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 Dtef Global Dialogues Gd3 Country%3Aindia - Run d17a74d...

Global Dialogues GD3 - India

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

TAGS:

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Reasoning

Global South Agriculture & Ecology

Best Models (Coverage)

1.Claude 3.7 Sonnet
81.6%
2.Claude Sonnet 4.5
80.9%
3.Gemini 2.5 Flash
80.6%
4.Claude Sonnet 4
79.8%
5.GPT 4.1
79.7%

🔀 Least Similar Models

GPT 4.1vsGPT OSS 20b

73.2% similarity

👯 Most Similar Models

Claude Sonnet 4.5vsClaude Sonnet 4

90.4% 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 81.6%	8th 79.0%	4th 79.8%	2nd 80.9%	3rd 80.6%	21st 66.1%	11th 77.8%	9th 78.8%	12th 76.7%	5th 79.7%	13th 75.8%	17th 72.6%	10th 78.6%	14th 74.7%	6th 79.6%	7th 79.1%	18th 72.3%	20th 70.6%	19th 71.0%	15th 73.3%	16th 73.2%
81.2%	89%	87%	91%	89%	84%	60%	78%	84%	81%	80%	79%	83%	83%	79%	89%	88%	67%	84%	64%	80%	87%
77.6%	80%	74%	82%	80%	73%	88%	72%	85%	66%	73%	84%	78%	82%	86%	80%	75%	61%	86%	76%	78%	70%
68.5%	69%	66%	75%	76%	75%	71%	66%	79%	69%	75%	66%	73%	71%	66%	68%	68%	63%	60%	58%	60%	65%
55.1%	67%	49%	48%	50%	64%	52%	60%	54%	48%	64%	59%	48%	66%	69%	68%	38%	69%	33%	69%	44%	39%
91.5%	94%	94%	95%	93%	92%	93%	85%	90%	95%	93%	94%	88%	90%	91%	93%	90%	92%	87%	94%	94%	84%
80.0%	85%	82%	86%	86%	89%	61%	82%	87%	84%	84%	73%	84%	82%	70%	85%	83%	77%	85%	72%	61%	81%
89.6%	92%	89%	97%	93%	93%	83%	86%	92%	91%	87%	87%	93%	87%	79%	89%	93%	93%	93%	84%	88%	92%
71.7%	88%	73%	81%	82%	78%	36%	66%	76%	78%	87%	62%	74%	71%	65%	89%	87%	58%	48%	57%	81%	68%
80.5%	74%	83%	86%	71%	86%	69%	81%	85%	82%	85%	83%	82%	85%	87%	73%	82%	93%	79%	76%	72%	76%
55.6%	69%	49%	47%	66%	81%	52%	66%	54%	48%	61%	62%	35%	59%	61%	65%	48%	76%	33%	67%	32%	36%
86.5%	90%	87%	88%	87%	91%	89%	89%	86%	91%	89%	90%	83%	87%	83%	88%	86%	85%	78%	86%	84%	79%
56.3%	76%	61%	51%	62%	77%	43%	55%	57%	52%	68%	65%	35%	53%	60%	72%	56%	40%	55%	62%	39%	43%
81.3%	73%	91%	90%	77%	81%	77%	90%	81%	84%	73%	82%	82%	88%	86%	72%	72%	82%	79%	80%	83%	84%
80.8%	80%	83%	79%	76%	77%	91%	88%	82%	82%	71%	81%	84%	90%	86%	67%	77%	85%	72%	81%	80%	84%
83.5%	92%	89%	91%	92%	86%	62%	94%	91%	91%	96%	76%	86%	89%	79%	96%	79%	71%	71%	74%	77%	72%
82.8%	94%	90%	92%	91%	79%	64%	79%	86%	83%	89%	84%	77%	83%	81%	83%	91%	81%	67%	68%	87%	89%
63.7%	66%	68%	68%	72%	73%	52%	63%	58%	61%	63%	56%	50%	63%	56%	78%	72%	67%	57%	65%	60%	69%
72.4%	79%	80%	81%	89%	86%	40%	61%	70%	63%	82%	71%	67%	68%	60%	85%	85%	68%	82%	59%	73%	71%
72.1%	68%	72%	72%	64%	54%	49%	86%	66%	73%	82%	73%	68%	78%	58%	87%	86%	72%	80%	70%	92%	64%
80.9%	82%	81%	86%	79%	77%	90%	91%	80%	77%	72%	81%	73%	87%	80%	80%	85%	81%	72%	75%	89%	81%
82.9%	83%	91%	94%	94%	92%	54%	90%	89%	91%	84%	81%	89%	90%	75%	75%	94%	72%	73%	59%	81%	90%
81.6%	88%	85%	87%	89%	85%	63%	87%	83%	82%	88%	81%	84%	88%	81%	81%	90%	77%	80%	69%	76%	69%
76.0%	90%	81%	80%	81%	83%	64%	76%	77%	76%	79%	81%	56%	72%	76%	90%	79%	47%	82%	81%	72%	74%
85.6%	88%	90%	82%	82%	95%	72%	95%	86%	92%	77%	82%	79%	91%	91%	88%	93%	84%	81%	77%	88%	85%
83.5%	85%	85%	83%	79%	84%	92%	89%	85%	86%	75%	83%	81%	86%	86%	70%	74%	83%	88%	83%	95%	82%
76.7%	77%	76%	81%	77%	72%	65%	74%	75%	81%	74%	83%	75%	81%	81%	71%	78%	79%	77%	73%	76%	84%
66.8%	79%	69%	73%	76%	73%	44%	57%	76%	63%	75%	57%	65%	64%	55%	76%	72%	58%	76%	53%	68%	74%
72.6%	84%	79%	78%	91%	90%	40%	75%	87%	74%	89%	65%	69%	73%	57%	86%	84%	66%	52%	52%	66%	67%
58.7%	65%	59%	59%	70%	68%	41%	73%	74%	49%	58%	69%	25%	57%	62%	60%	67%	57%	58%	61%	64%	37%
71.9%	86%	77%	75%	83%	89%	69%	55%	68%	73%	81%	66%	66%	66%	80%	78%	79%	68%	40%	66%	68%	77%
82.6%	94%	90%	93%	92%	86%	62%	90%	89%	85%	85%	84%	79%	87%	78%	69%	82%	74%	83%	71%	74%	88%
80.2%	82%	83%	74%	73%	73%	77%	83%	70%	80%	74%	82%	76%	78%	82%	79%	80%	84%	89%	91%	93%	81%
64.0%	62%	62%	70%	71%	70%	67%	62%	74%	64%	70%	62%	68%	66%	62%	65%	69%	60%	56%	54%	52%	58%
74.4%	75%	74%	78%	74%	69%	75%	79%	82%	75%	75%	76%	79%	76%	76%	65%	70%	77%	64%	70%	74%	79%
75.1%	82%	81%	70%	87%	83%	61%	65%	78%	72%	85%	68%	66%	82%	88%	80%	68%	74%	78%	88%	69%	53%
80.9%	88%	88%	89%	84%	75%	72%	90%	91%	82%	79%	84%	76%	83%	79%	80%	80%	74%	77%	79%	70%	79%
80.9%	83%	88%	85%	93%	73%	57%	82%	82%	75%	93%	84%	88%	85%	74%	95%	91%	74%	75%	71%	83%	68%
87.7%	92%	90%	92%	90%	89%	95%	91%	82%	90%	92%	84%	79%	95%	72%	98%	95%	83%	86%	79%	72%	96%
71.2%	86%	79%	72%	86%	82%	47%	77%	75%	77%	87%	68%	77%	80%	60%	80%	86%	54%	60%	55%	53%	55%
95.0%	99%	94%	97%	96%	97%	100%	94%	93%	97%	97%	94%	99%	99%	94%	97%	98%	92%	88%	86%	88%	96%
73.7%	76%	69%	78%	81%	87%	71%	87%	85%	86%	86%	71%	59%	75%	73%	81%	81%	57%	27%	51%	86%	80%
72.3%	75%	77%	73%	73%	72%	62%	75%	74%	74%	76%	72%	76%	73%	77%	72%	73%	62%	72%	72%	67%	71%
74.2%	84%	81%	81%	82%	81%	70%	63%	70%	77%	74%	76%	69%	69%	70%	80%	78%	74%	74%	73%	61%	72%

Model Similarity Dendrogram

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