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%3Aturkey C10 - Run bcabdb8...

Global Dialogues GD3 - Turkey (10 context Qs)

DTEF: Predict response distributions for Turkey. 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
68.1%
2.GPT 4.1
67.7%
3.Claude 3.7 Sonnet
67.2%
4.Claude Haiku 4.5
67.1%
5.Claude Sonnet 4.5
66.9%

🔀 Least Similar Models

Claude Sonnet 4.5vsMistral Medium 3

66.0% similarity

👯 Most Similar Models

GPT 4.1 MinivsGPT 4o Mini

90.8% 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 67.2%	4th 67.1%	1st 68.1%	5th 66.9%	20th 60.2%	18th 61.6%	9th 63.8%	13th 63.5%	16th 62.2%	2nd 67.7%	8th 64.2%	21st 59.8%	11th 63.6%	14th 63.4%	5th 66.9%	7th 66.0%	15th 62.4%	19th 60.9%	12th 63.5%	10th 63.7%	17th 61.7%
59.9%	64%	57%	59%	68%	49%	53%	58%	62%	59%	64%	59%	60%	61%	59%	62%	61%	64%	49%	65%	58%	66%
34.2%	30%	30%	36%	38%	0%	43%	24%	39%	31%	31%	47%	43%	51%	47%	40%	30%	28%	33%	38%		24%
86.2%	92%	86%	88%	89%	75%	89%	84%	89%	80%	89%	92%	92%	89%	92%	84%	86%	84%	92%	84%	79%	75%
62.0%	64%	66%	71%	55%	55%	54%	64%	69%	64%	55%	55%	55%	55%	63%	65%	74%	75%	62%	71%	55%	56%
80.9%	85%	78%	85%	79%	92%	86%	92%	85%	81%	78%	83%	71%	78%	77%	73%	76%	81%	83%	85%	59%	92%
79.0%	74%	74%	71%	74%	86%	86%	77%	81%	89%	76%	74%	87%	89%	86%	74%	74%	74%	80%	76%	87%	70%
50.6%	58%	44%	55%	58%	45%	36%	50%	55%	54%	44%	50%	55%	44%	44%	56%	56%	54%	60%	51%	54%	39%
62.5%	71%	65%	71%	75%	75%	48%	63%	59%	58%	80%	58%	58%	58%	47%	65%	63%	51%	61%	58%	53%	75%
66.3%	64%	67%	56%	56%	71%	51%	67%	70%	67%	70%	68%	66%	70%	68%	61%	66%	76%	79%	58%	67%	74%
58.2%	64%	80%	61%	72%	55%	55%	46%	40%	55%	61%	55%	55%	55%	55%	60%	64%	51%	49%	55%	55%	80%
50.3%	49%	60%	59%	45%	0%	66%	64%	49%	41%	49%	49%	47%	39%	49%	50%	50%	41%	40%	76%	75%	59%
69.8%	78%	73%	71%	70%	80%	71%	75%	71%	71%	75%	75%	80%	47%	75%	71%	63%	71%	50%	71%	67%	60%
72.2%	64%	76%	85%	85%	71%	100%	76%	58%	71%	76%	86%	57%	76%	83%	69%	67%	57%	57%	89%	57%	57%
58.3%	54%	54%	54%	56%	49%	62%	54%	62%	54%	65%	58%	59%	54%	64%	60%	58%	64%	66%	46%	58%	74%
45.5%	55%	46%	46%	50%	49%	49%	43%	32%	40%	51%	55%	29%	46%	42%	45%	53%	51%	45%	41%		42%
55.3%	58%	55%	63%	57%	67%	46%	58%	59%	56%	56%	49%	47%	47%	49%	64%	58%	47%	57%	51%	51%	67%
59.9%	64%	77%	77%	71%	45%	50%	58%	46%	60%	60%	64%	27%	60%	55%	65%	72%	45%	50%	61%	75%	75%
63.7%	67%	58%	77%	67%	75%	48%	58%	69%	64%	80%	58%	58%	58%	54%	70%	66%	62%	57%	58%	59%	75%
50.7%	58%	53%	46%	53%	48%	42%	70%	53%	56%	75%	34%	32%	45%	58%	64%	65%	53%	33%	32%	59%	36%
59.9%	63%	66%	66%	70%	64%	49%	66%	54%	60%	66%	56%	49%	66%	47%	74%	70%	57%	40%	62%	49%	63%
71.1%	70%	79%	79%	56%	32%	75%	74%	66%	79%	66%	85%	76%	79%	94%	63%	70%	63%	71%	85%	82%	49%
68.4%	71%	75%	75%	71%	67%	68%	67%	67%	62%	75%	70%	63%	64%	65%	73%	70%	68%	63%	68%	66%	69%
46.1%	44%	43%	44%	44%	43%	52%	48%	50%	46%	45%	51%	37%	48%	57%	44%	47%	50%	36%	48%	41%	50%
62.6%	70%	72%	72%	59%	58%	71%	54%	51%	65%	72%	72%	58%	72%	62%	63%	57%	58%	49%	64%	58%	58%
54.8%	58%	61%	59%	56%	58%	55%	64%	56%	51%	58%	48%	58%	64%	46%	53%	48%	61%	44%	56%	64%	33%
60.5%	67%	61%	64%	67%	67%	54%	59%	64%	59%	66%	57%	60%	61%	57%	66%	62%	59%	61%	61%	51%	47%
65.8%	76%	71%	71%	71%	74%	41%	63%	63%	68%	54%	38%	69%	64%	60%	71%	69%	80%	83%	64%	74%	58%
60.4%	72%	67%	71%	74%	31%	54%	67%	59%	56%	80%	63%	58%	58%	47%	63%	70%	59%	43%	42%		75%
61.2%	67%	71%	75%	86%	86%	54%	64%	51%	47%	46%	56%	64%	46%	37%	66%	51%	46%	67%	71%	73%	62%
72.8%	69%	80%	72%	74%	56%	61%	63%	84%	59%	76%	82%	67%	88%	79%	72%	76%	78%	80%	80%	74%	58%
73.4%	72%	88%	74%	70%	70%	73%	67%	76%	71%	88%	76%	65%	70%	74%	82%	75%	72%	67%	76%	72%	63%
72.8%	68%	75%	73%	71%	86%	71%	77%	71%	81%	71%	68%	68%	71%	68%	77%	75%	77%	68%	77%	68%	68%
73.7%	80%	73%	75%	77%	63%	77%	71%	77%	68%	77%	80%	80%	77%	80%	71%	73%	71%	80%	71%	63%	63%
56.9%	69%	52%	66%	64%	55%	43%	48%	56%	58%	56%	54%	49%	49%	58%	65%	69%	62%	63%	47%	52%	60%
71.0%	90%	69%	89%	86%	40%	74%	54%	89%	75%	89%	54%	69%	64%	73%	77%	71%	63%	71%	64%	63%	68%
61.0%	67%	62%	67%	70%	36%	72%	64%	56%	54%	72%	66%	63%	65%	63%	62%	59%	55%	57%	49%	66%	55%
68.9%	69%	74%	73%	76%	73%	65%	54%	49%	56%	74%	85%	53%	69%	76%	82%	75%	82%	75%	69%	68%	50%
73.9%	85%	75%	77%	66%	97%	81%	87%	97%	84%	84%	80%	59%	76%	80%	77%	81%	49%	47%	76%	47%	47%
55.9%	62%	58%	53%	56%	57%	63%	59%	62%	59%	71%	52%	57%	59%	44%	62%	59%	59%	47%	32%	47%	55%
92.3%	87%	94%	92%	90%	95%	90%	96%	90%	100%	90%	87%	87%	90%	87%	96%	94%	96%	87%	96%	99%	95%
54.5%	55%	51%	51%	55%	58%	53%	54%	54%	53%	61%	53%	43%	66%	50%	61%	57%	50%	57%	49%	56%	58%
83.0%	83%	90%	86%	86%	75%	58%	86%	94%	64%	83%	83%	70%	86%	94%	88%	88%	88%	86%	86%	86%	83%
64.0%	63%	78%	75%	63%	60%	61%	55%	47%	47%	55%	77%	73%	61%	63%	70%	69%	50%	75%	72%	60%	70%

Model Similarity Dendrogram

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