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%3Aindia C10 - Run 52b4b5c...

Global Dialogues GD3 - India (10 context Qs)

DTEF: Predict response distributions for India. 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
83.2%
2.GPT 5.1
83.0%
3.Claude Sonnet 4
82.9%
4.GPT 4.1
82.3%
5.GPT 5
82.2%

🔀 Least Similar Models

Claude Sonnet 4.5vsGPT OSS 20b

66.6% similarity

👯 Most Similar Models

Claude 3.7 SonnetvsGPT 4.1

87.5% 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	1st 83.2%	6th 81.7%	3rd 82.9%	16th 76.2%	8th 81.0%	21st 70.2%	11th 79.3%	7th 81.5%	9th 80.0%	4th 82.3%	12th 78.7%	17th 76.1%	10th 79.7%	18th 74.8%	5th 82.2%	2nd 83.0%	13th 77.5%	19th 74.8%	15th 76.7%	14th 76.9%	20th 73.1%
82.7%	85%	87%	90%	90%	88%	65%	78%	86%	81%	84%	80%	81%	86%	79%	88%	87%	87%	83%	80%	81%	70%
80.4%	78%	72%	82%	82%	58%	91%	77%	86%	70%	82%	87%	86%	90%	89%	75%	86%	83%	62%	87%	86%	79%
63.2%	76%	63%	57%	0%	66%	69%	57%	67%	57%	77%	71%	73%	66%	69%	64%	69%	69%	69%	60%	64%	64%
91.0%	90%	88%	90%	97%	92%	92%	93%	88%	87%	96%	88%	97%	94%	87%	94%	88%	89%	87%	91%	94%	89%
91.2%	87%	95%	89%	92%	95%	92%	95%	96%	95%	95%	96%	92%	91%	99%	92%	95%	91%	73%	83%	93%	80%
80.3%	92%	90%	87%	86%	90%	86%	82%	87%	87%	83%	82%	68%	83%	69%		83%	81%	65%	83%	69%	54%
79.2%	82%	80%	83%	82%	78%	73%	74%	84%	80%	83%	82%	77%	81%	80%	78%	81%	82%	89%	75%	76%	63%
74.5%	88%	75%	77%	86%	76%	44%	69%	80%	83%	82%	62%	70%	74%	68%	92%	81%	86%	63%	63%	79%	67%
80.0%	73%	89%	79%	79%	89%	62%	79%	85%	80%	90%	85%	82%	84%	85%	76%	78%	85%	76%	76%	74%	74%
94.3%	97%	97%	96%	96%	97%	97%	92%	89%	97%	97%	95%	97%	96%	97%	94%	91%	83%	83%	97%	96%	96%
83.9%	84%	89%	93%	91%	78%	85%	87%	77%	89%	83%	88%	90%	77%	76%	85%	75%	77%	77%	79%	89%	92%
84.0%	91%	86%	93%	93%	92%	86%	91%	95%	92%	87%	79%	95%	62%	73%	88%	92%	82%	59%	91%	75%	62%
82.7%	73%	87%	79%	78%	78%	80%	83%	84%	85%	82%	89%	86%	89%	87%	83%	84%	81%	84%	82%	81%	81%
90.0%	94%	86%	89%	88%	95%	79%	86%	97%	96%	91%	91%	78%	95%	78%	90%	97%	89%	95%	95%	93%	89%
84.0%	91%	85%	94%	94%	84%	63%	93%	95%	91%	85%	80%	90%	82%	74%	93%	91%	90%	58%	69%	77%	85%
78.9%	86%	84%	90%	86%	75%	65%	78%	80%	81%	81%	73%	73%	82%	69%	90%	83%	91%	64%	81%	82%	63%
61.1%	70%	69%	72%	69%	55%	54%	65%	43%	61%	63%	52%	54%	61%	53%	67%	65%	55%	50%	69%	62%	74%
70.6%	89%	67%	86%	86%	78%	45%	58%	77%	69%	77%	59%	65%	67%	53%	78%	70%	83%	70%	68%	66%	72%
68.3%	67%	56%	61%	55%	80%	49%	60%	77%	73%	81%	62%	43%	77%	73%	89%	95%	64%	66%	50%	80%	76%
77.5%	76%	79%	80%	81%	89%	73%	84%	76%	72%	84%	74%	69%	78%	72%	80%	84%	75%	69%	76%	71%	85%
84.7%	86%	88%	94%	88%	90%	66%	87%	94%	88%	86%	86%	93%	83%	78%	86%	90%	93%	85%	70%	80%	68%
79.8%	80%	77%	85%	85%	88%	60%	84%	85%	84%	82%	77%	79%	80%	73%	78%	82%	84%	87%	71%	83%	72%
76.0%	76%	70%	81%	78%	85%	85%	82%	84%	67%	75%	84%	60%	77%	66%	73%	74%	73%	74%	85%	74%	73%
87.4%	82%	86%	82%	82%	94%	77%	88%	91%	89%	87%	91%	83%	90%	92%	89%	93%	88%	88%	87%	88%	88%
84.3%	85%	89%	86%	85%	92%	84%	90%	91%	92%	86%	94%	71%	90%	71%	84%	93%	62%	79%	89%	94%	63%
74.5%	78%	77%	73%	73%	81%	66%	71%	70%	79%	75%	83%	77%	77%	73%	72%	77%	79%	79%	77%	75%	53%
65.8%	79%	70%	80%	78%	76%	43%	62%	68%	63%	68%	55%	64%	65%	61%	73%	70%	65%	61%	65%	64%	52%
72.9%	85%	80%	80%	80%	84%	43%	77%	78%	82%	77%	72%	62%	70%	60%	90%	89%	67%	74%	57%	70%	54%
74.4%	82%	94%	83%	94%	80%	64%	78%	69%	68%	64%	68%	75%	65%	64%	85%	81%	64%	71%	69%	69%	75%
75.2%	89%	76%	86%	88%	77%	61%	61%	85%	75%	84%	76%	58%	73%	70%	85%	80%	51%	91%	84%	70%	60%
80.6%	89%	82%	93%	93%	91%	63%	91%	87%	89%	84%	76%	75%	84%	74%	78%	75%	83%	63%	69%		73%
79.0%	78%	86%	93%	0%	83%	80%	93%	82%	93%	72%	77%	75%	83%	80%	81%	80%	80%	80%	89%	88%	85%
58.3%	64%	59%	52%	0%	62%	64%	52%	62%	52%	72%	67%	68%	62%	64%	60%	64%	64%	64%	55%	59%	59%
75.9%	83%	78%	78%	79%	65%	70%	77%	79%	78%	83%	70%	71%	76%	68%	76%	81%	79%	78%	72%	73%	79%
83.1%	89%	97%	98%	96%	85%	69%	75%	73%	72%	81%	72%	86%	80%	80%	82%	92%	73%	76%	94%	88%	88%
84.1%	91%	91%	94%	95%	81%	67%	90%	94%	87%	91%	85%	79%	85%	72%	82%	92%	83%	71%	76%	83%	78%
82.1%	84%	89%	84%	89%	88%	67%	84%	84%	83%	83%	76%	88%	80%	75%	89%	81%	82%	88%	75%	78%	78%
84.4%	90%	90%	93%	79%	73%	93%	95%	93%	98%	94%	94%	77%	97%	85%	94%	90%	68%	88%	90%	46%	46%
75.8%	94%	83%	82%	84%	80%	58%	82%	87%	77%	91%	71%	62%	86%	59%	87%	85%	70%	66%	61%	57%	69%
88.4%	94%	91%	84%	0%	94%	97%	84%	95%	84%	95%	100%	99%	94%	97%	92%	96%	96%	96%	87%	91%	91%
74.7%	77%	75%	71%	70%	78%	59%	81%	81%	86%	71%	82%	60%	71%	72%	76%	79%	71%	73%	77%	74%	84%
77.2%	83%	80%	77%	80%	72%	67%	80%	78%	73%	85%	72%	76%	82%	84%	78%	76%	77%	68%	76%	79%	79%
65.6%	71%	81%	70%	70%	49%	65%	67%	45%	53%	71%	81%	68%	62%	69%	67%	72%	57%	73%	67%	58%	62%

Model Similarity Dendrogram

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