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 Excited Than Concerned C5 - Run 37e0007...

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

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

Factual Accuracy & Hallucination

Reasoning

Efficiency & Succinctness

General Knowledge

Best Models (Coverage)

1.Claude Sonnet 4.5
81.7%
2.GPT 4.1 Mini
81.3%
3.Claude Sonnet 4
80.6%
4.Claude Haiku 4.5
80.0%
5.GPT 4.1
79.8%

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	4th 80.0%	3rd 80.6%	1st 81.7%	10th 77.0%	12th 74.2%	11th 76.8%	9th 78.1%	5th 79.8%	2nd 81.3%	13th 70.4%	6th 79.5%	8th 78.9%	7th 79.1%
68.9%	63%	65%	81%	52%	61%	80%	60%	55%	83%	63%	79%	79%	75%
72.2%	79%	81%	80%	84%	48%	68%	70%	86%	55%	79%	76%	71%	62%
75.8%	90%	75%	67%	66%	67%	69%	59%	68%	77%	87%	82%	88%	90%
87.0%	87%	87%	87%	87%	87%	87%	87%	87%	87%	87%	87%	87%	87%
82.5%	68%	82%	95%	94%	83%	88%	92%	81%	73%	75%	93%	77%	71%
77.4%	56%	70%	75%	96%	88%	82%	81%	74%	78%	92%	94%	88%	32%
84.4%	74%	86%	88%	83%	78%	89%	86%	90%	86%	80%	88%	79%	90%
65.6%	64%	68%	68%	71%	59%	75%	74%	80%	56%	72%	55%	55%	56%
73.6%	80%	86%	82%	69%	73%	73%	75%	83%	94%	52%	66%	52%	72%
84.2%	91%	84%	85%	90%	71%	87%	88%	96%	86%	55%	84%	85%	92%
83.0%	90%	84%	83%	90%	89%	68%	69%	80%	76%	88%	85%	94%	83%
73.8%	76%	66%	70%	58%	97%	79%	77%	54%	88%	56%	61%	93%	85%
78.3%	79%	89%	76%	94%	85%	61%	73%	76%	90%	48%	80%	78%	89%
87.0%	87%	87%	87%	87%	87%	87%	87%	87%	87%	87%	87%	87%	87%
72.6%	76%	83%	80%	69%	51%	71%	73%	69%	80%	62%	79%	71%	80%
71.3%	72%	63%	77%	65%	59%	75%	65%	61%	76%	86%	77%	78%	73%
94.9%	94%	95%	95%	96%	94%	96%	94%	98%	95%	93%	93%	94%	97%
78.0%	86%	82%	87%	77%	75%	80%	78%	89%	85%	43%	72%	74%	86%
80.1%	86%	88%	95%	79%	67%	74%	75%	95%	89%	55%	75%	79%	84%
80.4%	92%	76%	83%	81%	90%	68%	78%	86%	77%	86%	77%	76%	75%
76.5%	85%	87%	89%	77%	76%	77%	79%	82%	78%	35%	64%	86%	79%
66.5%	77%	70%	73%	36%	60%	47%	64%	74%	67%	69%	76%	78%	74%
87.1%	87%	81%	88%	90%	93%	75%	95%	91%	86%	89%	76%	90%	91%
73.8%	76%	78%	79%	66%	71%	74%	70%	71%	75%	74%	82%	77%	66%
75.4%	74%	89%	71%	94%	90%	56%	68%	71%	85%	44%	76%	74%	88%
79.0%	70%	73%	83%	56%	92%	84%	66%	72%	87%	89%	86%	85%	84%
83.5%	85%	87%	92%	73%	72%	91%	76%	87%	84%	88%	79%	84%	88%
78.2%	91%	76%	65%	63%	77%	80%	76%	79%	91%	63%	93%	85%	77%
84.8%	94%	94%	94%	93%	10%	81%	98%	84%	88%	81%	91%	97%	97%
68.5%	71%	74%	72%	72%	61%	62%	63%	78%	87%	74%	71%	59%	46%
73.1%	77%	62%	79%	51%	70%	81%	66%	60%	82%	79%	80%	78%	85%
76.3%	79%	79%	86%	80%	67%	81%	81%	86%	78%	69%	69%	59%	78%
82.5%	90%	72%	83%	85%	70%	89%	85%	95%	88%	56%	82%	84%	93%
84.0%	87%	76%	79%	78%	89%	89%	86%	89%	89%	78%	92%	87%	73%
85.5%	90%	90%	86%	82%	95%	84%	94%	87%	78%	86%	80%	69%	90%
82.0%	78%	85%	88%	86%	83%	87%	91%	87%	73%	73%	75%	73%	87%
77.8%	77%	85%	88%	80%	70%	80%	80%	84%	82%	66%	79%	75%	66%
70.7%	77%	73%	73%	38%	71%	72%	79%	77%	75%	71%	79%	76%	58%
74.8%	66%	80%	80%	68%	84%	60%	63%	72%	82%	78%	83%	78%	79%
87.1%	93%	91%	78%	87%	90%	79%	78%	77%	95%	80%	97%	93%	94%
81.6%	76%	84%	82%	87%	80%	88%	87%	78%	87%	49%	92%	84%	87%
75.9%	74%	87%	87%	85%	81%	66%	77%	82%	77%	75%	59%	67%	70%
72.0%	70%	73%	77%	84%	40%	61%	74%	76%	70%	80%	81%	70%	80%
73.4%	68%	83%	77%	69%	64%	74%	74%	80%	82%	47%	82%	77%	77%
85.2%	87%	87%	87%	94%	83%	87%	95%	88%	82%	66%	79%	88%	84%
73.5%	89%	95%	82%	80%	66%	70%	87%	67%	73%	32%	62%	72%	80%