Infographics

Precise data, readable text, numbers

4 tasks · 11 models tested · 44 results

Solar system

image
google gemini-2.5-flash-image
5.0/10 8.5 s
google gemini-2.5-flash-image
Cost < 0.01 $
Resolution 1344 x 768
Time 8.5 s
Matania Judgment
Quality
7
Composition
8
Creativity
7
Text accuracy
2
Fidelity
4
Overall
5
Review
The image is aesthetically pleasing with good visual composition, but it fails on the critical aspects of the prompt. Fidelity is low as the scale of the planets is not respected, and the text is nearly illegible or composed of incoherent characters (gibberish), making the infographic and fact-presentation functions impossible.
google gemini-3-pro-image-preview
5.5/10 31.3 s
google gemini-3-pro-image-preview
Cost < 0.01 $
Resolution 2752 x 1536
Time 31.3 s
Matania Judgment
Quality
7
Composition
8
Creativity
7
Text accuracy
2
Fidelity
5
Overall
5.5
Review
The image is aesthetically successful with a beautiful poster-like composition, but it fails on the requested functional aspects. The text is nearly illegible and composed of incoherent characters (gibberish), which makes the "infographic" and "key facts" elements completely ineffective. Furthermore, the "to scale" constraint is difficult to verify but appears to have been sacrificed in favor of visual aesthetics.
google imagen-4.0-fast-generate-001
4.8 s
google imagen-4.0-fast-generate-001
Cost 0.02 $
Resolution 1408 x 768
Time 4.8 s
google imagen-4.0-generate-001
5.0/10 11.4 s
google imagen-4.0-generate-001
Cost 0.04 $
Resolution 1408 x 768
Time 11.4 s
Matania Judgment
Quality
8
Composition
7
Creativity
7
Text accuracy
2
Fidelity
4
Overall
5
Review
The image is aesthetically successful with great visual quality, but it fails on textual and scientific constraints. The text is mostly illegible or composed of incoherent characters (textual hallucinations), which makes the "infographic" and "key facts" aspects completely ineffective. Furthermore, the request to be "to scale" is visually impossible to respect in a single image of this type, and the lack of text readability heavily penalizes prompt fidelity.
google imagen-4.0-ultra-generate-001
5.3/10 11.9 s
google imagen-4.0-ultra-generate-001
Cost 0.08 $
Resolution 1408 x 768
Time 11.9 s
Matania Judgment
Quality
8
Composition
9
Creativity
7
Text accuracy
2
Fidelity
4
Overall
5.25
Review
The visual aesthetics and composition are excellent, offering a professional and appealing output. However, the model fails heavily on fidelity and textual accuracy: the text is composed of incoherent characters (gibberish) and the scale of the planets is not respected, despite this being an explicit constraint in the prompt.
openai chatgpt-image-latest
5.0/10 46.7 s
openai chatgpt-image-latest
Cost 0.22 $
Resolution 1536 x 1024
Time 46.7 s
Matania Judgment
Quality
7
Composition
8
Creativity
7
Text accuracy
2
Fidelity
4
Overall
5
Review
The image is aesthetically pleasing with a beautiful poster-like composition, but it fails on both critical points of the prompt: the scale of the planets is not respected at all, and the text is largely illegible or composed of incoherent characters. Fidelity is penalized by the model's inability to generate accurate textual information and a consistent scientific scale as requested.
segmind ideogram-3
6.5/10 16.0 s
segmind ideogram-3
Cost 0.04 $
Resolution 1344 x 768
Time 16.0 s
Matania Judgment
Quality
8
Composition
9
Creativity
7
Text accuracy
4
Fidelity
6
Overall
6.5
Review
The visual aesthetics and composition are excellent, successfully achieving a "poster" look. However, fidelity is compromised by the model's inability to generate legible and coherent text, turning the requested facts into visual gibberish. Furthermore, the "planets to scale" constraint is visually impossible to respect on a poster of this type without sacrificing readability, but the major failure lies in the textual accuracy.
segmind seedream-4.5
5.5/10 25.8 s
segmind seedream-4.5
Cost 0.04 $
Resolution 2560 x 1472
Time 25.8 s
Matania Judgment
Quality
7
Composition
8
Creativity
7
Text accuracy
2
Fidelity
5
Overall
5.5
Review
The visual aesthetics and infographic composition are successful, offering a clean and attractive output. However, prompt adherence is heavily penalized by the model's inability to generate legible and coherent text, rendering the 'key facts' completely unreadable and nonsensical. Furthermore, the 'to scale' constraint is difficult to verify and appears to have been sacrificed in favor of aesthetics.
segmind seedream-v5-lite
4.4/10 51.5 s
segmind seedream-v5-lite
Cost 0.04 $
Resolution 2848 x 1600
Time 51.5 s
Matania Judgment
Quality
6
Composition
7
Creativity
5
Text accuracy
1
Fidelity
4
Overall
4.38
Review
The image fails on the most crucial point: textual accuracy. Although it visually resembles an infographic, the text consists of scribbles and illegible characters, which contradicts the instruction 'featuring key facts.' Furthermore, the 'planets to scale' constraint is visually impossible to respect within such a composition, and the overall fidelity is penalized by the model's inability to generate coherent text.
xai grok-imagine-image
6.0/10 7.6 s
xai grok-imagine-image
Cost 0.02 $
Resolution 2752 x 1504
Time 7.6 s
Matania Judgment
Quality
7
Composition
8
Creativity
7
Text accuracy
2
Fidelity
6
Overall
6
Review
The visual aesthetics and composition are successful, providing a professional infographic look. However, fidelity is compromised by the AI's inability to generate legible and coherent text, rendering the requested "key facts" completely unusable. Furthermore, the "to scale" constraint is impossible to verify visually and appears to be ignored in favor of aesthetic presentation.
xai grok-imagine-image-pro
5.0/10 17.4 s
xai grok-imagine-image-pro
Cost 0.07 $
Resolution 2816 x 1536
Time 17.4 s
Matania Judgment
Quality
7
Composition
8
Creativity
7
Text accuracy
2
Fidelity
4
Overall
5
Review
The visual aesthetics and composition are successful, offering a professional poster-like appearance. However, the model fails heavily on fidelity and textual accuracy: the text is unreadable gibberish instead of real facts, and the requirement to render planets to scale is visually impossible to achieve within this type of graphic composition. The fidelity score is penalized by the inability to generate coherent English text as requested.

Climate

image
google gemini-2.5-flash-image
6.6/10 7.3 s
google gemini-2.5-flash-image
Cost < 0.01 $
Resolution 1344 x 768
Time 7.3 s
Matania Judgment
Quality
7
Composition
8
Creativity
6
Text accuracy
4
Fidelity
7
Overall
6.63
Review
The image adheres well to the overall theme, and the composition is aesthetically pleasing for a data visualization. However, the accuracy of the text and numbers is low, exhibiting the inconsistent characters typical of image generation models. While the subject fidelity is correct, the "data visualization" aspect suffers from a lack of scientific rigor regarding scales and labels.
google gemini-3-pro-image-preview
7.6/10 27.5 s
google gemini-3-pro-image-preview
Cost < 0.01 $
Resolution 2752 x 1536
Time 27.5 s
Matania Judgment
Quality
8
Composition
7
Creativity
6
Text accuracy
4
Fidelity
9
Overall
7.63
Review
The image adheres well to the requested elements (temperature, CO2, 150 years, English language) with a clean aesthetic. However, the accuracy of the text and figures is poor, displaying the incoherent characters typical of image generation models. The composition is effective but remains fairly conventional for a data visualization.
google imagen-4.0-fast-generate-001
4.3 s
google imagen-4.0-fast-generate-001
Cost 0.02 $
Resolution 1408 x 768
Time 4.3 s
google imagen-4.0-generate-001
8.0/10 10.1 s
google imagen-4.0-generate-001
Cost 0.04 $
Resolution 1408 x 768
Time 10.1 s
Matania Judgment
Quality
8
Composition
9
Creativity
7
Text accuracy
4
Fidelity
9
Overall
8
Review
The image is aesthetically very successful, featuring a balanced composition and high technical quality. It perfectly respects the subject matter (climate, 150 years, temperature, and CO2), but fails on textual precision: the numbers and words are incoherent glyphs typical of image generation models, which undermines the readability of a data visualization.
google imagen-4.0-ultra-generate-001
7.6/10 16.5 s
google imagen-4.0-ultra-generate-001
Cost 0.08 $
Resolution 1408 x 768
Time 16.5 s
Matania Judgment
Quality
8
Composition
7
Creativity
6
Text accuracy
4
Fidelity
9
Overall
7.63
Review
The image adheres well to the data visualization request, featuring two distinct curves for temperature and CO2 over a long period. However, the textual accuracy is poor, with illegible or inconsistent characters and numbers, which is a common issue in image generation. While the composition is aesthetic and clean, it lacks true scientific rigor.
openai chatgpt-image-latest
7.9/10 44.0 s
openai chatgpt-image-latest
Cost 0.22 $
Resolution 1536 x 1024
Time 44.0 s
Matania Judgment
Quality
8
Composition
8
Creativity
7
Text accuracy
4
Fidelity
9
Overall
7.88
Review
The image adheres very well to the requested elements (temperature and CO2 graphs, 150-year context) with a polished aesthetic. However, the textual accuracy is poor, featuring the incoherent numbers and words typical of image generation models, which is problematic for a data visualization task.
segmind ideogram-3
8.8/10 15.7 s
segmind ideogram-3
Cost 0.04 $
Resolution 1344 x 768
Time 15.7 s
Matania Judgment
Quality
8
Composition
9
Creativity
7
Text accuracy
6
Fidelity
10
Overall
8.75
Review
The image perfectly respects all elements of the prompt, including both types of charts and the requested language. The composition is aesthetic and professional, typical of a high-quality infographic. However, textual precision could be improved, as some figures or y-axis labels are slightly blurry or inconsistent, which is common for image generation models.
segmind seedream-4.5
7.0/10 24.2 s
segmind seedream-4.5
Cost 0.04 $
Resolution 2560 x 1472
Time 24.2 s
Matania Judgment
Quality
7
Composition
8
Creativity
6
Text accuracy
3
Fidelity
8
Overall
7
Review
The image adheres well to the requested theme and structure, featuring two distinct charts. However, textual precision is very low, with illegible or incoherent text (typical hallucinations of image models), which undermines its function as a "data visualization." While the composition is aesthetically pleasing, the informative aspect is sacrificed for visual rendering.
segmind seedream-v5-lite
5.5/10 32.5 s
segmind seedream-v5-lite
Cost 0.04 $
Resolution 2848 x 1600
Time 32.5 s
Matania Judgment
Quality
7
Composition
6
Creativity
5
Text accuracy
2
Fidelity
6
Overall
5.5
Review
The image respects the overall theme of climate data visualization but fails on textual accuracy, displaying the incoherent and illegible text typical of image generation models. Fidelity is mediocre because, although charts are present, they lack actual scientific structure, and the readability required by the "data visualization" aspect is sacrificed in favor of a generic aesthetic.
xai grok-imagine-image
7.8/10 6.5 s
xai grok-imagine-image
Cost 0.02 $
Resolution 2752 x 1504
Time 6.5 s
Matania Judgment
Quality
8
Composition
8
Creativity
6
Text accuracy
4
Fidelity
9
Overall
7.75
Review
The image perfectly adheres to the request for a 150-year data visualization featuring the two curves (temperature and CO2). While the aesthetic quality and composition are excellent, the text precision is poor, displaying the illegible or inconsistent characters typical of image generation models. However, fidelity to the overall concept is very high.
xai grok-imagine-image-pro
7.6/10 20.3 s
xai grok-imagine-image-pro
Cost 0.07 $
Resolution 2816 x 1536
Time 20.3 s
Matania Judgment
Quality
8
Composition
7
Creativity
6
Text accuracy
4
Fidelity
9
Overall
7.63
Review
The image perfectly respects the requested elements (temperature, CO2, 150-year period) with a clean aesthetic. However, textual precision is low, with characters and numbers becoming illegible or inconsistent as soon as you zoom in—a classic flaw of image generation models when handling complex textual data.

Periodic table

image
google gemini-2.5-flash-image
2.0/10 6.2 s
google gemini-2.5-flash-image
Cost < 0.01 $
Resolution 1344 x 768
Time 6.2 s
Matania Judgment
Quality
4
Composition
5
Creativity
3
Text accuracy
0
Fidelity
1
Overall
2
Review
The image fails critically at the requested task. Although it possesses a "painterly" aesthetic, the text is completely illegible, consisting of incoherent characters and fanciful symbols devoid of any scientific value. Fidelity is almost non-existent, as precise data (atomic numbers, masses, exact names) are missing in favor of a purely decorative and erroneous rendering.
google gemini-3-pro-image-preview
2.0/10 26.3 s
google gemini-3-pro-image-preview
Cost < 0.01 $
Resolution 2752 x 1536
Time 26.3 s
Matania Judgment
Quality
4
Composition
5
Creativity
3
Text accuracy
0
Fidelity
1
Overall
2
Review
The image is a total failure for this specific task. Although it visually resembles a table, the text is completely illegible and consists of a string of incoherent characters (textual hallucinations), rendering the scientific information non-existent. The model fails to respect the fundamental constraint of providing accurate textual data (names, symbols, masses).
google imagen-4.0-fast-generate-001
4.2 s
google imagen-4.0-fast-generate-001
Cost 0.02 $
Resolution 1408 x 768
Time 4.2 s
google imagen-4.0-generate-001
1.6/10 7.0 s
google imagen-4.0-generate-001
Cost 0.04 $
Resolution 1408 x 768
Time 7.0 s
Matania Judgment
Quality
4
Composition
3
Creativity
2
Text accuracy
0
Fidelity
1
Overall
1.63
Review
The image is a total failure for this specific task. The model is incapable of generating a complete and legible periodic table; the text is a string of incoherent characters and unreadable symbols (textual hallucinations). Fidelity is near zero, as none of the requested scientific data is presented accurately.
google imagen-4.0-ultra-generate-001
2.6/10 10.4 s
google imagen-4.0-ultra-generate-001
Cost 0.08 $
Resolution 1408 x 768
Time 10.4 s
Matania Judgment
Quality
4
Composition
5
Creativity
3
Text accuracy
1
Fidelity
2
Overall
2.63
Review
The image fails almost entirely in its primary mission. Although it visually resembles a periodic table, the text is completely illegible, consisting of abstract and incoherent characters that respect neither the names, the symbols, nor the atomic masses requested. Fidelity is extremely low because crucial textual information is absent, rendering the image useless for its intended purpose.
openai chatgpt-image-latest
3.4/10 56.4 s
openai chatgpt-image-latest
Cost 0.24 $
Resolution 1536 x 1024
Time 56.4 s
Matania Judgment
Quality
6
Composition
7
Creativity
5
Text accuracy
1
Fidelity
2
Overall
3.38
Review
The image fails almost completely at the requested task. Although the visual aesthetics are acceptable, the text is totally illegible and incoherent (massive textual hallucinations), making the tool unusable for a periodic table. Fidelity is extremely low, as essential scientific data (names, symbols, masses) are not accurately present.
segmind ideogram-3
3.4/10 16.1 s
segmind ideogram-3
Cost 0.04 $
Resolution 1344 x 768
Time 16.1 s
Matania Judgment
Quality
6
Composition
7
Creativity
5
Text accuracy
1
Fidelity
2
Overall
3.38
Review
The image fails massively on the requested task: although the visual aesthetics are correct, the text is completely illegible, incoherent, and does not contain the 118 elements with their scientific data at all. The model generated an artistic representation of a chart rather than a functional periodic table, which constitutes a critical failure in fidelity and textual accuracy.
segmind seedream-4.5
2.6/10 26.3 s
segmind seedream-4.5
Cost 0.04 $
Resolution 2560 x 1472
Time 26.3 s
Matania Judgment
Quality
4
Composition
5
Creativity
4
Text accuracy
0
Fidelity
2
Overall
2.63
Review
The image is a total failure for this specific task. Although the visual aesthetics are reminiscent of a painting, the text is completely illegible, composed of incoherent characters and visual artifacts, rendering all scientific information (atomic numbers, symbols, masses) non-existent. The model is clearly incapable of handling dense and precise textual data such as that required by the prompt.
segmind seedream-v5-lite
1.6/10 86.1 s
segmind seedream-v5-lite
Cost 0.04 $
Resolution 2848 x 1600
Time 86.1 s
Matania Judgment
Quality
2
Composition
3
Creativity
4
Text accuracy
0
Fidelity
1
Overall
1.63
Review
The image is a total failure relative to the prompt. Although it possesses a painterly aesthetic, the text is completely illegible, consisting of meaningless scribbles, and it is impossible to distinguish the 118 elements, their symbols, or their masses. Fidelity is near zero, as the requirements for informative content and the French language are not respected at all.
xai grok-imagine-image
2.0/10 6.3 s
xai grok-imagine-image
Cost 0.02 $
Resolution 2752 x 1504
Time 6.3 s
Matania Judgment
Quality
4
Composition
5
Creativity
3
Text accuracy
0
Fidelity
1
Overall
2
Review
The image fails completely to fulfill its primary function: it is incapable of generating legible or structured text, producing only incoherent gibberish. While the visual aesthetics are acceptable, prompt adherence is virtually non-existent as the requested scientific data (atomic numbers, symbols, masses) is either absent or unreadable.
xai grok-imagine-image-pro
3.6/10 16.0 s
xai grok-imagine-image-pro
Cost 0.07 $
Resolution 2816 x 1536
Time 16.0 s
Matania Judgment
Quality
7
Composition
8
Creativity
6
Text accuracy
0
Fidelity
2
Overall
3.63
Review
The image is aesthetically successful but fails completely on a functional level. Although it resembles a periodic table, the text is entirely illegible and consists of fanciful characters with no scientific value, making the requested information (names, symbols, masses) nonexistent. Prompt adherence is very low because the primary objective of providing accurate textual data is not met.

Country comparison

image
google gemini-2.5-flash-image
4.3/10 6.7 s
google gemini-2.5-flash-image
Cost < 0.01 $
Resolution 1344 x 768
Time 6.7 s
Matania Judgment
Quality
6
Composition
5
Creativity
5
Text accuracy
2
Fidelity
4
Overall
4.25
Review
The image fails on textual accuracy, presenting incoherent and illegible text (character hallucinations), which is critical for an infographic. While the overall aesthetic attempts to follow the requested format, it fails to correctly list the 10 economies or display reliable numerical data, compromising its fidelity to the information-sharing task.
google gemini-3-pro-image-preview
6.6/10 28.5 s
google gemini-3-pro-image-preview
Cost < 0.01 $
Resolution 2752 x 1536
Time 28.5 s
Matania Judgment
Quality
7
Composition
8
Creativity
6
Text accuracy
4
Fidelity
7
Overall
6.63
Review
The image respects the infographic structure and has a clean visual appearance, but textual accuracy is very low, with incoherent or illegible words and numbers. Although the flags and the concept are present, fidelity is penalized by the model's inability to generate correct English text and accurate economic data as requested.
google imagen-4.0-fast-generate-001
4.1 s
google imagen-4.0-fast-generate-001
Cost 0.02 $
Resolution 1408 x 768
Time 4.1 s
google imagen-4.0-generate-001
4.5/10 7.3 s
google imagen-4.0-generate-001
Cost 0.04 $
Resolution 1408 x 768
Time 7.3 s
Matania Judgment
Quality
7
Composition
6
Creativity
5
Text accuracy
2
Fidelity
4
Overall
4.5
Review
The image fails on its most critical point: textual accuracy. While the aesthetics are acceptable, the text consists of illegible and incoherent pseudo-characters, making the infographic unusable. Furthermore, fidelity is compromised as the model fails to generate a structured and readable list of the 10 requested economies.
google imagen-4.0-ultra-generate-001
4.9/10 11.2 s
google imagen-4.0-ultra-generate-001
Cost 0.08 $
Resolution 1408 x 768
Time 11.2 s
Matania Judgment
Quality
7
Composition
8
Creativity
6
Text accuracy
2
Fidelity
4
Overall
4.88
Review
The image presents a polished aesthetic and a balanced composition, but fails heavily in terms of fidelity and textual accuracy. Although the infographic concept is respected, the text is largely incoherent (gibberish) and the numerical data is illegible or incorrect, which is a dealbreaker for an economic comparison task.
openai chatgpt-image-latest
4.9/10 45.1 s
openai chatgpt-image-latest
Cost 0.21 $
Resolution 1536 x 1024
Time 45.1 s
Matania Judgment
Quality
7
Composition
8
Creativity
6
Text accuracy
2
Fidelity
4
Overall
4.88
Review
The image fails on critical points requested by the prompt: the text is largely illegible or composed of incoherent characters (textual hallucinations), and the savings count does not appear to strictly adhere to the top 10. Although the composition is aesthetic and the flags are present, the failure in textual accuracy and fidelity to numerical data heavily penalizes the evaluation.
segmind ideogram-3
6.5/10 11.9 s
segmind ideogram-3
Cost 0.04 $
Resolution 1344 x 768
Time 11.9 s
Matania Judgment
Quality
8
Composition
9
Creativity
7
Text accuracy
4
Fidelity
6
Overall
6.5
Review
The visual aesthetics and composition are excellent, featuring a professional and clean rendering. However, fidelity is compromised as the model failed to list the 10 requested savings (only 5 are visible) and exhibits text and numerical data errors typical of image generation models.
segmind seedream-4.5
4.3/10 34.3 s
segmind seedream-4.5
Cost 0.04 $
Resolution 2560 x 1472
Time 34.3 s
Matania Judgment
Quality
6
Composition
5
Creativity
5
Text accuracy
2
Fidelity
4
Overall
4.25
Review
The image fails on the most crucial point: textual accuracy and data fidelity. While the overall aesthetics are correct, the text is illegible or incoherent (typical textual hallucinations of image models), and the number of countries displayed does not strictly follow the "top 10" instruction. The infographic structure is present, but the informative utility is zero due to the inaccuracy of the text.
segmind seedream-v5-lite
3.5/10 52.0 s
segmind seedream-v5-lite
Cost 0.04 $
Resolution 2848 x 1600
Time 52.0 s
Matania Judgment
Quality
6
Composition
5
Creativity
4
Text accuracy
1
Fidelity
3
Overall
3.5
Review
The image fails almost completely on textual and data constraints: the text is illegible, consisting of incoherent characters (gibberish), and does not represent a structured list of the top 10 global economies. Although the infographic's aesthetics are tempting, fidelity is very low because the model is unable to generate accurate textual data and correct flags for an economic comparison.
xai grok-imagine-image
4.9/10 7.7 s
xai grok-imagine-image
Cost 0.02 $
Resolution 2752 x 1504
Time 7.7 s
Matania Judgment
Quality
7
Composition
8
Creativity
6
Text accuracy
2
Fidelity
4
Overall
4.88
Review
The image is aesthetically pleasing and follows the structure of an infographic, but it fails significantly in terms of textual accuracy, displaying incoherent gibberish. Furthermore, the model fails to precisely list the 10 requested global economies, providing instead a generic visual representation that does not fulfill the informative purpose of the prompt.
xai grok-imagine-image-pro
4.5/10 19.9 s
xai grok-imagine-image-pro
Cost 0.07 $
Resolution 2816 x 1536
Time 19.9 s
Matania Judgment
Quality
7
Composition
6
Creativity
5
Text accuracy
2
Fidelity
4
Overall
4.5
Review
The image fails significantly on fidelity and textual accuracy: it does not list the 10 requested economies, and the text consists of incoherent characters (gibberish). Although the visual aesthetics are correct, the inability to provide legible and accurate textual data renders the infographic unusable for its intended purpose.
Code