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 Ctx Dtef Global Dialogues Gd3 Country%3Achina Ctx - Run 353a509...

Global Dialogues GD3 - China (with context)

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

Knowledge, learning and memory

Best Models (Coverage)

1.Claude Sonnet 4.5
81.0%
2.Claude 3.7 Sonnet
80.2%
3.Claude Sonnet 4
80.0%
4.GPT 5
79.0%
5.Mistral Large 2411
78.5%

🔀 Least Similar Models

Claude Sonnet 4.5vsGPT OSS 20b

68.0% similarity

👯 Most Similar Models

GPT 4.1 NanovsQwen3 30b A3B Instruct 2507

88.0% 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
Score	2nd 80.2%	6th 78.2%	3rd 80.0%	1st 81.0%	15th 75.7%	18th 74.7%	13th 75.9%	5th 78.5%	10th 77.1%	7th 78.0%	16th 75.5%	21st 70.6%	11th 76.8%	19th 74.3%	4th 79.0%	8th 77.5%	12th 76.4%	20th 74.3%	17th 75.3%	9th 77.5%	14th 75.8%
86.2%	87%	87%	88%	92%	78%	86%	96%	91%	93%	83%	91%	88%	88%	67%	83%	85%	83%	84%	88%	92%	80%
82.0%	77%	84%	85%	94%	77%	83%	83%	77%	71%	78%	83%	88%	80%	89%	90%	80%	81%	90%	85%	81%	65%
64.5%	76%	76%	76%	76%	53%	49%	66%	66%	53%	68%	76%	49%	49%	90%	68%	68%	68%	53%	53%	53%	68%
86.5%	88%	86%	90%	89%	90%	87%	88%	84%	89%	90%	90%	88%	87%	78%	85%	80%	85%	83%	88%	86%	86%
90.6%	93%	87%	91%	96%	87%	87%	99%	95%	87%	92%	87%	87%	87%	87%	99%	94%	90%	87%	87%	87%	96%
78.7%	82%	81%	77%	81%	84%	83%	76%	93%	80%	75%	76%	69%	78%	74%	79%	75%	80%	80%	72%	74%	83%
71.5%	79%	76%	75%	82%	70%	48%	71%	78%	67%	69%	63%	62%	70%	64%	86%	85%	86%	70%	62%	68%	70%
58.8%	64%	57%	69%	58%	54%	33%	56%	80%	52%	64%	64%	55%	53%	45%	68%	64%	62%	56%	61%	59%	61%
72.3%	64%	60%	75%	65%	55%	73%	80%	83%	85%	74%	79%	64%	78%	65%	66%	74%	70%	78%	77%	81%	73%
85.1%	88%	88%	92%	91%	88%	88%	80%	64%	88%	88%	79%	85%	88%	88%	90%	86%	87%	67%	88%	87%	87%
68.1%	84%	86%	84%	74%	62%	77%	68%	86%	61%	61%	81%	68%	66%	51%	62%	61%	57%	47%	84%	85%	25%
83.2%	88%	86%	86%	89%	85%	68%	86%	82%	87%	86%	83%	84%	87%	81%	86%	87%	83%	65%	86%	79%	83%
84.0%	83%	91%	87%	86%	86%	86%	87%	86%	89%	87%	86%	86%	78%	86%	84%	80%	77%	71%	86%	78%
87.1%	86%	89%	87%	82%	89%	87%	87%	93%	95%	86%	89%	75%	89%	81%	91%	92%	88%	85%	89%	89%	81%
76.8%	77%	79%	78%	77%	76%	70%	77%	77%	75%	76%	75%	76%	76%	74%	80%	77%	77%	79%	76%	80%	80%
79.3%	76%	78%	77%	77%	75%	91%	86%	77%	82%	84%	80%	68%	87%	70%	81%	81%	85%	79%	82%	72%	78%
72.3%	84%	85%	88%	89%	77%	66%	59%	52%	66%	78%	77%	72%	65%	69%	78%	78%	66%	46%	77%	72%	75%
85.4%	89%	88%	88%	88%	85%	88%	82%	83%	87%	78%	83%	67%	86%	82%	89%	89%	92%	86%	82%	90%	92%
56.0%	53%	49%	61%	52%	61%	48%	58%	52%	59%	57%	57%	38%	57%	70%	56%	58%	58%	64%	46%	72%	51%
77.5%	95%	64%	79%	87%	93%	84%	83%	76%	83%	92%	43%	43%	93%	91%	67%	70%	58%	82%	88%	80%	76%
76.1%	75%	76%	80%	80%	78%	72%	80%	77%	77%	84%	77%	81%	81%	77%	76%	70%	82%	65%	75%	74%	62%
84.4%	91%	82%	89%	88%	78%	68%	84%	88%	87%	81%	80%	86%	86%	82%	82%	84%	89%	82%	83%	85%	97%
74.4%	88%	77%	89%	89%	68%	55%	74%	75%	76%	70%	74%	89%	49%	50%	81%	84%	58%	80%	62%	85%	90%
84.0%	86%	81%	87%	84%	88%	82%	84%	85%	89%	85%	91%	86%	87%	86%	82%	87%	83%	86%	86%	86%	53%
85.7%	90%	88%	84%	87%	86%	89%	78%	90%	86%	86%	83%	83%	88%	90%	89%	87%	82%	87%	85%	90%	71%
67.0%	72%	77%	73%	76%	67%	58%	72%	67%	63%	69%	70%	66%	61%	56%	63%	66%	59%	58%	74%	66%	73%
67.3%	77%	61%	72%	72%	80%	73%	56%	75%	67%	69%	47%	53%	67%	56%	71%	71%	74%	88%	60%	52%	73%
80.1%	80%	80%	80%	80%	88%	62%	82%	86%	86%	85%	74%	80%	82%	68%	89%	85%	83%	77%	74%	81%
86.6%	87%	90%	91%	95%	90%	87%	84%	87%	82%	85%	89%	89%	84%	80%	91%	83%	89%	88%	89%	82%	77%
83.9%	87%	84%	86%	91%	95%	75%	88%	86%	86%	88%	80%	77%	81%	81%	85%	84%	88%	79%	78%	83%	80%
84.4%	84%	87%	91%	88%	57%	80%	89%	85%	93%	90%	83%	81%	91%	81%	86%	85%	85%	81%	81%	89%	85%
59.1%	63%	44%	45%	56%	49%	95%	41%	83%	73%	63%	73%	49%	49%	49%	63%	63%	63%	45%	49%	63%	63%
59.1%	57%	57%	42%	65%	90%	90%	10%	55%	55%	57%	42%	41%	90%	90%	57%	54%	57%	90%	41%	45%	57%
82.0%	84%	73%	83%	87%	94%	77%	76%	83%	81%	79%	76%	80%	77%	79%	85%	86%	87%	91%	75%	83%	85%
50.0%	60%	86%	69%	55%	19%	41%	42%	38%	29%	35%	43%	55%	43%	49%	59%	50%	51%	46%	56%	52%	72%
68.4%	69%	72%	66%	66%	63%	82%	76%	56%	57%	66%	60%	60%	73%	81%	67%	66%	64%	70%	78%	69%	75%
78.9%	76%	84%	81%	82%	76%	89%	81%	73%	80%	75%	81%	81%	81%	84%	72%	66%	80%	78%	80%	75%	81%
92.2%	95%	89%	96%	96%	94%	83%	94%	95%	98%	94%	96%	87%	95%	87%	93%	96%	95%	91%	87%	93%	83%
77.8%	86%	79%	84%	86%	66%	59%	79%	80%	70%	85%	78%	68%	89%	69%	83%	75%	80%	71%	74%	82%	90%
66.7%	69%	69%	53%	68%	95%	95%	69%	82%	77%	69%	53%	45%	53%	53%	69%	69%	69%	53%	53%	69%	69%
79.8%	87%	81%	87%	81%	58%	80%	84%	88%	83%	91%	82%	52%	83%	66%	90%	88%	73%	70%	72%	93%	87%
87.0%	89%	92%	92%	94%	89%	62%	87%	90%	83%	92%	91%	58%	85%	92%	95%	88%	91%	87%	87%	91%	93%
81.0%	83%	76%	87%	90%	63%	74%	84%	75%	89%	92%	82%	75%	84%	87%	83%	82%	71%	79%	84%	79%	82%

Model Similarity Dendrogram

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