LLMs TigerLive LLM benchmarks

Muse Spark 1.3 (max): benchmark scores, price and ranking

Muse Spark 1.3 (max) from Meta AI ranks #20 of 741 LLMs on the LLMs Tiger aggregate benchmark score (55.0), based on 12 benchmark results captured up to 2026-10-05.

Organisation
Meta AI
Type
Frontier model
Open weights
No
Released
2026-09-02 (source: epoch)
Cheapest API price
$1.25 in / $4.25 out per million tokens (via meta, observed 2026-10-05T21:47Z)
Aggregate rank
#20 of 741 (score 55.0)

Relative to other models, Muse Spark 1.3 (max) is strongest on SciCode (#7 of 100) and weakest on CursorBench (#7 of 13).

Muse Spark 1.3 (max) benchmark results

Muse Spark 1.3 (max) benchmark scores, ranked against all models measured on each benchmark
BenchmarkScoreRankSourceCaptured
SciCode58.8%#7 of 100Epoch AI Benchmarking Hub2026-10-05
LMArena Document Elo1,471#2 of 18LMArena2026-10-05
WebDev Arena1,652#8 of 63Epoch AI Benchmarking Hub2026-10-05
CritPt24.9%#15 of 111Epoch AI Benchmarking Hub2026-10-05
Chess Puzzles38.0%#19 of 124Epoch AI Benchmarking Hub2026-10-05
LMArena Text Elo1,494#5 of 28LMArena2026-10-05
FrontierMath T1-374.0%#18 of 69Epoch AI Benchmarking Hub2026-10-05
LMArena Vision Elo1,290#6 of 22LMArena2026-10-05
LMArena Code Elo1,657#9 of 29LMArena2026-10-05
FrontierMath T446.3%#19 of 52Epoch AI Benchmarking Hub2026-10-05
Mystery Games25.0%#27 of 57Epoch AI Benchmarking Hub2026-10-05
CursorBench41.6%#7 of 13Epoch AI Benchmarking Hub2026-10-05

Muse Spark 1.3 (max) is also listed at 7 other reasoning-effort settings; this page shows the highest-effort row, which is the one the leaderboard keeps by default.

Models ranked nearby

Compare it on the live leaderboard → · How the aggregate score works