%	86%	75%	85%	75%	91%	91%	81%	87%	79%	78%	81%
68.2%	76%	61%	73%	83%	69%	42%	71%	83%	70%	73%	68%	63%	60%	63%	73%	77%	69%	70%	69%	57%	63%
81.7%	71%	82%	82%	73%	87%	74%	79%	89%	83%	84%	80%	85%	89%	85%	72%	75%	85%	86%	83%	87%	85%
77.8%	78%	84%	78%	82%	80%	81%	79%	74%	80%	77%	85%	79%	81%	76%	79%	85%	56%	77%	82%	72%	68%
87.8%	94%	90%	91%	90%	93%	89%	94%	81%	94%	81%	91%	78%	85%	76%	88%	98%	79%	73%	98%	86%	94%
76.0%	94%	79%	79%	77%	79%	80%	80%	80%	71%	79%	78%	79%	69%	75%	80%	80%	73%	45%	70%	65%	84%
77.6%	63%	83%	72%	68%	83%	88%	76%	67%	81%	75%	89%	72%	82%	81%	76%	74%	77%	76%	84%	81%	82%
65.4%	70%	72%	68%	58%	64%	64%	73%	56%	66%	66%	67%	78%	65%	78%	52%	70%	54%	55%	72%	60%	65%
73.2%	72%	76%	78%	84%	70%	67%	77%	77%	77%	78%	69%	71%	73%	70%	67%	71%	72%	76%	70%	78%	65%
67.3%	76%	65%	79%	74%	74%	55%	66%	73%	59%	73%	65%	59%	67%	65%	76%	72%	62%	66%	63%	55%	70%
63.8%	74%	71%	75%	75%	74%	57%	74%	46%	64%	65%	66%	44%	59%	60%	74%	69%	59%	37%	62%	63%	72%
62.2%	75%	55%	73%	77%	74%	43%	56%	69%	57%	67%	60%	52%	64%	53%	66%	69%	69%	51%	56%	59%	61%
44.6%	50%	35%	46%	42%	66%	32%	52%	55%	41%	42%	45%	56%	52%	28%	59%	63%	44%	37%	27%	28%	36%
83.4%	89%	75%	87%	89%	88%	82%	87%	74%	84%	89%	86%	82%	86%	73%	85%	82%	83%	75%	87%	91%	78%
82.7%	83%	90%	88%	74%	82%	74%	86%	77%	91%	92%	83%	82%	89%	82%	84%	83%	81%		67%		83%
76.6%	83%	78%	83%	83%	78%	68%	83%	75%	74%	79%	80%	71%	81%	72%	83%	82%	72%	69%	68%	70%	77%
63.6%	56%	57%	68%	65%	67%	73%	67%	68%	67%	55%	67%	57%	63%	70%	65%	63%	65%	57%	61%	68%	56%
78.9%	83%	80%	84%	83%	84%	75%	77%	77%	79%	83%	76%	72%	84%	78%	84%	76%	76%	71%	72%	81%	82%
67.6%	70%	73%	68%	65%	62%	70%	73%	67%	67%	63%	69%	70%	64%	70%	60%	68%	70%	71%	65%	71%	63%
64.3%	68%	70%	66%	57%	72%	67%	68%	57%	64%	64%	65%	78%	69%	70%	66%	63%	56%	58%	70%	49%	54%
57.7%	62%	60%	60%	58%	65%	54%	55%	59%	57%	64%	54%	53%	60%	51%	61%	57%	52%	56%	54%	61%	58%
55.8%	65%	59%	61%	71%	85%	37%	58%	69%	63%	55%	54%	54%	51%	46%	60%	62%	42%	41%	38%	46%	55%
71.1%	85%	84%	81%	84%	81%	69%	81%	66%	71%	59%	80%	57%	64%	63%	69%	78%	61%	58%	73%	65%	65%
63.1%	73%	56%	69%	72%	73%	53%	60%	70%	70%	65%	62%	52%	64%	53%	61%	60%	58%	57%	58%	82%	58%
62.0%	66%	61%	70%	70%	60%	64%	67%	68%	65%	66%	54%	66%	62%	56%	60%	65%	62%	47%	56%	55%	63%
64.6%	62%	68%	53%	59%	61%	59%	64%	53%	64%	61%	62%	78%	58%	66%	61%	64%	59%	66%	71%	97%	71%
54.3%	53%	50%	63%	58%	56%	58%	53%	63%	53%	56%	55%	41%	59%	51%	53%	53%	58%	48%	47%	46%	66%
75.3%	77%	72%	78%	70%	85%	63%	85%	85%	78%	83%	74%	57%	75%	66%	83%	81%	84%	77%	70%	60%	79%
70.0%	72%	66%	75%	66%	41%	70%	73%	75%	74%	78%	71%	74%	80%	76%	78%	70%	73%	68%	53%	74%	62%
69.1%	79%	71%	74%	74%	75%	54%	72%	75%	70%	75%	69%	68%	65%	59%	77%	72%	49%	66%	64%	72%	72%
72.1%	73%	69%	83%	92%	67%	70%	90%	84%	82%	76%	77%	94%	79%	72%	0%	79%	62%	65%	64%	72%	64%
79.2%	89%	84%	93%	86%	77%	90%	10%	86%	90%	90%	82%	65%	90%	70%	92%	86%	65%	82%	79%	72%	86%
52.6%	65%	53%	56%	60%	57%	46%	64%	65%	52%	66%	52%	58%	60%	48%	46%	46%	39%	37%	42%	51%	42%
94.0%	98%	94%	91%	97%	99%	97%	98%	90%	98%	99%	100%	83%	96%	95%	93%	93%	94%	91%	90%	89%	89%
63.2%	61%	54%	63%	61%	76%	50%	71%	71%	76%	61%	58%	49%	62%	53%	69%	73%	66%	67%	45%	67%	74%
80.4%	84%	71%	77%	80%	85%	70%	81%	80%	83%	93%	73%	96%	81%	81%	81%	83%	78%	72%	88%	74%	77%
63.5%	63%	67%	70%	70%	59%	59%	59%	51%	64%	63%	73%	54%	61%	70%	68%	66%	57%	72%	66%	62%	59%

Model Similarity Dendrogram

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