Meta's Muse Spark 1.3 passes DeepSeek V4 Flash on opencode with 23T tokens used
jack_w_rae · x · 2026-09-09
According to user @noctus91, Meta's Muse Spark 1.3 has overtaken DeepSeek V4 Flash in token usage on opencode, racking up 23T tokens. That is an exceptional volume for a model that launched relatively recently, suggesting substantial real-world coding adoption.
Related event: Meta's Muse Spark 1.3 hits 23T tokens on opencode(2 posts)→
More from coding & agent
- Kolab Benchmark Uses Pro Screen Recordings to Show AI Agents Overestimate Collaboration Quality — minnesotanlp · 2026-10-27
- Dev argues Claude burns far more tokens than GPT models for the same coding work — haider1 · 2026-10-27
- Stop building agents that can't change models: stable contracts, external state, real evals — rseroter · 2026-10-27
- Cheap models can cost more in agent harnesses than frontier ones, researcher warns — vasuman · 2026-10-27
- Kanzo: A 5k-Line Rust Kanban Binary With MCP for Claude Code and Codex — allmudi · 2026-10-27
- 'A human approves everything' is a trap: approval fatigue and how to actually design safe agents — Efistoffeles · 2026-10-27