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 10034ac...

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:

Select Prompt:

Average key point coverage extent for each model across all prompts.

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	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	2nd 80.0%	4th 77.3%	- -	1st 80.6%	5th 66.9%	3rd 78.0%
66.0%	64%	44%		80%	63%	79%
73.4%	79%	87%		60%	66%	75%
67.8%	91%	68%		72%	32%	76%
87.0%	87%	87%		87%	87%	87%
77.4%	70%	89%		73%	67%	88%
77.4%	56%	79%		79%	85%	88%
84.0%	74%	83%		82%	93%	88%
59.4%	57%	76%		55%	54%	55%
76.6%	79%	88%		87%	63%	66%
81.8%	91%	91%		88%	56%	83%
87.2%	89%	90%		84%	88%	85%
61.4%	76%	59%		85%	33%	54%
78.0%	79%	88%		95%	48%	80%
87.0%	87%	87%		87%	87%	87%
73.2%	76%	78%		73%	60%	79%
73.6%	72%	70%		76%	73%	77%
93.6%	94%	94%		94%	93%	93%
73.6%	86%	77%		88%	53%	64%
76.8%	86%	80%		88%	55%	75%
83.4%	92%	76%		84%	88%	77%
65.0%	85%	67%		79%	35%	59%
65.4%	77%	40%		61%	73%	76%
86.0%	87%	90%		84%	93%	76%
75.0%	79%	67%		75%	72%	82%
75.0%	74%	88%		93%	44%	76%
77.6%	70%	61%		85%	91%	81%
76.6%	85%	72%		86%	61%	79%
81.8%	92%	68%		85%	71%	93%
91.0%	94%	91%		93%	96%	81%
72.6%	71%	75%		66%	76%	75%
74.2%	77%	53%		79%	82%	80%
75.2%	79%	82%		77%	69%	69%
80.6%	89%	91%		90%	51%	82%
86.6%	92%	77%		83%	89%	92%
76.8%	90%	79%		79%	63%	73%
74.2%	78%	84%		78%	66%	65%
75.0%	77%	83%		82%	51%	82%
69.2%	77%	38%		76%	71%	84%
75.2%	66%	62%		82%	83%	83%
91.4%	93%	97%		95%	80%	92%
78.2%	76%	86%		87%	50%	92%
68.8%	73%	80%		75%	56%	60%
74.0%	77%	89%		66%	54%	84%
69.2%	68%	71%		82%	47%	78%
84.4%	87%	94%		82%	72%	87%
64.2%	84%	79%		70%	37%	51%