SShogo Bench

Grok 4.7 vs Muse Spark 1.3

Grok 4.7 leads Muse Spark 1.3 by 0.1 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Grok 4.7 wins 5 and Muse Spark 1.3 wins 10 of 16 shared benchmarks. Muse Spark 1.3 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGrok 4.7Muse Spark 1.3
Agentic coding5860
Long-horizon autonomy6964
Knowledge-work agents4745
Computer use3943
Security & context learning5053

Shared benchmarks

BenchmarkGrok 4.7Muse Spark 1.3
APEX-Agentsindex70.0%58.6%
FrontierSWEindex29.5%25.8%
CursorBenchindex46.3%41.6%
Chess Puzzles41.0%37.0%
CritPt18.0%26.0%
DTBench96.0%96.5%
FrontierMath Tier 417.1%46.3%
FrontierMath Tiers 1-353.0%74.4%
GeoBench61.0%86.0%
LMCA49.4%53.9%
MirrorCode54.4%54.4%
OTIS Mock AIME98.1%99.2%
ProofBench26.0%58.0%
SciCode57.8%59.7%
WebDev Arena16381652
WeirdML v38.5%6.7%

Specs and price

Grok 4.7Muse Spark 1.3
Agent Index54.8 (#27)54.7 (#28)
Agent $/M$0.98$0.030
Input / output $/M$2.00 / $6.00$0.10 / $0.20
Context500K1M
ReleasedSep 21, 2026Sep 2, 2026
WeightsClosedClosed
API hosts52

Don’t pick one. Route.

Shogo can run Grok 4.7 and Muse Spark 1.3 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo