Use image-specific quality criteria. The announcement supports wide and panoramic aspect ratios at 1K, 2K and 4K; output quality and billing still need checks on the real endpoint.
The provider positioning is a hypothesis to test. Compare preservation of unchanged image regions and instruction compliance at the same output size and quality setting.
Build cases with one intended change and explicitly protected regions. Nano Banana 2.1 reached general availability October 6, 2026; Sunburst launched September 8. Provider positioning does not replace a controlled editing test.
Separate appearance from edit correctness
Judge whether the requested modification happened and whether the original identity, background and layout remain correct. Score those requirements independently from general visual quality.
Keep the edit sequence reproducible
Save each original image, instruction and result. Keep resolution and aspect ratio fixed where supported. Count every retry, upload and generation through the final accepted edit.
Three criteria for this comparison
Preservation of regions that should not change
Compliance with the requested edit and rendered text
Accepted edits across a multi-turn sequence
Run a fair comparison
Use the same representative inputs and a written answer rubric. Pin the model version and record the endpoint, thinking configuration, quantization when known, context length, output allowance and concurrency. Preserve native request differences in an adapter rather than silently dropping fields.
Measure full request time, error rate and reported usage. For tools, validate arguments and score the result after execution. For images, preserve resolution and preprocessing. A valid response format alone does not establish a correct answer.
Compare cost per accepted result
Calculate input cost plus all billed output, including reasoning where the provider counts it. Add retries and discarded answers. Divide the total by the number of results that pass your quality criteria. Keep API usage cost separate from deployment and engineering cost.
Artificial Analysis observations are refreshed by the integrated Radar. Differences in artifact, benchmark version or method prevent a score comparison. Read the evidence methodology →
YOUR WORKLOAD
Compare cost per accepted task.
Enter results from your own evaluation. A task should count once it meets your written quality criteria. Include failed attempts and retries in total spend. These inputs stay in this browser and are not a Flonno benchmark.
Nano Banana 2.1
Enter all four values. Attempted tasks must be at least one; accepted tasks cannot exceed attempted tasks.
GPT Image 2.5 Sunburst
Enter all four values. Attempted tasks must be at least one; accepted tasks cannot exceed attempted tasks.
Turn evidence into a deployment decision
A source benchmark can inform your shortlist, while your evaluation shows whether a model finishes the work at an acceptable cost. Keep the chosen endpoint, processing terms and output limits in the decision record. Inclusion in the Radar does not mean the model is served by Flonno.
