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 C10 Dtef Global Dialogues Gd5 AiConcern%3Aequally Concerned And Excited C10 - Run b9e46b6...

Global Dialogues GD5 - Equally concerned and excited (10 context Qs)

DTEF: Predict response distributions for Equally concerned and excited. 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 81.8%	3rd 80.5%	5th 74.5%	1st 83.4%	6th 72.6%	4th 75.4%
87.7%	88%	84%	88%	93%	88%	85%
70.2%	80%	82%	62%	61%	74%	62%
67.5%	96%	61%	66%	70%	37%	75%
89.0%	89%	89%	89%	89%	89%	89%
81.5%	90%	94%	85%	86%	72%	62%
79.3%	48%	88%	81%	78%	90%	91%
93.2%	84%	96%	93%	96%	97%	93%
57.2%	61%	71%	47%	59%	47%	58%
74.0%	70%	93%	67%	93%	60%	61%
81.0%	88%	83%	74%	83%	74%	84%
87.5%	94%	94%	94%	85%	79%	79%
69.0%	85%	57%	67%	86%	53%	66%
72.0%	86%	83%	60%	94%	54%	55%
89.0%	89%	89%	89%	89%	89%	89%
70.7%	73%	72%	53%	77%	72%	77%
91.0%	93%	89%	93%	88%	92%	91%
92.8%	92%	94%	95%	93%	90%	93%
69.0%	75%	82%	85%	87%	39%	46%
75.5%	78%	83%	78%	80%	79%	55%
65.8%	77%	77%	59%	78%	39%	65%
58.5%	69%	58%	68%	79%	30%	47%
71.5%	90%	60%	62%	78%	58%	81%
82.5%	87%	90%	59%	89%	96%	74%
77.8%	77%	88%	67%	76%	79%	80%
68.8%	84%	78%	56%	93%	51%	51%
73.5%	73%	85%	81%	82%	50%	70%
82.5%	94%	77%	69%	92%	76%	87%
84.7%	91%	66%	83%	93%	77%	98%
80.2%	91%	93%	10%	91%	98%	98%
73.7%	76%	82%	76%	75%	62%	71%
92.7%	91%	92%	95%	92%	97%	89%
73.0%	71%	80%	72%	81%	69%	65%
77.3%	72%	86%	73%	74%	80%	79%
86.3%	86%	85%	87%	88%	84%	88%
83.7%	77%	88%	94%	76%	85%	82%
81.3%	77%	89%	96%	79%	75%	72%
87.8%	92%	87%	82%	92%	91%	83%
68.8%	75%	36%	67%	76%	75%	84%
69.3%	69%	62%	65%	84%	65%	71%
85.8%	91%	69%	84%	92%	88%	91%
90.0%	95%	95%	90%	92%	90%	78%
77.5%	75%	81%	84%	89%	71%	65%
72.3%	81%	84%	61%	63%	68%	77%
73.7%	69%	66%	64%	84%	79%	80%
86.0%	90%	87%	93%	83%	75%	88%
68.3%	85%	78%	65%	79%	58%	45%