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%3Amore Concerned Than Excited C10 - Run 566c4a5...

Global Dialogues GD3 - More concerned than excited (10 context Qs)

DTEF: Predict response distributions for More concerned than excited. Source: Global Dialogues GD3 (https://github.com/collect-intel/global-dialogues)

TAGS:

Instruction Following & Prompt Adherence

Reasoning

Factual Accuracy & Hallucination

General Knowledge

Efficiency & Succinctness

Best Models (Coverage)

1.Claude Haiku 4.5
82.7%
2.Claude Sonnet 4.5
81.9%
3.Mistral Medium 3
81.7%
4.GPT 4.1
81.5%
5.Llama 4 Maverick
80.7%

View Blueprint

Select Prompt:

Macro Coverage Overview

Average key point coverage extent for each model across all prompts.

Pro Tip

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	Claude Sonnet 4	Claude Sonnet 4.5	Gemini 2.5 Flash	Gemma 3 12b It	Llama 4 Maverick	Mistral Medium 3	GPT 4.1	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini	Qwen3 30b A3B Instruct 2507	Qwen3 Next 80b A3B Instruct
Score	1st 82.7%	6th 79.7%	2nd 81.9%	6th 79.7%	11th 72.7%	5th 80.7%	3rd 81.7%	4th 81.5%	10th 73.6%	13th 52.2%	12th 71.8%	9th 76.1%	8th 76.9%
75.5%	92%	83%	78%	79%	71%	80%	86%	89%	70%	38%	66%	76%	74%
80.5%	81%	87%	90%	84%	76%	82%	97%	94%	77%	16%	79%	91%	92%
60.3%	55%	39%	78%	62%	31%	69%	59%	52%	50%	80%	97%	53%	59%
88.3%	75%	91%	93%	92%	84%	93%	94%	95%	89%	94%	90%	83%	75%
90.0%	95%	97%	97%	94%	95%	95%	90%	92%	85%	77%	82%	97%	74%
83.5%	94%	92%	93%	90%	79%	78%	76%	78%	73%	93%	89%	75%	76%
83.0%	87%	81%	85%	72%	83%	83%	93%	85%	72%	74%	90%	87%	87%
67.8%	86%	69%	72%	72%	49%	82%	84%	80%	63%	29%	67%	62%	67%
75.8%	84%	70%	71%	83%	71%	84%	74%	81%	79%	73%	67%	74%	74%
93.6%	96%	94%	96%	94%	94%	92%	94%	95%	85%	95%	94%	94%	94%
78.5%	90%	86%	86%	75%	75%	79%	83%	71%	74%	83%	60%	83%	75%
89.7%	93%	95%	96%	93%	80%	90%	91%	80%	88%	95%	81%	95%	89%
82.4%	73%	84%	81%	83%	87%	72%	80%	78%	86%	85%	86%	87%	89%
88.1%	92%	90%	91%	88%	89%	89%	93%	95%	90%	56%	86%	94%	92%
77.7%	90%	79%	87%	87%	75%	94%	92%	91%	76%	8%	75%	78%	78%
72.3%	87%	76%	82%	82%	76%	72%	85%	87%	65%	12%	62%	82%	72%
52.5%	75%	66%	62%	61%	46%	58%	49%	50%	47%	36%	37%	40%	55%
60.8%	76%	69%	69%	65%	54%	63%	80%	73%	50%	14%	47%	71%	59%
64.8%	58%	77%	71%	69%	59%	66%	63%	83%	59%	44%	78%	54%	61%
80.7%	85%	85%	83%	83%	75%	86%	82%	86%	79%	72%	73%	77%	83%
79.0%	89%	83%	81%	84%	72%	86%	88%	89%	87%	17%	80%	83%	88%
80.5%	89%	82%	82%	90%	76%	85%	90%	94%	90%	7%	83%	87%	91%
80.2%	81%	77%	76%	83%	72%	82%	78%	86%	82%	78%	81%	86%	80%
81.5%	84%	80%	80%	85%	74%	84%	89%	85%	86%	63%	82%	85%	82%
86.4%	90%	89%	87%	79%	88%	85%	94%	95%	89%	55%	87%	96%	89%
77.4%	81%	81%	81%	86%	82%	81%	78%	86%	80%	25%	80%	84%	81%
70.7%	84%	77%	78%	77%	65%	66%	84%	82%	65%	41%	59%	81%	60%
67.7%	86%	74%	82%	81%	70%	81%	78%	63%	51%	48%	49%	49%	68%
75.8%	85%	84%	88%	89%	64%	83%	71%	72%	72%	66%	70%	71%	71%
65.6%	82%	74%	81%	71%	75%	71%	78%	71%	46%	56%	41%	64%	43%
77.2%	79%	83%	77%	85%	82%	82%	85%	86%	79%	21%	81%	83%	81%
83.3%	98%	85%	74%	90%	75%	83%	94%	99%	96%	39%	56%	100%	94%
56.8%	51%	35%	73%	58%	27%	65%	55%	48%	46%	84%	92%	49%	55%
75.2%	72%	81%	82%	95%	67%	72%	77%	82%	70%	72%	69%	70%	69%
79.0%	86%	82%	91%	54%	78%	77%	73%	78%	77%	81%	85%	82%	83%
76.0%	87%	94%	89%	59%	87%	89%	87%	91%	70%	26%	66%	69%	74%
77.1%	88%	81%	84%	88%	79%	88%	90%	88%	72%	11%	65%	82%	86%
86.8%	79%	95%	95%	96%	95%	93%	94%	95%	97%	65%	59%	70%	95%
68.4%	83%	77%	74%	80%	66%	86%	72%	79%	62%	31%	55%	56%	68%
82.3%	90%	73%	85%	98%	63%	94%	95%	88%	85%	49%	67%	88%	95%
74.9%	92%	89%	90%	61%	92%	93%	94%	81%	55%	37%	42%	64%	84%
55.3%	49%	57%	57%	53%	53%	63%	53%	67%	57%	44%	62%	53%	51%
75.2%	89%	83%	73%	76%	75%	73%	69%	65%	92%	53%	71%	66%	93%