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%3Akazakhstan C10 - Run 3052c3b...

Global Dialogues GD3 - Kazakhstan (10 context Qs)

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

TAGS:

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Reasoning

Kazakhstan

Best Models (Coverage)

1.Claude Sonnet 4.5
74.0%
2.GPT 4.1 Mini
73.3%
3.Claude Sonnet 4
73.0%
4.Claude 3.7 Sonnet
72.4%
5.Qwen3 30b A3B Instruct 2507
72.1%

🔀 Least Similar Models

Claude Sonnet 4.5vsGPT OSS 20b

69.2% similarity

👯 Most Similar Models

Mistral Medium 3vsGPT 4o

93.8% 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	4th 72.4%	7th 71.7%	3rd 73.0%	1st 74.0%	17th 70.1%	20th 69.0%	13th 70.7%	16th 70.2%	12th 70.7%	18th 69.9%	2nd 73.3%	9th 71.1%	10th 71.1%	6th 72.0%	8th 71.3%	11th 71.0%	19th 69.4%	15th 70.3%	5th 72.1%	14th 70.7%	21st 67.0%
77.0%	88%	82%	82%	82%	79%	63%	75%	79%	82%	69%	76%	75%	74%	78%	83%	82%	81%	69%	75%	81%	62%
45.4%	42%	43%	46%	47%	42%	46%	36%	44%	39%	43%	55%	52%	52%	55%	34%	39%	31%	55%	53%	55%	45%
71.5%	74%	62%	82%	76%	66%	61%	76%	71%	71%	76%	82%	71%	71%	76%	66%	76%	70%	74%	61%	73%	66%
77.8%	86%	72%	77%	86%	76%	75%	80%	87%	79%	82%	86%	75%	79%	75%	77%	71%	64%	67%	77%	80%	82%
72.0%	64%	79%	64%	70%	73%	65%	76%	72%	67%	73%	76%	83%	72%	80%	69%	71%	72%	89%	64%	78%	54%
75.7%	68%	64%	61%	68%	73%	86%	72%	77%	77%	78%	72%	72%	89%	88%	72%	67%	88%	73%	78%	94%	73%
86.7%	93%	86%	89%	92%	90%	85%	90%	93%	93%	87%	90%	84%	90%	90%	87%	86%	75%	77%	100%	72%	71%
70.4%	74%	66%	67%	80%	72%	54%	74%	72%	72%	68%	74%	74%	67%	69%	73%	74%	70%	76%	62%	70%
83.7%	88%	83%	82%	82%	88%	62%	83%	87%	78%	83%	88%	78%	83%	88%	94%	88%	98%	77%	83%	82%	82%
72.9%	76%	78%	70%	76%	75%	75%	72%	76%	75%	71%	75%	75%	75%	75%	68%	67%	67%	63%	75%	75%	71%
50.1%	55%	54%	57%	57%	43%	57%	57%	62%	46%	41%	54%	46%	47%	43%	47%	46%	43%	37%	63%	54%	43%
66.6%	69%	62%	69%	69%	66%	58%	63%	71%	71%	71%	64%	65%	72%	65%	73%	69%	65%	60%	65%	68%	64%
61.4%	55%	69%	66%	66%	63%	70%	54%	62%	61%	58%	65%	50%	57%	57%	64%	64%	62%	62%	60%	62%	62%
72.4%	70%	62%	59%	70%	68%	77%	70%	73%	71%	70%	78%	82%	70%	83%	83%	69%	76%	73%	73%	65%	78%
81.3%	87%	85%	87%	87%	76%	74%	86%	84%	89%	82%	73%	80%	87%	87%	73%	82%	85%	80%	77%	63%	84%
74.6%	78%	76%	82%	85%	82%	67%	73%	72%	73%	70%	74%	81%	75%	62%	75%	78%	77%	76%	74%	75%	62%
56.0%	60%	66%	63%	68%	65%	54%	63%	51%	58%	54%	66%	51%	42%	57%	68%	56%	42%	39%	51%	56%	47%
63.2%	69%	64%	71%	71%	69%	48%	55%	62%	69%	60%	54%	61%	60%	55%	69%	62%	71%	65%	67%	57%	68%
47.0%	46%	34%	47%	40%	72%	27%	46%	55%	46%	49%	40%	34%	50%	46%	60%	56%	47%	73%	26%	52%	42%
75.9%	79%	79%	79%	79%	81%	74%	79%	71%	71%	79%	72%	71%	79%	71%	78%	76%	73%	73%	79%	71%	79%
82.9%	74%	84%	92%	77%	92%	77%	86%	82%	81%	86%	89%	84%	92%	92%	74%	75%	82%	83%	80%	88%	70%
68.9%	65%	67%	68%	67%	67%	76%	62%	58%	67%	67%	87%	71%	68%	72%	77%	68%	58%	70%	86%	68%	58%
81.0%	79%	93%	82%	86%	82%	83%	89%	82%	89%	72%	77%	77%	72%	86%	77%	77%	84%	75%	79%	75%	84%
77.1%	79%	87%	81%	76%	74%	71%	77%	72%	79%	82%	88%	79%	77%	75%	82%	79%	71%	71%	77%	71%	71%
76.4%	77%	72%	78%	74%	77%	75%	78%	75%	72%	77%	76%	69%	80%	76%	71%	79%	86%	80%	83%	75%	75%
75.2%	74%	87%	74%	67%	68%	82%	83%	72%	80%	76%	87%	83%	74%	82%	70%	74%	64%	70%	83%	68%	62%
76.1%	81%	78%	76%	87%	82%	59%	69%	76%	82%	75%	60%	75%	82%	71%	81%	80%	75%	82%	81%	83%	63%
69.0%	70%	71%	72%	72%	49%	72%	72%	70%	72%	74%	76%	77%	71%	68%	63%	70%	71%	65%	68%	62%	63%
76.6%	88%	72%	72%	81%	75%	71%	88%	74%	77%	75%	75%	75%	75%	75%	77%	77%	79%	75%	75%	75%	77%
67.6%	72%	66%	72%	74%	64%	72%	69%	55%	66%	62%	64%	58%	63%	60%	72%	75%	73%	71%	61%	90%	61%
66.9%	63%	69%	71%	71%	62%	83%	62%	57%	69%	71%	82%	78%	71%	74%	48%	55%	54%	74%	77%	58%	55%
93.8%	94%	93%	86%	92%	97%	92%	92%	97%	97%	92%	86%	97%	97%	92%	97%	92%	99%	94%	92%	95%	97%
71.9%	76%	62%	82%	76%	66%	61%	76%	71%	71%	76%	82%	71%	71%	76%	66%	76%	70%	74%	61%	73%	73%
77.9%	84%	69%	82%	84%	79%	72%	70%	84%	79%	79%	74%	71%	79%	71%	86%	86%	80%	84%	64%	71%	87%
54.5%	56%	67%	72%	72%	31%	53%	50%	56%	42%	42%	42%	72%	42%	42%	50%	67%	50%	42%	76%	63%	58%
64.0%	69%	68%	67%	67%	49%	70%	62%	69%	62%	67%	67%	65%	67%	59%	62%	59%	65%	57%	64%	68%	62%
39.2%	38%	38%	42%	42%	38%	47%	33%	29%	38%	38%	47%	33%	42%	47%	31%	29%	42%	57%	47%	26%	40%
89.0%	86%	97%	100%	93%	93%	88%	86%	100%	92%	93%	94%	80%	93%	93%	93%	93%	77%	77%	100%	83%	57%
65.0%	58%	64%	72%	70%	62%	83%	59%	56%	60%	66%	76%	68%	60%	69%	61%	60%	65%	65%	66%	70%	54%
85.5%	81%	96%	75%	81%	91%	97%	81%	86%	86%	81%	75%	86%	86%	81%	91%	81%	87%	83%	97%	83%	91%
56.8%	61%	55%	66%	61%	44%	62%	53%	54%	47%	50%	61%	67%	55%	62%	47%	59%	55%	53%	58%	56%	67%
77.3%	86%	77%	75%	79%	76%	70%	79%	69%	75%	75%	76%	75%	75%	86%	89%	77%	73%	77%	79%	79%	76%
79.3%	82%	83%	84%	84%	78%	72%	82%	52%	71%	66%	97%	88%	75%	86%	86%	86%	69%	88%	84%	75%	78%

Model Similarity Dendrogram

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