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: Gd7 C10 Dtef Global Dialogues Gd7 AiConcern%3Amore Excited Than Concerned C10 - Run 1e0826d...

Global Dialogues GD7 - More excited than concerned (10 context Qs)

DTEF: Predict response distributions for More excited than concerned. Source: Global Dialogues GD7 (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 80.6%	2nd 77.3%	- -	3rd 77.1%	5th 59.7%	4th 73.3%
77.4%	78%	59%		78%	93%	79%
77.6%	78%	94%		74%	71%	71%
76.8%	77%	88%		82%	59%	78%
76.8%	76%	82%		70%	74%	82%
70.2%	91%	58%		67%	73%	62%
29.0%	29%	29%		29%	29%	29%
64.4%	86%	66%		80%	33%	57%
60.6%	71%	96%		18%	74%	44%
65.8%	74%	74%		74%	45%	62%
62.0%	82%	66%		70%	36%	56%
79.8%	83%	93%		84%	63%	76%
65.0%	76%	59%		87%	30%	73%
63.8%	71%	90%		78%	16%	64%
70.2%	83%	86%		86%	10%	86%
67.8%	84%	86%		73%	8%	88%
72.6%	81%	63%		80%	74%	65%
73.6%	80%	62%		74%	76%	76%
85.4%	88%	74%		90%	87%	88%
89.0%	92%	94%		78%	92%	89%
76.2%	92%	90%		88%	25%	86%
74.0%	85%	88%		88%	21%	88%
63.0%	93%	67%		66%	28%	61%
71.4%	77%	69%		57%	77%	77%
68.4%	83%	38%		75%	72%	74%
67.8%	79%	85%		82%	8%	85%
79.6%	83%	80%		90%	59%	86%
89.0%	97%	89%		88%	89%	82%
81.2%	92%	96%		97%	29%	92%
76.4%	85%	84%		80%	63%	70%
88.0%	88%	88%		88%	88%	88%
56.2%	51%	77%		51%	51%	51%
82.4%	90%	86%		83%	86%	67%
69.2%	87%	78%		84%	37%	60%
59.6%	83%	62%		68%	37%	48%
70.8%	68%	92%		72%	63%	59%
80.2%	90%	82%		77%	76%	76%
65.6%	77%	46%		79%	63%	63%
81.6%	72%	72%		83%	89%	92%
76.6%	70%	66%		84%	82%	81%
87.8%	84%	89%		90%	88%	88%
80.8%	80%	89%		77%	74%	84%
69.0%	82%	77%		66%	50%	70%
69.2%	81%	58%		78%	70%	59%
79.8%	91%	69%		88%	75%	76%
67.2%	66%	100%		63%	41%	66%
85.8%	79%	92%		85%	88%	85%
72.4%	84%	84%		61%	76%	57%
73.0%	81%	56%		75%	79%	74%
95.8%	94%	93%		98%	95%	99%
81.6%	71%	89%		80%	76%	92%
72.4%	94%	82%		85%	37%	64%
80.2%	78%	81%		89%	82%	71%
77.6%	76%	93%		79%	63%	77%
76.2%	88%	66%		95%	45%	87%