Back

Meta

Muse Spark

ReasoningClosed weights
Intelligence
31.3
Rank 118 of 744 measured models
Coding
58.6
Rank 93 of 298 measured models
Context window
262K
Rank 458 of 1199 measured models

Muse Spark scores 31.3 on the Artificial Analysis Intelligence Index, ranking 118th of 744 measured models. The closest models on this index are Claude Opus 4.6 (batch) (31.9), K2 Horizon 375B A23B (30.5), and DeepSeek V4 Pro 0424 (30.4).

Artificial Analysis Indices
Intelligence31.3
Rank 118 of 744 measured models
Coding58.6
Rank 93 of 298 measured models
Capability indexes
Performance in specific industries, measured by Artificial Analysis
Economics39.0
Rank 112 of 225 measured models
Standard Benchmarks
GPQA Diamond88.4%
Rank 94 of 619 measured models
HLE40.7%
Rank 80 of 664 measured models
IFBench75.9%
Rank 25 of 450 measured models
AA-LCR78.0%
Rank 120 of 575 measured models
TerminalBench Hard45.5%
Rank 34 of 432 measured models
Terminal-Bench 2.162.2%
Rank 95 of 244 measured models
τ²-Bench91.5%
Rank 60 of 440 measured models
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy