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%3Achina C10 - Run 16403c2...

Global Dialogues GD3 - China (10 context Qs)

DTEF: Predict response distributions for China. 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.Llama 4 Maverick
76.6%
3.Claude 3.7 Sonnet
76.5%
4.Claude Haiku 4.5
76.3%
5.Mistral Large 2411
76.2%

🔀 Least Similar Models

Claude Sonnet 4.5vsGPT OSS 20b

68.8% similarity

👯 Most Similar Models

Claude 3.7 SonnetvsGPT 4.1

88.3% 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	3rd 76.5%	4th 76.3%	1st 78.3%	11th 73.4%	16th 71.0%	13th 72.2%	2nd 76.6%	5th 76.2%	6th 75.7%	8th 74.8%	10th 73.9%	15th 71.9%	9th 74.5%	17th 70.9%	14th 71.9%	12th 73.2%	20th 69.9%	21st 66.7%	7th 75.5%	18th 70.8%	19th 70.0%
80.7%	86%	81%	87%	80%	65%	72%	89%	89%	87%	86%	80%	76%	77%	85%	83%	77%	80%	67%	81%	81%	85%
69.3%	69%	60%	73%	73%	46%	71%	72%	76%	54%	73%	77%	82%	71%	77%	64%	78%	67%	62%	80%	71%	59%
82.5%	89%	78%	90%	93%	67%	83%	80%	79%	67%	88%	92%	80%	89%	80%	79%	83%	84%	84%	83%	71%	94%
87.1%	88%	85%	90%	87%	88%	84%	88%	82%	88%	90%	89%	88%	87%	83%	89%	86%	85%	83%	90%	91%	88%
88.6%	94%	88%	99%	96%	93%	91%	96%	92%	97%	85%	85%	85%	89%	81%	89%	86%	84%	93%	91%	73%	73%
79.8%	72%	80%	77%	83%	80%	82%	82%	95%	78%	80%	82%	74%	79%	74%	70%	77%	86%	79%	75%	79%	92%
83.4%	83%	83%	84%	85%	87%	84%	81%	82%	86%	85%	81%	79%	83%	85%	85%	84%	85%	85%	80%	85%	79%
71.7%	81%	79%	78%	81%	79%	53%	69%	76%	74%	83%	68%	63%	77%	61%	77%	75%	70%	72%	59%	56%	75%
76.9%	64%	70%	65%	65%	89%	76%	86%	82%	84%	74%	78%	86%	78%	81%	68%	70%	81%	86%	82%	83%	66%
86.5%	88%	84%	92%	91%	88%	88%	83%	80%	88%	87%	84%	88%	88%	88%	89%	86%	83%	81%	88%	86%	87%
67.2%	71%	72%	68%	78%	55%	85%	65%	86%	72%	56%	69%	81%	57%	50%	61%	61%	69%	54%	93%	84%	25%
82.0%	88%	86%	86%	89%	85%	79%	83%	87%	86%	82%	78%	84%	73%	81%	88%	86%	67%	60%	86%	84%	83%
57.2%	44%	66%	63%	53%	64%	81%	64%	48%	69%	49%	67%	62%	60%	79%	43%	53%	43%	34%	73%	43%	43%
79.5%	83%	84%	83%	83%	91%	65%	91%	76%	83%	80%	84%	61%	85%	62%	80%	79%	83%	80%	90%	77%	69%
73.7%	75%	83%	79%	73%	77%	68%	83%	83%	78%	83%	67%	78%	82%	64%	61%	74%	66%	75%	65%	71%	62%
72.7%	80%	70%	73%	70%	65%	64%	87%	78%	74%	79%	73%	70%	76%	74%	72%	76%	78%	50%	80%	61%	77%
72.9%	91%	89%	91%	82%	70%	62%	74%	52%	71%	76%	74%	48%	75%	65%	77%	82%	58%	60%	78%	93%	62%
71.1%	84%	78%	81%	80%	81%	49%	69%	79%	67%	81%	55%	63%	76%	59%	81%	75%	58%	50%	66%	81%	80%
55.0%	58%	49%	65%	52%	71%	36%	54%	69%	60%	62%	52%	45%	54%	49%	57%	64%	65%	50%	42%	53%	49%
84.5%	91%	88%	94%	94%	90%	78%	87%	89%	78%	94%	80%	81%	91%	81%	88%	92%	79%	48%	85%	81%	85%
63.8%	64%	68%	71%	58%	58%	67%	76%	64%	76%	60%	68%	68%	65%	75%	51%	53%	55%	51%	59%	65%	67%
73.2%	75%	81%	88%	73%	83%	70%	87%	89%	84%	66%	76%	74%	84%	75%	52%	68%	57%	62%	59%	69%	66%
78.3%	86%	74%	86%	86%	59%	68%	73%	74%	86%	78%	86%	75%	66%	49%	90%	85%	82%	89%	74%	89%	90%
64.9%	58%	73%	68%	57%	71%	91%	67%	65%	71%	58%	84%	51%	61%	77%	55%	58%	56%	57%	83%	51%	51%
75.3%	76%	70%	84%	84%	85%	68%	83%	75%	85%	74%	82%	61%	76%	60%	70%	71%	76%	81%	88%	64%	68%
66.0%	60%	73%	70%	63%	66%	66%	69%	66%	71%	63%	71%	67%	70%	70%	65%	64%	53%	59%	71%	68%	62%
66.6%	79%	74%	80%	79%	80%	42%	61%	71%	59%	78%	44%	59%	75%	49%	78%	74%	66%	60%	56%	65%	69%
68.8%	74%	79%	80%	80%	38%	63%	80%	83%	71%	80%	71%	65%	78%	64%	59%	69%	62%	39%	65%	72%	72%
86.1%	91%	91%	91%	95%	89%	90%	87%	83%	83%	82%	82%	77%	81%	80%	87%	88%	79%	85%	89%	87%	92%
80.3%	85%	80%	87%	88%	68%	87%	76%	83%	82%	86%	80%	74%	80%	75%	84%	79%	81%	76%	79%	80%	76%
68.8%	67%	80%	73%	67%	68%	75%	80%	89%	85%	65%	67%	81%	79%	75%	57%	54%	64%	51%	80%	39%	49%
62.6%	59%	70%	59%	0%	81%	65%	67%	69%	81%	61%	56%	68%	59%	67%	69%	65%	64%	64%	65%	44%	81%
69.1%	79%	69%	80%	0%	58%	73%	71%	70%	58%	78%	83%	70%	79%	71%	70%	77%	75%	75%	73%	80%	62%
82.6%	85%	84%	83%	89%	86%	78%	73%	84%	83%	84%	76%	80%	82%	80%	87%	85%	84%	84%	78%	82%	87%
53.0%	60%	72%	53%	74%	29%	49%	40%	37%	36%	45%	39%	55%	49%	43%	63%	58%	49%	54%	74%	59%	75%
55.2%	55%	56%	57%	56%	27%	65%	59%	58%	51%	53%	64%	71%	52%	71%	44%	59%	48%	44%	70%	50%	50%
59.9%	64%	59%	61%	55%	34%	81%	77%	61%	74%	53%	81%	70%	64%	71%	42%	39%	58%	57%	74%	38%	44%
82.8%	96%	90%	93%	75%	86%	90%	95%	95%	96%	89%	80%	74%	87%	72%	83%	82%	70%		79%	74%	51%
69.9%	78%	76%	81%	75%	73%	69%	81%	79%	76%	75%	75%	70%	71%	59%	65%	69%	60%	57%	59%	60%	60%
69.8%	63%	74%	63%	60%	85%	69%	72%	73%	85%	65%	60%	72%	63%	72%	73%	69%	68%	68%	69%	77%	66%
68.0%	76%	65%	76%	78%	28%	81%	73%	72%	60%	71%	69%	69%	75%	62%	72%	68%	62%	67%	67%	62%	75%
88.2%	97%	93%	92%	94%	91%	68%	82%	94%	76%	95%	90%	87%	82%	88%	92%	91%	93%	85%	86%	88%	88%
79.0%	82%	78%	74%	82%	79%	78%	82%	64%	84%	85%	78%	78%	78%	83%	83%	77%	72%	83%	82%	78%	78%

Model Similarity Dendrogram

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