Muse Spark · Reference

Agentic coding models: index, speed and deployment control

Compare the documented effort configurations of coding-oriented models. The Intelligence Index is a broad composite, not a coding-only benchmark.

Research snapshot leaderboard

ConfigurationAA indexTokens/sWeights
Claude Fable 5.1 max with fallback6662Closed
Claude Fable 5.1 xhigh with fallback6560Closed
Claude Opus 5 max6356Closed
Claude Fable 5.1 high with fallback6255Closed
Muse Spark 1.3 max (gated)62Not reportedClosed
Claude Fable 5 with fallback6265Closed
Muse Spark 1.3 xhigh61186Closed
GPT-5.6 Sol max6169Closed
Grok 4.6 high6155Closed
Claude Opus 5 high6149Closed
Kimi K3 max6038Open
GLM-5.3 max6063Open

Rank on completed work

Select representative repository fixes, hold tests and permissions constant, and score accepted changes rather than lines of code. Record total time and token cost, including recovery attempts.

Ready to test the workflow?

Create account & add credits

Snapshot, not an independent retest

These configurations come from the supplied 3 September 2026 leaderboard. Multiple rows represent different efforts of the same model.

Frequently asked questions

How current is this information?

This page uses the supplied research snapshot dated 3 September 2026. Verify current access, pricing and provider terms before an evaluation.

Put Muse Spark 1.3 to work

Fund a controlled evaluation, send a reference frame or document, and measure quality and cost on your own workload.