specs at a glance
| Leaderboard rank | #9 of 24 |
|---|---|
| SWE-bench Verified | 86.6% |
| SWE-bench Pro | — |
| Terminal-Bench | 82.9% (TB2.1) |
| Input price / 1M | $1.25 |
| Output price / 1M | $4.25 |
| Context window | 1M |
| Open weights | No |
| Access | Muse Code CLI (beta, macOS/Linux) · Meta Model API |
| Maker | Meta |
how good is Muse Spark 1.2 at coding?
Muse Spark 1.2 sits at #9 of 24 ranked models, posting 86.6% on SWE-bench Verified — 10.4 points behind #1 Claude Opus 5. Terminal-Bench (agentic terminal work): 82.9% (TB2.1).
Score provenance: Independent (vals.ai, Aug 6 2026, mini-swe-agent bash-only harness): SWE-bench Verified 86.6%. Added Aug 7, 2026, the day after Meta launched it alongside the Muse Code terminal agent. This is an exact tie with Grok 4.5 at 86.6%, not a win over it; Grok 4.5 takes the higher rank only on the SWE-bench Pro tiebreak, since Meta has published no Pro figure. Meta published no SWE-bench Verified number of its own, so the independent score is the ranked one. A 4.6-point gain over Muse Spark 1.1 (82.0%) in four weeks. The weakness is long work: 64% on vals.ai's 1-to-4-hour task tier against 90% for Claude Opus 5 and 74% for Claude Opus 4.8, while short tasks reach 92%. Terminal-Bench 2.1 82.9% and DeepSWE 1.1 59.3% are Meta-reported, and Meta published them alongside Claude Opus 5's higher 86.7% and 65.0%. Standard pricing $1.25/$4.25 per 1M matches Muse Spark 1.1; a contributor tier cuts that to $0.10/$0.20 in exchange for permission to train on your prompts and completions. See /p/meta-muse-code-contributor-tier-data-pricing/.
what does Muse Spark 1.2 cost?
$1.25 per 1M input tokens and $4.25 per 1M output — #8 cheapest of the 24 models we track. Coding workloads are output-heavy, so weight the output rate when budgeting. Run your own volume through the AI API cost calculator for a monthly estimate.
where can you use it?
Available via Muse Code CLI (beta, macOS/Linux) · Meta Model API. As a proprietary model, you're on the maker's infrastructure and release schedule.
More coverageAI coding models on GENZ TECH
Ranked on our AI Coding Leaderboard — scores confirmed against primary sources only, updated 2026-08-10.