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%3Amore Concerned Than Excited C10 - Run adca5fa...

Global Dialogues GD5 - More concerned than excited (10 context Qs)

DTEF: Predict response distributions for More concerned than 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 79.5%	4th 76.0%	- -	1st 80.1%	5th 59.1%	3rd 76.7%
84.6%	78%	87%		89%	87%	82%
68.0%	86%	90%		71%	27%	66%
53.6%	80%	65%		49%	29%	45%
82.0%	82%	82%		82%	82%	82%
86.8%	92%	89%		93%	77%	83%
59.2%	50%	0%		71%	84%	91%
82.0%	91%	95%		86%	49%	89%
64.8%	56%	77%		74%	54%	63%
69.6%	69%	92%		91%	56%	40%
61.8%	74%	73%		89%	8%	65%
72.2%	81%	75%		77%	49%	79%
75.2%	81%	69%		82%	54%	90%
75.6%	84%	94%		88%	31%	81%
82.0%	82%	82%		82%	82%	82%
67.8%	70%	70%		70%	61%	68%
86.4%	90%	83%		76%	95%	88%
88.0%	87%	92%		87%	87%	87%
72.8%	92%	94%		82%	28%	68%
66.2%	79%	83%		76%	26%	67%
63.6%	76%	71%		78%	30%	63%
66.8%	72%	69%		75%	45%	73%
77.6%	98%	51%		80%	68%	91%
81.6%	95%	87%		80%	73%	73%
74.2%	71%	84%		64%	74%	78%
75.6%	83%	95%		88%	31%	81%
74.2%	71%	82%		86%	45%	87%
83.0%	83%	70%		92%	83%	87%
74.8%	87%	69%		86%	46%	86%
93.0%	95%	97%		89%	87%	97%
75.0%	70%	69%		77%	74%	85%
80.8%	82%	80%		82%	75%	85%
62.2%	71%	71%		61%	66%	42%
59.0%	70%	69%		83%	7%	66%
73.2%	72%	79%		63%	76%	76%
87.6%	86%	90%		92%	85%	85%
78.0%	79%	84%		78%	79%	70%
85.0%	85%	80%		88%	91%	81%
68.2%	67%	64%		68%	69%	73%
63.4%	68%	52%		83%	45%	69%
63.2%	86%	0%		90%	50%	90%
91.8%	89%	96%		96%	87%	91%
77.0%	82%	85%		79%	63%	76%
53.8%	69%	76%		55%	19%	50%
77.6%	77%	77%		92%	56%	86%
85.0%	94%	81%		83%	75%	92%
74.0%	76%	78%		83%	55%	78%