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: Gd3 C10 Dtef Global Dialogues Gd3 AiConcern%3Aequally Concerned And Excited C10 - Run 46b62b4...

Global Dialogues GD3 - Equally concerned and excited (10 context Qs)

DTEF: Predict response distributions for Equally concerned and excited. Source: Global Dialogues GD3 (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	1st 84.0%	3rd 81.2%	- -	2nd 83.3%	5th 64.0%	4th 73.7%
67.2%	74%	77%		88%	40%	57%
65.6%	86%	62%		91%	13%	76%
68.6%	68%	62%		74%	62%	77%
88.2%	84%	92%		93%	92%	80%
89.4%	99%	84%		96%	93%	75%
91.6%	91%	92%		94%	89%	92%
89.0%	91%	90%		87%	88%	89%
75.2%	86%	84%		92%	42%	72%
85.6%	84%	91%		92%	85%	76%
92.0%	92%	92%		92%	92%	92%
85.8%	91%	87%		83%	81%	87%
90.8%	93%	91%		90%	94%	86%
78.8%	87%	81%		86%	53%	87%
81.6%	93%	94%		92%	68%	61%
84.4%	86%	90%		92%	72%	82%
79.4%	85%	79%		87%	82%	64%
67.2%	91%	70%		64%	36%	75%
75.4%	83%	83%		75%	58%	78%
59.8%	54%	79%		61%	49%	56%
82.8%	93%	90%		79%	76%	76%
69.4%	88%	83%		90%	20%	66%
86.0%	86%	85%		92%	79%	88%
78.0%	80%	93%		89%	49%	79%
81.2%	95%	88%		88%	59%	76%
75.8%	80%	81%		94%	64%	60%
71.8%	81%	79%		80%	68%	51%
72.6%	80%	80%		68%	70%	65%
79.8%	89%	92%		86%	41%	91%
79.4%	92%	87%		73%	78%	67%
73.2%	82%	70%		86%	68%	60%
71.6%	84%	83%		88%	20%	83%
71.6%	79%	86%		75%	86%	32%
64.6%	62%	55%		67%	55%	84%
79.8%	81%	91%		78%	73%	76%
72.6%	94%	50%		69%	79%	71%
76.2%	86%	69%		79%	74%	73%
66.4%	81%	84%		84%	9%	74%
82.2%	86%	81%		90%	71%	83%
80.4%	84%	85%		81%	73%	79%
85.0%	93%	90%		99%	90%	53%
82.0%	93%	96%		89%	40%	92%
41.8%	41%	46%		37%	44%	41%
82.2%	86%	66%		93%	77%	89%