Responses and Chat Completions are supported; the Decisions API was added in beta on October 6, 2026. Evaluate that endpoint separately and recheck prices and token tiers.
Choose labeled inputs and hold back a test set. Haiku 5.5 launched October 7, 2026; GPT-6 Luna launched September 22. Both are candidates for a routine-work evaluation, with different native reasoning and endpoint choices.
Do not silently compare different endpoints
GPT-6 Luna gained a Decisions API beta on October 6, while its Responses and Chat Completions endpoints remain separate choices. Record the endpoint explicitly. A Decisions experiment should be evaluated independently from a general generation request.
Count valid-but-wrong output
A JSON validator only catches format errors. Use expected values to score classifications and extraction fields, then include repair and retries in the accepted-result cost. Keep Haiku's effort setting in the recorded configuration.
Three criteria for this comparison
Correct values as well as valid schemas
Tail latency under production-like concurrency
Retries and total billed output per accepted decision
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.
Latest recorded measurements aligned by exact artifact, benchmark version, source and methodology. These are source results, not tests of Flonno's deployment.
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.
Claude Haiku 5.5
Enter all four values. Attempted tasks must be at least one; accepted tasks cannot exceed attempted tasks.
GPT-6 Luna
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.
