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 Dtef Global Dialogues Gd5 AiConcern%3Amore Excited Than Concerned - Run 3781e28...

Global Dialogues GD5 - More excited than concerned

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

TAGS:

Instruction Following & Prompt Adherence

Reasoning

General Knowledge

Efficiency & Succinctness

Factual Accuracy & Hallucination

Best Models (Coverage)

1.Claude Sonnet 4.5
80.6%
2.Claude Haiku 4.5
80.1%
3.Claude Sonnet 4
79.6%
4.Gemini 2.5 Flash
79.5%
5.GPT 4.1 Mini
79.2%

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 80.1%	3rd 79.6%	1st 80.6%	4th 79.5%	12th 73.5%	10th 75.6%	9th 76.3%	6th 78.4%	5th 79.2%	13th 70.7%	11th 75.1%	8th 76.7%	7th 78.3%
70.7%	75%	63%	63%	74%	64%	81%	73%	57%	76%	63%	75%	80%	75%
73.8%	83%	81%	80%	88%	48%	69%	78%	84%	76%	62%	80%	61%	70%
71.5%	83%	75%	70%	76%	86%	64%	68%	66%	67%	66%	67%	65%	77%
62.2%	66%	66%	66%	73%	85%	59%	48%	58%	55%	41%	53%	66%	72%
82.2%	94%	95%	93%	77%	91%	85%		88%	84%	46%	70%	76%	87%
86.2%	87%	82%	83%	94%	85%	87%	93%	74%	88%	83%	93%	87%	84%
86.1%	74%	86%	86%	86%	78%	88%	92%	90%	90%	90%	88%	89%	82%
69.9%	70%	83%	72%	69%	59%	92%	73%	76%	70%	70%	63%	58%	54%
85.1%	89%	90%	88%	83%	79%	88%	88%	82%	84%	87%	88%	72%	88%
82.1%	90%	74%	90%	89%	67%	80%	84%	89%	82%	74%	83%	81%	84%
79.0%	89%	88%	83%	88%	88%	66%	69%	82%	78%	69%	68%	75%	84%
66.7%	60%	69%	53%	57%	88%	77%	63%	55%	68%	54%	59%	92%	72%
68.0%	66%	71%	82%	94%	54%	51%	64%	58%	80%	49%	54%	77%	84%
71.9%	75%	70%	75%	90%	83%	77%	63%	66%	63%	63%	61%	70%	79%
71.5%	76%	70%	73%	71%	60%	62%	71%	72%	74%	84%	75%	71%	70%
64.2%	73%	61%	75%	90%	57%	58%	61%	55%	64%	35%	57%	73%	75%
83.8%	85%	93%	91%	89%	93%	91%	87%	86%	74%	67%	69%	85%	80%
79.4%	86%	82%	87%	76%	70%	81%	77%	88%	82%	79%	73%	71%	80%
79.9%	85%	88%	88%	82%	70%	73%	78%	89%	81%	66%	76%	80%	83%
78.3%	87%	75%	83%	85%	91%	67%	78%	81%	74%	77%	72%	73%	75%
77.8%	82%	88%	87%	63%	78%	80%	67%	83%	79%	78%	70%	84%	73%
70.8%	75%	70%	73%	75%	56%	56%	61%	74%	81%	69%	77%	78%	76%
85.6%	84%	88%	88%	86%	62%	88%	78%	87%	95%	97%	77%	87%	96%
75.8%	74%	77%	75%	69%	75%	75%	82%	79%	77%	77%	82%	73%	70%
63.9%	62%	66%	77%	90%	49%	47%	59%	53%	76%	45%	50%	73%	84%
76.2%	82%	73%	83%	73%	91%	84%	65%	72%	73%	46%	81%	83%	84%
81.4%	77%	92%	97%	64%	76%	81%	71%	92%	85%	83%	75%	82%	83%
81.5%	91%	76%	62%	79%	95%	77%	74%	87%	95%	71%	92%	88%	72%
86.8%	94%	94%	94%	95%	10%	81%	97%	97%	97%	96%	97%	80%	97%
81.5%	84%	77%	89%	83%	79%	79%	83%	91%	86%	80%	82%	69%	78%
74.3%	77%	62%	82%	80%	74%	81%	71%	61%	77%	79%	64%	81%	77%
79.5%	79%	86%	86%	74%	68%	80%	81%	85%	81%	81%	80%	76%	77%
80.9%	87%	72%	88%	79%	70%	79%	83%	94%	83%	75%	83%	74%	85%
85.5%	89%	79%	83%	83%	82%	87%	92%	88%	88%	86%	93%	78%	84%
78.2%	79%	89%	84%	78%	90%	83%	82%	74%	80%	63%	78%	68%	68%
87.7%	86%	85%	88%	89%	83%	87%	91%	94%	88%	98%	86%	83%	82%
78.7%	85%	89%	89%	75%	79%	78%	79%	85%	82%	67%	71%	75%	69%
72.8%	77%	66%	74%	68%	70%	68%	83%	77%	75%	71%	84%	71%	63%
73.2%	79%	78%	80%	70%	78%	60%	63%	83%	80%	44%	77%	79%	80%
87.4%	93%	93%	78%	78%	91%	79%	82%	82%	91%	91%	93%	91%	94%
82.2%	80%	94%	85%	83%	86%	87%	86%	86%	79%	58%	77%	83%	84%
69.1%	73%	71%	71%	59%	71%	70%	78%	78%	64%	81%	58%	59%	65%
70.9%	77%	74%	73%	89%	45%	63%	74%	79%	82%	54%	72%	69%	71%
76.6%	68%	81%	77%	76%	80%	63%	74%	80%	79%	79%	83%	76%	80%
87.3%	82%	95%	83%	92%	82%	89%	92%	80%	88%	93%	86%	88%	85%
73.9%	74%	86%	81%	76%	66%	81%	77%	71%	70%	67%	63%	77%	72%