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: Gd5 C5 Dtef Global Dialogues Gd5 AiConcern%3Amore Concerned Than Excited C5 - Run 53a7891...

Global Dialogues GD5 - More concerned than excited (5 context Qs)

DTEF: Predict response distributions for More concerned than excited. Source: Global Dialogues GD5 (https://github.com/collect-intel/global-dialogues)

TAGS:

Instruction Following & Prompt Adherence

Reasoning

Factual Accuracy & Hallucination

AI Safety & Robustness

General Knowledge

Best Models (Coverage)

1.Claude Sonnet 4.5
78.9%
2.Claude Haiku 4.5
78.5%
3.Llama 4 Maverick
77.7%
4.GPT 4.1 Mini
77.1%
5.Claude Sonnet 4
76.8%

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 Haiku 4.5	Claude Sonnet 4	Claude Sonnet 4.5	Gemini 2.5 Flash	Gemma 3 12b It	Llama 4 Maverick	Mistral Medium 3	GPT 4.1	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini	Qwen3 30b A3B Instruct 2507	Qwen3 Next 80b A3B Instruct
Score	2nd 78.5%	5th 76.8%	1st 78.9%	9th 75.1%	12th 69.9%	3rd 77.7%	8th 75.8%	6th 76.3%	4th 77.1%	13th 59.7%	10th 73.5%	11th 72.1%	7th 76.1%
72.6%	83%	70%	85%	36%	67%	87%	75%	56%	89%	73%	78%	74%	71%
72.2%	86%	77%	81%	83%	70%	74%	86%	83%	68%	27%	66%	70%	67%
56.9%	79%	79%	71%	62%	45%	59%	54%	55%	51%	30%	43%	45%	67%
82.0%	82%	82%	82%	82%	82%	82%	82%	82%	82%	82%	82%	82%	82%
84.2%	68%	82%	84%	87%	74%	92%	90%	91%	91%	70%	86%	90%	89%
71.5%	54%	70%	71%	76%	74%	79%	77%	66%	66%	92%	76%	78%	50%
86.3%	82%	89%	96%	85%	86%	89%	82%	93%	92%	69%	87%	84%	88%
64.6%	60%	65%	71%	73%	40%	66%	75%	77%	60%	61%	71%	60%	61%
66.2%	76%	89%	86%	63%	54%	67%	66%	80%	80%	39%	44%	46%	70%
73.7%	73%	64%	81%	86%	58%	75%	67%	70%	88%	60%	80%	71%	85%
71.2%	79%	72%	82%	68%	84%	72%	58%	66%	76%	76%	44%	63%	85%
83.9%	81%	90%	90%	60%	92%	90%	90%	75%	92%	64%	90%	89%	88%
77.8%	74%	75%	80%	97%	72%	72%	88%	87%	81%	58%	70%	79%	78%
82.0%	82%	82%	82%	82%	82%	82%	82%	82%	82%	82%	82%	82%	82%
67.1%	70%	70%	65%	67%	49%	67%	67%	66%	74%	69%	68%	67%	73%
64.1%	82%	65%	71%	35%	57%	92%	52%	47%	62%	71%	55%	72%	72%
88.4%	86%	89%	90%	96%	91%	90%	90%	91%	87%	87%	83%	80%	89%
77.5%	88%	85%	84%	86%	73%	82%	93%	88%	76%	39%	69%	75%	70%
74.1%	81%	77%	80%	90%	77%	76%	85%	82%	72%	23%	67%	71%	82%
73.2%	93%	76%	85%	69%	67%	57%	76%	74%	77%	84%	73%	48%	72%
73.7%	72%	70%	74%	82%	78%	73%	72%	79%	77%	56%	76%	77%	72%
70.7%	86%	83%	73%	49%	73%	71%	75%	64%	62%	41%	89%	69%	84%
84.5%	90%	86%	95%	91%	92%	98%	80%	86%	73%	73%	73%	90%	72%
68.3%	67%	69%	69%	70%	63%	65%	75%	70%	63%	68%	76%	71%	62%
77.5%	73%	74%	79%	97%	73%	71%	88%	86%	82%	57%	69%	79%	79%
80.5%	83%	85%	87%	73%	87%	85%	72%	83%	89%	75%	86%	56%	85%
80.9%	87%	77%	83%	72%	67%	86%	74%	82%	91%	73%	87%	83%	90%
77.0%	87%	78%	80%	68%	76%	88%	82%	83%	82%	45%	83%	76%	73%
82.2%	95%	99%	96%	82%	10%	63%	71%	99%	98%	82%	94%	79%	100%
70.0%	70%	67%	68%	82%	67%	87%	75%	82%	71%	30%	81%	66%	64%
69.2%	81%	65%	63%	66%	70%	93%	70%	49%	80%	63%	56%	71%	73%
53.9%	61%	56%	53%	54%	70%	54%	58%	53%	50%	53%	40%	44%	55%
74.0%	82%	62%	78%	91%	56%	75%	71%	75%	87%	63%	78%	62%	82%
74.8%	90%	72%	69%	90%	85%	70%	76%	78%	65%	85%	76%	58%	58%
83.1%	87%	91%	89%	92%	85%	91%	90%	90%	92%	20%	88%	84%	81%
74.0%	69%	77%	81%	83%	71%	80%	71%	77%	71%	59%	71%	71%	81%
75.5%	79%	86%	85%	72%	73%	93%	72%	76%	69%	47%	72%	86%	72%
66.7%	71%	62%	70%	72%	65%	66%	69%	69%	68%	65%	67%	68%	55%
63.8%	67%	59%	72%	57%	53%	61%	60%	67%	80%	78%	64%	45%	67%
74.5%	86%	71%	64%	70%	74%	69%	69%	62%	91%	42%	92%	85%	93%
86.4%	83%	90%	91%	80%	84%	89%	88%	92%	84%	82%	86%	87%	87%
77.4%	73%	81%	78%	85%	79%	81%	81%	79%	74%	79%	59%	79%	78%
60.8%	69%	71%	67%	66%	54%	61%	74%	70%	55%	34%	49%	70%	50%
78.2%	77%	93%	84%	69%	56%	80%	78%	76%	91%	53%	86%	84%	90%
84.8%	92%	84%	89%	86%	92%	93%	90%	86%	82%	47%	92%	80%	90%
72.1%	76%	76%	76%	73%	69%	79%	73%	84%	74%	21%	78%	70%	88%