BenchLeader

Muse Spark 1.1 vs Step 5 Preview

Verdict
  • Muse Spark 1.1 and Step 5 Preview are level on quality (65.2 vs 65.0).
  • Muse Spark 1.1 is stronger in agents & tools, coding, human preference, instruction following, maths, multimodal.
  • Step 5 Preview is stronger in knowledge, reasoning, composite, long context.
  • Step 5 Preview is 1.4× cheaper ($1.43 vs $2.00 per 1M blended).
MetricMuse Spark 1.1Step 5 Preview
BenchLeader Index65.265.0
Agents & tools score62.6
Coding score68.0
Human preference score66.2
Instruction following score77.8
Knowledge score70.572.0
Maths score62.7
Multimodal score64.860.8
Reasoning score69.282.1
Composite score84.4
Long context score70.8
Blended price $/M$2.00$1.43
Output speed210 tok/s
Time to first answer2.9 s
Context window1.0M1M
SimpleQA Verified57.8%
SciCode58.2%
APEX-Agents41.9%
ProofBench39.0%
Epoch Capabilities Index154.6
LMArena Text1493
LMArena Hard Prompts1513
LMArena Coding1531
LMArena WebDev1542
LMArena Vision1294
LMArena Agent-3
AA Intelligence Index43.6
AA-LCR88.3%
MMMU-Pro76.4%
AA-Omniscience16.4
Humanity's Last Exam (AA)46.5%
SciCode (AA)58.9%
SWE-Bench Pro61.5%
MCP Atlas88.1%
MultiChallenge75.3%
PRBench Finance55.0%
PRBench Legal57.0%
MultiNRC65.6%
EQ-Bench 41260
CritPt20.9%
GDPval (AA)53.6%
FORTRESS12.4%
SWE-Bench Pro (private)51.5%
VTB44.8%
LMArena Maths1486
LMArena Creative Writing1451
LMArena Instruction Following1471
LMArena Multi-turn1497
LMArena Longer Queries1481
LMArena Document1480
DeepSWE53.3%
GBAEval7.9%
Vending-Bench 26520.5
GDP.pdf15.0%

Data as of 2026-09-19. Best configuration of each model; every score links to its source on the model pages.

Muse Spark 1.1 vs Step 5 Preview: questions

Is Muse Spark 1.1 better than Step 5 Preview?
Muse Spark 1.1 and Step 5 Preview are level on quality (65.2 vs 65.0). The BenchLeader Index combines every independent quality benchmark; Muse Spark 1.1 is ahead overall as of 2026-09-19, but check the category scores for your use.
Which is cheaper, Muse Spark 1.1 or Step 5 Preview?
Step 5 Preview is cheaper: $1.43 against $2.00 per million tokens, blended at three input tokens per output token.
Which has the larger context window?
Muse Spark 1.1 accepts more context: 1.0M against 1M tokens.