BenchLeader

Gemini 3.7 Flash vs Muse Spark 1.1

Verdict
  • Gemini 3.7 Flash (medium) and Muse Spark 1.1 are level on quality (64.4 vs 64.9).
  • Gemini 3.7 Flash (medium) is stronger in coding, composite, knowledge, long context, multimodal.
  • Muse Spark 1.1 is stronger in reasoning, agents & tools, human preference, instruction following, maths.
  • Gemini 3.7 Flash (medium) is 1.3× cheaper ($1.50 vs $2.00 per 1M blended).
  • Gemini 3.7 Flash (medium) streams 1.5× faster (282 vs 194 tokens per second).
MetricGemini 3.7 Flash (medium)Muse Spark 1.1
BenchLeader Index64.464.9
Coding score68.368.2
Composite score78.972.2
Knowledge score75.273.1
Long context score68.165.3
Multimodal score69.464.9
Reasoning score63.568.8
Agents & tools score62.7
Human preference score66.0
Instruction following score77.8
Maths score52.2
Blended price $/M$1.50$2.00
Output speed282 tok/s194 tok/s
Time to first answer5.3 s2.0 s
Context window1M1.0M
SimpleQA Verified57.8%
SciCode57.9%58.2%
APEX-Agents41.9%
ProofBench39.0%
Epoch Capabilities Index154.6
LMArena Text1492
LMArena Hard Prompts1511
LMArena Coding1531
LMArena WebDev1541
LMArena Vision1293
LMArena Agent-2.6
AA Intelligence Index39.634.3
AA-LCR83.0%77.7%
MMMU-Pro84.7%
AA-Omniscience23.728.1
GPQA Diamond (AA)92.1%89.8%
Humanity's Last Exam (AA)39.0%46.2%
SciCode (AA)59.8%58.8%
SWE-Bench Pro61.5%
MCP Atlas88.1%
MultiChallenge75.3%
PRBench Finance55.0%
PRBench Legal57.0%
MultiNRC65.6%
EQ-Bench 41260
ARC-AGI-191.2%
ARC-AGI-263.8%

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