DTeval

A Collective Intelligence Project

Loading blueprint versions...

Please wait while we gather all the unique runs for this blueprint.

Analysis: Gd4 C10 Dtef Global Dialogues Gd4 AgeGroup%3A18 25 C10 - Run 67ce945...

Global Dialogues GD4 - 18-25 (10 context Qs)

DTEF: Predict response distributions for 18-25. Source: Global Dialogues GD4 (https://github.com/collect-intel/global-dialogues)

TAGS:

Global Dialogues Gd4

Instruction Following & Prompt Adherence

Efficiency & Succinctness

Factual Accuracy & Hallucination

Best Models (Coverage)

1.Claude 3.7 Sonnet
84.0%
2.GPT 5
83.4%
3.GPT 5.1
83.3%
4.Claude Sonnet 4
83.3%
5.Claude Sonnet 4.5
83.2%

🔀 Least Similar Models

Claude Sonnet 4.5vsGPT OSS 20b

74.6% similarity

👯 Most Similar Models

Claude Haiku 4.5vsClaude Sonnet 4

89.2% similarity

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

	Prompts vs. Models	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 4.1 Fast
Score		1st 84.0%	7th 82.5%	4th 83.3%	5th 83.2%	11th 81.4%	19th 77.3%	13th 80.0%	12th 80.8%	9th 81.8%	6th 82.7%	10th 81.5%	20th 76.5%	8th 82.4%	15th 79.8%	2nd 83.4%	3rd 83.3%	18th 77.5%	21st 74.8%	16th 79.4%	17th 78.0%	14th 79.8%
73.6%		86%	73%	86%	90%	67%	44%	67%	76%	70%	76%	65%	71%	77%	59%	76%	71%	72%	83%	76%	84%	77%
65.5%		77%	61%	59%	68%	81%	41%	58%	56%	62%	82%	69%	60%	75%	65%	75%	78%	70%	67%	58%	66%	47%
83.8%		88%	79%	90%	90%	81%	86%	90%	80%	81%	82%	89%	78%	86%	82%	89%	87%	78%	85%	78%	76%	84%
82.2%		90%	87%	86%	86%	82%	86%	81%	85%	80%	87%	84%	78%	83%	81%	85%	81%	61%	76%	79%		85%
69.3%		81%	73%	73%	74%	75%	62%	70%	72%	72%	70%	67%	69%	71%	69%	68%	67%	63%	50%	65%	72%	73%
84.9%		92%	87%	90%	94%	92%	67%	81%	88%	81%	98%	85%	58%	97%	93%	94%	92%	83%	78%	81%	65%	86%
66.2%		79%	86%	83%	85%	81%	57%	65%	56%	60%	60%	55%	50%	53%	55%	79%	71%	53%	63%	56%	76%	67%
83.5%		89%	78%	78%	62%	79%	87%	85%	85%	85%	83%	88%	89%	89%	84%	90%	84%	86%	84%	85%	77%	86%
83.0%		90%	75%	81%	81%	79%	88%	78%	91%	83%	93%	89%	73%	89%	83%	89%	91%	91%	71%	72%	72%	83%
70.2%		60%	58%	55%	62%	55%	81%	72%	76%	60%	64%	77%	91%	83%	86%	48%	64%	72%	86%	85%	56%	83%
86.3%		92%	86%	89%	91%	88%	82%	79%	90%	87%	90%	82%	81%	90%	88%	89%	89%	84%	89%	80%	77%	89%
86.3%		90%	92%	91%	90%	89%	82%	86%	82%	85%	90%	92%	74%	87%	88%	85%	94%	82%	74%	85%	82%	93%
85.5%		86%	89%	83%	90%	90%	88%	79%	82%	85%	86%	86%	83%	90%	88%	84%	85%	86%	83%	87%	78%	87%
60.4%		57%	69%	69%	61%	57%	63%	67%	44%	54%	60%	57%	67%	55%	53%	65%	66%	63%	57%	65%	59%	60%
76.1%		75%	62%	77%	79%	61%	69%	73%	84%	73%	82%	81%	79%	73%	72%	81%	82%	75%	84%	72%	80%	84%
79.1%		83%	80%	76%	86%	90%	72%	74%	72%	83%	83%	85%	67%	83%	70%	85%	90%	78%	79%	67%	88%	71%
85.0%		88%	85%	82%	93%	88%	88%	87%	85%	80%	80%	91%	88%	85%	83%	82%	84%	79%	87%	81%	79%	89%
85.7%		88%	89%	90%	96%	93%	86%	93%	89%	91%	92%	86%	75%	84%	77%	76%	82%	85%	77%	91%	86%	74%
83.0%		86%	83%	86%	86%	84%	84%	82%	80%	82%	85%	85%	72%	85%	87%	86%	88%	78%	83%	81%	78%	83%
76.3%		77%	79%	76%	76%	74%	70%	80%	79%	74%	81%	73%	80%	75%	78%	79%	78%	73%	78%	79%	73%	71%
88.8%		94%	94%	95%	98%	88%	78%	95%	94%	94%	93%	93%	74%	93%	75%	92%	89%	89%	80%	90%	82%	85%
88.0%		80%	90%	93%	84%	85%	96%	89%	90%	93%	88%	84%	85%	86%	86%		86%	95%	83%	85%	93%	89%
79.9%		93%	71%	78%	85%	88%	76%	78%	76%	83%	92%	70%	66%	90%	83%	93%	86%	60%	71%	80%	69%	90%
55.0%		60%	63%	58%	59%	56%	43%	58%	59%	60%	57%	48%	54%	66%	47%	52%	57%	50%	57%	47%	55%	50%
84.9%		90%	90%	87%	89%	77%	86%	88%	84%	81%	91%	84%	82%	88%	79%	89%	86%	78%	79%	87%	85%	83%
83.4%		91%	95%	82%	87%	87%	91%	87%	67%	87%	83%	87%	88%	86%	87%	80%	82%	66%	61%	87%	87%	84%
86.7%		94%	97%	88%	90%	90%	77%	96%	82%	79%	94%	83%	79%	87%	81%	98%	97%	81%	80%	79%	80%	88%
78.2%		82%	81%	75%	75%	78%	58%	74%	93%	84%	82%	78%	78%	87%	82%	91%	88%	85%	68%	71%	66%	67%
79.1%		93%	85%	86%	82%	73%	69%	83%	85%	80%	87%	75%	79%	80%	64%	91%	86%	76%	74%	65%	80%	68%
84.2%		95%	89%	94%	88%	91%	68%	83%	86%	84%	87%	85%	80%	86%	72%	88%	85%	86%	78%	91%	77%	75%
86.1%		90%	84%	85%	88%	91%	83%	84%	88%	85%	93%	78%	86%	90%	89%	86%	94%	75%	88%	85%	76%	90%
85.2%		92%	89%	81%	86%	88%	81%	82%	86%	89%	84%	88%	74%	85%	88%	90%	86%	80%	87%	92%	78%	83%
79.4%		83%	82%	75%	89%	91%	71%	75%	73%	79%	85%	77%	66%	74%	73%	91%	79%	77%	87%	66%	91%	84%
66.7%		69%	70%	67%	68%	84%	59%	64%	64%	75%	68%	69%	60%	68%	61%	70%	71%	69%	57%	63%	67%	58%
80.2%		83%	82%	78%	82%	77%	81%	81%	78%	86%	79%	77%	82%	81%	85%	82%	77%	72%	76%	82%	81%	83%
82.3%		88%	85%	85%	86%	88%	75%	82%	86%	84%	87%	78%	66%	89%	89%	87%	87%	61%	85%	83%	69%	88%
83.8%		84%	88%	88%	77%	82%	84%	82%	83%	88%	84%	82%	87%	85%	79%	91%	87%	76%	79%	89%	82%	83%
80.0%		77%	83%	71%	67%	75%	89%	84%	87%	82%	76%	75%	78%	75%	85%	90%	92%	81%	77%	87%	75%	73%
83.5%		88%	82%	84%	82%	86%	84%	79%	83%	83%	81%	85%	82%	88%	84%	87%	81%	75%	85%	89%	81%	85%
86.5%		87%	91%	91%	90%	91%	87%	83%	88%	91%	90%	91%	60%	87%	90%	93%	88%	81%	71%	91%	84%	91%
87.3%		89%	92%	87%	89%	82%	75%	84%	88%	89%	91%	91%	75%	92%	90%	92%	90%	92%	84%	75%	98%	89%
86.0%		90%	83%	95%	95%	87%	96%	92%	87%	90%	80%	90%	92%	65%	80%	91%	82%	82%	86%	84%	77%	82%
76.9%		88%	74%	68%	81%	66%	70%	80%	74%	77%	85%	78%	74%	66%	78%	84%	73%	83%	93%	64%	83%	76%
74.3%		70%	79%	75%	73%	68%	70%	86%	84%	87%	76%	69%	75%	83%	71%	62%	66%	70%	63%	78%	91%	64%
84.3%		91%	88%	92%	94%	82%	85%	86%	88%	77%	89%	83%	79%	84%	85%	89%	89%	72%	63%	87%	79%	89%
83.8%		81%	90%	89%	80%	84%	75%	78%	77%	86%	85%	95%	70%	94%	92%	77%	86%	81%	75%	92%	83%	89%
75.8%		79%	80%	73%	74%	78%	78%	77%	85%	80%	73%	73%	75%	79%	76%	78%	75%	67%	68%	75%	75%	74%
91.1%		81%	90%	98%	94%	90%	80%	83%	86%	90%	99%	90%	82%	99%	98%	93%	85%	99%	96%	90%	95%	96%
88.4%		81%	93%	93%	83%	84%	95%	86%	85%	97%	81%	94%	92%	86%	88%	87%	85%	93%	89%	86%	93%	85%
88.2%		87%	93%	90%	90%	92%	86%	94%	85%	94%	87%	90%	88%	91%	83%	90%	94%	92%	80%	80%		78%
86.0%		81%	93%	90%	88%	82%	83%	95%	93%	96%	82%	85%	84%	89%	80%	88%	86%	84%	78%	85%	87%	77%
83.5%		87%	80%	87%	89%	81%	69%	92%	89%	85%	88%	77%	71%	86%	83%	89%	86%	83%	79%	73%	86%	93%
74.3%		79%	85%	77%	85%	87%	67%	60%	78%	84%	79%	78%	65%	77%	74%	81%	81%	65%	55%	83%	60%	60%
60.0%		71%	67%	52%	65%	69%	56%	60%	63%	67%	57%	59%	62%	64%	58%	73%	59%	43%	41%	63%	59%	52%
87.4%		94%	88%	92%	93%	79%	87%	81%	91%	88%	91%	89%	89%	89%	89%	91%	89%	87%	75%	91%	74%	88%
84.7%		93%	82%	90%	91%	86%	75%	79%	86%	87%	91%	82%	78%	83%	77%	89%	95%	89%	87%	76%	81%	82%
65.5%		64%	56%	67%	61%	64%	51%	67%	69%	78%	78%	72%	49%	69%	54%	81%	76%	71%	60%	55%	71%	62%
89.5%		94%	93%	89%	92%	90%	93%	86%	88%	83%	87%	95%	83%	92%	95%	86%	90%	93%	87%	95%	84%	85%
67.2%		81%	70%	64%	79%	88%	53%	63%	65%	74%	73%	71%	56%	73%	59%	72%	77%	56%	53%	59%	64%	62%
74.2%		71%	81%	82%	84%	82%	90%	77%	85%	70%	63%	71%	73%	77%	78%	74%	66%	73%	54%	74%	54%	80%
83.3%		88%	82%	91%	92%	56%	83%	90%	86%	83%	83%	91%	87%	96%	83%	86%	83%	89%	32%	89%	84%	95%
76.0%		84%	80%	80%	86%	79%	61%	71%	80%	77%	78%	62%	74%	79%	71%	86%	79%	75%	63%	78%		77%
83.1%		86%	86%	96%	87%	84%	94%	86%	85%	90%	92%	86%	74%	86%	73%	95%	86%	69%	69%	88%	45%	89%
85.7%		89%	88%	85%	86%	62%	88%	84%	88%	84%	89%	82%	77%	92%	91%	84%	92%	83%	89%	88%	88%	91%
82.9%		94%	76%	81%	87%	90%	71%	81%	79%	84%	93%	68%	60%	91%	90%	95%	89%	68%	74%	85%	92%	93%
79.5%		82%	84%	83%	79%	97%	77%	76%	85%	94%	78%	83%	77%	76%	80%	77%	82%	62%	67%	66%	84%	81%
77.0%		84%	87%	74%	80%	87%	65%	72%	88%	86%	78%	76%	74%	78%	60%	87%	90%	76%	63%	63%	73%	76%
77.7%		86%	90%	86%	73%	82%	78%	81%	70%	70%	78%	85%	70%	77%	76%	84%	80%	80%	74%	63%	70%	78%
79.6%		85%	80%	83%	84%	86%	81%	62%	86%	77%	83%	81%	76%	81%	85%	83%	79%	72%	79%	71%	74%	83%
78.9%		84%	79%	79%	79%	70%	83%	80%	58%	71%	79%	87%	84%	79%	84%	80%	80%	77%	92%	79%	75%	78%
79.4%		78%	72%	89%	76%	92%	82%	81%	73%	79%	77%	77%	87%	88%	76%	76%	92%	75%	68%	80%	71%	78%
82.9%		86%	88%	85%	79%	71%	90%	84%	87%	78%	83%	85%	83%	90%	78%	87%	73%	85%	85%	85%	77%	81%
89.0%		96%	76%	95%	87%	71%	85%	90%	88%	85%	80%	93%	90%	84%	95%	95%	97%	96%	88%	92%	92%	94%
78.3%		72%	84%	85%	90%	84%	68%	88%	83%	91%	81%	82%	69%	84%	79%	73%	77%	76%	58%	67%	67%	86%
80.7%		86%	76%	85%	80%	81%	84%	82%	82%	80%	82%	82%	83%	86%	77%	72%	81%	78%	66%	84%	83%	85%
82.1%		86%	76%	89%	87%	75%	88%	89%	80%	75%	71%	83%	85%	79%	89%	81%	83%	78%	75%	85%		88%
81.3%		87%	85%	90%	88%	76%	89%	82%	85%	81%	80%	85%	75%	85%	87%	73%	80%	82%	63%	82%	72%	81%
87.0%		92%	90%	89%	91%	84%	79%	85%	87%	89%	90%	85%	88%	92%	87%	83%	95%	88%	77%	91%	84%	80%
84.8%		87%	91%	87%	89%	82%	81%	77%	83%	84%	89%	82%	70%	87%	88%	90%	90%	81%	88%	82%	84%	88%
85.1%		84%	90%	94%	85%	83%	88%	84%	87%	84%	87%	90%	81%	85%	85%	87%	86%	81%	71%	88%	81%	87%
91.9%		96%	88%	88%	88%	97%	95%	90%	98%	92%	96%	95%	95%	93%	90%	96%	93%	92%	91%	84%	95%	78%
87.6%		78%	94%	86%	90%	92%	86%	85%	87%	96%	92%	92%	88%	94%	94%	90%	89%	79%	80%	89%	79%	79%
82.2%		92%	81%	92%	88%	73%	86%	89%	86%	85%	88%	87%	77%	86%	77%	76%	81%	84%	77%	69%	68%	85%
85.2%		85%	87%	86%	83%	88%	91%	76%	88%	91%	88%	88%	78%	82%	82%	88%	78%	87%	86%	85%	87%	86%
83.9%		78%	88%	90%	75%	86%	83%	87%	84%	86%	86%	90%	73%	83%	87%	86%	90%	90%	76%	87%		73%
85.5%		89%	85%	87%	87%	89%	81%	80%	82%	88%	86%	79%	84%	92%	88%	90%	86%	84%	73%	89%	88%	88%
67.4%		73%	73%	68%	68%	66%	75%	77%	71%	65%	64%	77%	66%	65%	71%	59%	65%	49%	56%	77%	76%	55%
74.4%		70%	82%	77%	78%	80%	81%	74%	64%	75%	76%	83%	75%	71%	91%	66%	70%	75%	76%	80%	65%	54%
71.3%		74%	72%	85%	85%	92%	61%	66%	81%	76%	72%	71%	47%	72%	64%	68%	81%	66%	55%	72%		66%
83.1%		85%	91%	96%	91%	90%	81%	79%	87%	75%	91%	92%	80%	84%	74%	71%	74%	83%	68%	90%	83%	81%
77.5%		77%	69%	68%	74%	85%	63%	74%	73%	78%	74%	74%	78%	73%	78%	79%	86%	89%	89%	77%	90%	79%
63.5%		62%	80%	91%	94%	60%	55%	53%	50%	61%	52%	65%	46%	49%	47%	85%	77%	59%	56%	62%	60%	70%
68.5%		84%	83%	77%	76%	41%	70%	58%	60%	56%	65%	59%	58%	68%	69%	77%	77%	64%	70%	90%	68%	69%
87.0%		84%	91%	82%	84%	89%	75%	89%	88%	92%	86%	91%	90%	92%	87%	86%	91%	91%	85%	77%	82%	94%
65.1%		67%	65%	69%	67%	72%	78%	68%	63%	67%	61%	59%	66%	65%	62%	61%	60%	58%	66%	73%	55%	65%
86.0%		90%	87%	88%	87%	89%	85%	81%	84%	88%	86%	86%	89%	85%	79%	93%	89%	78%	85%	91%	77%	88%
88.7%		89%	89%	92%	87%	83%	92%	91%	93%	88%	88%	85%	96%	93%	92%	85%	90%	78%	85%	93%	92%	81%
87.6%		95%	80%	88%	82%	67%	83%	95%	94%	92%	85%	84%	95%	93%	93%	95%	91%	90%	82%	88%	77%	90%
79.3%		92%	78%	84%	89%	96%	45%	80%	72%	84%	90%	86%	67%	83%	75%	96%	94%	64%	76%	70%	62%	82%
81.0%		75%	86%	83%	73%	89%	79%	76%	80%	80%	89%	86%	72%	81%	70%	79%	84%	74%	82%	84%	88%	91%
79.0%		85%	77%	82%	84%	69%	85%	80%	87%	81%	89%	80%	75%	85%	81%	78%	82%	85%	81%	65%	56%	72%
89.8%		88%	90%	89%	88%	87%	90%	81%	96%	92%	92%	89%	96%	90%	96%	93%	94%	93%	90%	86%	94%	72%
87.3%		90%	92%	97%	98%	91%	83%	85%	90%	87%	80%	88%	97%	81%	86%	85%	86%	67%	69%	93%	94%	94%
86.6%		84%	86%	89%	85%	86%	71%	76%	79%	86%	97%	89%	91%	86%	92%	85%	95%	93%	96%	84%	77%	92%
85.4%		81%	88%	80%	84%	90%	73%	87%	83%	90%	84%	85%	96%	87%	89%	86%	89%	89%	83%	78%	88%	83%
82.2%		81%	90%	72%	88%	70%	67%	91%	77%	90%	93%	94%	90%	73%	74%	93%	80%	82%	74%	76%	89%	83%
82.8%		96%	91%	93%	86%	92%	65%	79%	66%	92%	92%	87%	72%	87%	79%	89%	95%	81%	31%	84%	92%	90%
63.2%		73%	59%	62%	68%	75%	36%	63%	59%	66%	81%	63%	55%	68%	60%	80%	78%	52%	52%	53%	78%	47%
72.8%		75%	61%	83%	66%	79%	84%	80%	81%	72%	75%	78%	72%	78%	93%	63%	65%	59%	59%	82%	69%	54%
88.1%		95%	93%	92%	90%	86%	89%	88%	86%	87%	90%	95%	78%	82%	77%	95%	87%	91%	95%	74%	89%	92%
86.3%		87%	89%	89%	92%	86%	86%	86%	88%	88%	87%	81%	89%	87%	78%	91%	96%	81%	81%	95%	76%	80%
85.3%		90%	92%	89%	88%	87%	75%	81%	82%	82%	88%	88%	67%	93%	90%	91%	91%	89%	76%	77%	84%	92%
88.4%		91%	82%	91%	86%	93%	82%	92%	93%	92%	91%	85%	88%	90%	86%	90%	91%	86%	87%	88%	85%	87%
88.0%		96%	91%	94%	90%	88%	89%	85%	87%	88%	88%	90%	87%	92%	90%	82%	89%	85%	74%	86%	87%	91%
88.8%		91%	87%	87%	86%	94%	89%	87%	95%	94%	90%	97%	57%	89%	97%	97%	94%	94%	81%	79%	92%	88%
72.6%		75%	74%	78%	66%	75%	84%	70%	69%	66%	67%	81%	74%	68%	81%	75%	72%	62%	69%	84%	64%	70%

Model Similarity Dendrogram

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