Model Release Radar
Price/capability frontier position, benchmark scores, and community signal
Model Release Radar
Muse Spark 1.2
meta·closed weights·Proprietary·released Wednesday, Aug 5, 2026
Frontier position
- Behind frontier DeepSWE pass@1 (agentic coding) - GPT-5.6 Sol, Grok 4.6, Claude Opus 5, Gemini 3.7 Flash, GPT-5.6 Terra are priced the same or lower and at least as capable.
Cost vs. capability
Loading chart…
Benchmark scores
Measured cost per task (DeepSWE)
| Benchmark | Pass@1 | Measured cost / task | Frontier |
|---|---|---|---|
| DeepSWE (agentic coding) (xhigh effort, 95% CI 52.7%-57.0%, 4 runs) | 54.9% | $3.70 (median $2.68) | behind |
Artificial Analysis scores (no matched cost)
Artificial Analysis scores below have no measured per-task cost, so no frontier claim is made for them here.
| Benchmark | Score |
|---|---|
| AA intelligence index | 56.8 |
| AA coding index | 72.2 |
| GPQA Diamond (science) | 90.4% |
| Humanity's Last Exam | 45.5% |
| LCR | 83.3% |
| SciCode (coding) | 56.4% |
| Tau2 (banking) | 34.8% |
| Terminal-Bench 2.1 (agentic) | 80.1% |
Community signal
| Variant | Coding Elo | Overall Elo | Votes |
|---|---|---|---|
| Rating | 1,496 | 1,488 | 3,247 |