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%3Afrance C5 - Run 30e1fe9...

Global Dialogues GD3 - France (5 context Qs)

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

TAGS:

Instruction Following & Prompt Adherence

Efficiency & Succinctness

Best Models (Coverage)

1.Claude 3.7 Sonnet
71.9%
2.Claude Sonnet 4
71.3%
3.Claude Sonnet 4.5
70.7%
4.GPT 4.1 Mini
70.5%
5.GPT 4.1
70.1%

🔀 Least Similar Models

Claude Haiku 4.5vsClaude Sonnet 4.5

66.7% similarity

👯 Most Similar Models

Claude Sonnet 4vsGPT 4.1

92.6% 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 71.9%	9th 69.6%	2nd 71.3%	3rd 70.7%	19th 64.3%	12th 69.2%	11th 69.3%	17th 66.6%	14th 68.0%	5th 70.1%	4th 70.5%	20th 64.0%	8th 69.6%	13th 68.7%	10th 69.5%	6th 69.9%	15th 67.3%	18th 64.4%	7th 69.8%	16th 66.7%	21st 62.1%
76.0%	66%	73%	84%	71%	68%	83%		84%	81%	89%	81%	81%	81%	78%	67%	73%	63%	74%	79%	80%	63%
54.6%	56%	47%	49%	68%	39%	52%	57%	56%	45%	61%	48%	55%	48%	63%	59%	65%	62%	53%	55%	55%
81.9%	79%	77%	86%	86%	69%	82%	73%	86%	69%	86%	86%	86%	98%	79%	73%	79%	96%	87%	71%	86%	86%
77.8%	75%	77%	89%	77%	60%	91%	77%	71%	75%	75%	78%	78%	78%	78%	71%	84%	77%	77%	77%	91%	77%
80.0%	89%		89%	84%		86%	84%		84%	72%	69%		72%	76%	89%		84%	67%	84%	72%	79%
69.0%	58%	64%	58%	58%	60%	67%	80%	69%	80%	72%	72%	72%	80%	72%	63%	72%	72%	65%	72%	68%	74%
64.4%	67%	68%	71%	75%	62%	64%	67%	70%	63%	68%	63%	54%	63%	60%	65%	66%	72%	61%	65%	52%	56%
75.7%	89%	85%	80%	80%	85%	62%	81%	77%	74%	81%	78%	78%	89%	69%	85%	77%	58%	69%	64%	78%	51%
69.2%	72%	65%	62%	64%	77%	58%	62%	80%	70%	73%	72%	65%	72%	75%	64%	73%	73%	72%	72%	56%	76%
74.6%	84%	74%	75%	75%	80%	77%	75%	75%	75%	78%	75%	80%	78%	65%	77%	64%	78%	67%	64%		77%
72.4%	83%	80%	77%	77%	69%	84%	71%	78%	71%	68%	76%	64%	70%	77%	68%	76%	54%	54%	75%	64%	84%
67.1%	71%	65%	65%	74%	69%	65%	65%	65%	63%	65%	65%	64%	64%	74%	74%	71%	59%	68%	65%	78%	60%
63.5%	56%	69%	69%	77%	59%	76%	59%	52%	63%	72%	68%	38%	68%	72%	77%	63%	66%	49%	76%	59%	46%
51.8%	61%	58%	55%	48%	44%	47%	60%	49%	53%	58%	53%	64%	51%	47%	45%	60%	55%	64%	60%	28%	28%
78.3%	91%	78%	80%	83%	82%	79%	75%	64%	73%	89%	79%	59%	79%	82%	100%	92%	55%	66%	91%	77%	70%
63.8%	60%	60%	62%	58%	48%	68%	71%	63%	71%	73%	65%	71%	66%	62%	58%	65%	67%	67%	63%	68%	54%
69.5%	86%	83%	83%	72%	63%	71%	63%	58%	69%	69%	73%	50%	65%	72%	72%	74%	71%	54%	69%		72%
55.2%	60%	57%	57%	57%	69%	35%	46%	49%	53%	37%	53%	53%	53%	51%	65%	62%	68%	62%	44%	60%	68%
33.9%	41%	28%	32%	34%	64%	22%	41%	28%	36%	36%	36%	28%	36%	16%	36%	45%	45%	22%	14%	36%	36%
59.4%	68%	68%	60%	57%	49%	63%	71%	52%	58%	57%	63%	41%	62%	53%		69%	58%	64%	71%		44%
63.5%	68%	63%	68%	71%	60%	77%	61%	56%	61%	68%	70%	50%	68%	82%	55%	56%	43%	62%	77%	68%	50%
74.3%	77%	76%	77%	77%	70%	91%	70%	62%	68%	84%	84%	62%	70%	85%	81%	82%	78%	63%	88%	78%	37%
71.8%	63%	68%	68%	67%	89%	86%	68%	84%	84%	68%	72%	60%	72%	78%	63%	68%	73%	74%	63%	71%	68%
57.9%	68%	67%	60%	68%	50%	61%	54%	54%	49%	68%	61%	36%	57%	49%	68%	65%	63%	46%	61%	65%	46%
54.3%	53%	62%	53%	49%	55%	62%	53%	50%	54%	57%	62%	67%	56%	46%	51%	49%	44%	57%	63%	56%	41%
45.8%	50%	51%	51%	45%	40%	47%	48%	32%	41%	48%	53%	41%	48%	48%	49%	45%	48%	57%			28%
67.4%	72%	75%	75%	69%	64%	58%	70%	54%	68%	75%	64%	73%	75%	64%	55%	73%	73%	74%	73%	57%	55%
79.7%	84%	83%	84%	84%	51%	79%	77%	82%	82%	81%	90%	90%	84%	79%	67%	68%	90%	82%	88%	86%	63%
69.5%	78%	80%	80%	80%	67%	64%	80%	65%	64%	60%	68%	60%	68%	69%	69%	65%	60%	60%	80%	74%	68%
67.5%	78%	63%	78%	80%		57%	69%	66%		65%	68%	56%	63%	60%	73%	74%	69%	67%	56%	72%	69%
66.4%	71%	67%	65%	68%	63%	72%	61%	55%	64%	77%	72%	61%	64%	64%	71%	74%	72%	63%	66%	64%	61%
47.3%	50%	53%	44%	44%	59%	47%	56%	44%	59%	44%	44%	44%	31%	50%	56%	50%	35%	44%	58%	23%	59%
80.9%	78%	77%	86%	86%	69%	82%	73%	86%	69%	86%	86%	86%	98%	79%	73%	79%	95%	87%	71%	66%	86%
70.7%	79%	79%	79%	65%	49%	71%	78%	76%	78%	63%	78%	67%	67%	71%	71%	83%	72%	77%	75%	46%	61%
72.5%	73%	58%	76%	76%	47%	80%	77%	80%	79%	79%	76%	63%	67%	62%	85%	80%	84%	73%	57%	72%	79%
69.4%	66%	71%	75%	60%	41%	78%	72%	69%	73%	68%	75%	83%	77%	78%	57%	59%	78%	68%	82%		58%
84.1%	86%	85%	86%	76%	88%	87%	86%	79%	89%	76%	86%	84%	86%	86%	88%	75%	89%	81%	89%	91%	74%
56.9%	71%	57%	69%	69%	72%	62%	77%		64%	69%	57%	49%	64%	51%	62%	55%	31%	38%	55%	46%	20%
81.7%	78%	92%	85%	88%	85%	82%	85%	75%	79%	75%	79%	91%	85%	100%	83%	85%	65%	71%	89%	84%	59%
89.6%	91%	85%	95%	95%	78%	91%	81%	95%	78%	95%	95%	95%	90%	88%	95%	88%	95%	95%	80%	81%	95%
69.3%	75%	75%	77%	80%	57%	65%	74%	77%	70%	71%	77%	66%	70%	77%	80%	80%	35%	32%	68%	77%	72%
73.5%	74%	85%	67%	74%	67%	54%	74%	74%	67%	71%	85%	59%	80%	89%	81%	66%	78%	62%	80%	74%	82%
84.5%	95%	75%	86%	95%	100%	90%	90%	89%	89%	86%	75%		81%	79%	76%	86%	90%	74%	81%	76%	76%

Model Similarity Dendrogram

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