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 C5 Dtef Global Dialogues Gd3 AiConcern%3Aequally Concerned And Excited C5 - Run 46b62b4...

Global Dialogues GD3 - Equally concerned and excited (5 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 81.1%	- -	2nd 82.7%	5th 54.7%	4th 69.9%
68.0%	84%	82%		88%	37%	49%
67.8%	85%	79%		91%	13%	71%
75.4%	72%	70%		81%	77%	77%
89.6%	86%	93%		91%	92%	86%
89.4%	96%	86%		86%	87%	92%
93.4%	91%	99%		84%	94%	99%
65.6%	91%	88%		85%	34%	30%
74.2%	86%	83%		92%	50%	60%
81.8%	84%	91%		87%	69%	78%
91.0%	95%	89%		86%	94%	91%
81.2%	91%	83%		85%	66%	81%
92.2%	91%	93%		91%	94%	92%
79.0%	96%	89%		93%	46%	71%
62.0%	82%	84%		86%	24%	34%
73.8%	88%	93%		90%	18%	80%
70.0%	78%	77%		87%	54%	54%
67.8%	91%	66%		71%	41%	70%
73.8%	75%	85%		65%	69%	75%
55.4%	48%	72%		59%	49%	49%
71.2%	88%	90%		90%	11%	77%
67.0%	88%	87%		93%	20%	47%
81.0%	90%	85%		92%	58%	80%
79.6%	74%	85%		77%	66%	96%
67.0%	93%	84%		82%	14%	62%
61.2%	89%	82%		83%	18%	34%
65.4%	74%	79%		81%	33%	60%
73.4%	79%	78%		64%	75%	71%
81.0%	89%	94%		91%	44%	87%
75.4%	90%	81%		72%	68%	66%
74.8%	86%	76%		89%	63%	60%
77.2%	85%	83%		87%	60%	71%
56.4%	75%	73%		70%	32%	32%
72.4%	65%	55%		74%	84%	84%
68.4%	87%	74%		95%	20%	66%
72.8%	86%	50%		80%	65%	83%
77.6%	82%	69%		86%	78%	73%
73.4%	86%	92%		89%	17%	83%
82.6%	86%	88%		74%	86%	79%
79.2%	82%	83%		84%	67%	80%
76.8%	97%	93%		88%	53%	53%
87.4%	94%	79%		89%	83%	92%
43.2%	46%	51%		37%	41%	41%
86.2%	89%	73%		89%	89%	91%