Decision support

ERNIE-Image vs Cosmos3-Super-Text2Image

Compare canonical objects directly. The useful dimensions change with the object type, so model and hardware comparisons stay separate.

Benchmark results

  • Arena Text to Image

    Arena rating · Higher is better

    • ERNIE-Image
      Not reported
    • Cosmos3-Super-Text2Image
      1150
      Arena #36CI 1144 to 1156
    Runs and sources
    ERNIE-Image

    Not reported

    Cosmos3-Super-Text2Image
    • default115095% CI 1144 to 1156 · 17,450 votes

Each model's best published result is shown; "Not reported" means no matched evaluation, not a score of zero. Arena and DeepSWE ranks are the leaderboards' own; other ranks are among catalogue models with a score. Results from different harnesses or settings are not directly comparable.

Arena ratings: Arena (lmarena-ai/leaderboard-dataset), licensed CC BY 4.0. Ratings come from pairwise human votes and are only comparable within one leaderboard; the interval is Arena's 95% confidence interval. Model names are matched to the Vertical Tabs catalog.

Model specifications

Release date
April 15, 2026
May 31, 2026
Context window
—
—
Native context
—
—
Max output tokens
—
—
Knowledge cutoff
—
—
Open weights
Open weights
Open weights
Parameter count
8B
64.6B

API pricing · USD per 1M tokens

Input
—
—
Output
—
—
Cached input
—
—
Cache write
—
—

Capabilities and modalities

Input modalities
text
text
Output modalities
image
image
Tool calling
—
—
Reasoning option
—
—
Supported options
—
—
Capabilities
—
—

Architecture and availability

Architecture
—
—
Model families
—
—
Tokenizer
—
—
Instruction format
—
—
License
Apache 2.0
OpenMDW-1.1
Providers
0
0
Provider endpoints
0
0
Ollama variants
0
0
Metadata source
curated
ai-research

A dash means the field is not reported. Provider-specific performance and pricing may differ.

To give you the best experience, we use cookies for personalization, insights, and performance. Learn more.