BenchLeader

Gemini 4 Argon vs Muse Spark 1.2

Full profiles: Gemini 4 Argon (Google) and Muse Spark 1.2 (Meta): every benchmark, price and rank.

Updated · Data from 11 sources

As of 10 Nov 2026, Gemini 4 Argon is ahead of Muse Spark 1.2 on quality (65.6 vs 61.7 on the BenchLeader Index), but Muse Spark 1.2 is 2.0× cheaper at $2.00 vs $4.00 per 1M tokens blended. Gemini 4 Argon leads in every category we measure both in. Gemini 4 Argon's current price runs until 30 Nov 2026, then $8.00.

Key facts (as of 10 Nov 2026)

  • Gemini 4 Argon scores 65.6 on the BenchLeader Index and Muse Spark 1.2 scores 61.7 (BenchLeader, 10 Nov 2026).
  • Gemini 4 Argon costs $4.00 per 1M tokens blended until 30 Nov 2026, then $8.00 (https://ai.google.dev/gemini-api/docs/pricing, checked 20 Oct 2026).
  • Muse Spark 1.2 costs $2.00 per 1M tokens blended (list price, 10 Nov 2026).
  • Muse Spark 1.2 streams 3×+ faster than Gemini 4 Argon (Artificial Analysis, 7-day median, 10 Nov 2026).
  • Of the 44 benchmarks both models have, Gemini 4 Argon leads 41 (BenchLeader, 10 Nov 2026).
  • On Arena WebDev, Gemini 4 Argon is rated 1683 and Muse Spark 1.2 1534 (LMArena, as published by 10 Nov 2026).

Which to pick for…

The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.

Use casePickWhyConfidence
CodingGemini 4 Argon67 vs 55 category score; Arena WebDev 1683 vs 1534High
Agents & tool useGemini 4 Argon58 vs 56 category score; Arena Agent 10.8 vs -8Medium
MathsGemini 4 Argon70 vs 67 category score; Arena Maths 1531 vs 1490Medium
ReasoningGemini 4 Argon70 vs 68 category score; Arena Hard Prompts 1546 vs 1515Medium
KnowledgeGemini 4 Argon72 vs 65 category score; SimpleQA Verified 76.0% vs 60.3%High
Long documentsEither65 vs 64 category score; AA-LCR v1.1 79.7% vs 79.0%Either
Chat quality (human preference)Gemini 4 Argon72 vs 69 on Arena votesMedium
Lowest costMuse Spark 1.2$2.00 vs $4.00 per 1M blended; agentic coding session $0.092 vs $0.160; from 1 Dec 2026: $2.00 vs $8.00–
Fastest first answerMuse Spark 1.27.9 s (Muse Spark 1.2 (xhigh)) vs 37.6 s (Gemini 4 Argon (high)) to the first answer token–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • Gemini 4 Argon (high) leads on quality: 65.6 vs 61.7.
  • Gemini 4 Argon (high) is stronger in agents & tools, coding, human preference, knowledge, long context, maths, reasoning.
  • Muse Spark 1.2 (xhigh) is stronger in multimodal.
  • Muse Spark 1.2 (xhigh) is 2.0× cheaper ($2.00 vs $4.00 per 1M blended) until 30 Nov 2026, then $2.00 vs $8.00 from 1 Dec 2026.
  • Muse Spark 1.2 (xhigh) streams 2.8× faster (192 vs 68 tokens per second).

At a glance

SpecGemini 4 ArgonMuse Spark 1.2
DeveloperGoogleMeta
Released30 Sep 20265 Aug 2026
Generally available13 Oct 20265 Aug 2026
Context window (tokens)1,048,5761,048,576
Max output (tokens)65,536 (up to 1,048,576 with long decode)–
Input typestext, image, video, audio, PDF–
Reasoning effort settingslow, medium, high–
Compared atGemini 4 Argon (high)Muse Spark 1.2 (xhigh)
Open weightsNoNo
Price in / out / cached input per 1M$2.00 / $10.00 / $0.100$1.25 / $4.25 / $0.150
Announced price change$4.00 / $20.00 / $0.200 from 1 Dec 2026None announced
API model IDgemini-4-argon–
Where to use itGemini API (AI Studio), Gemini Enterprise Agent Platform, Gemini app–

Limits, availability and announced prices from the vendors' own pages: ai.google.dev, ai.google.dev pricing (checked 20 Oct 2026). Everything else is from the day's data.

Category by category

Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.

CategoryGemini 4 Argon (high)Muse Spark 1.2 (xhigh)Leader
Reasoning69.968.3Gemini 4 Argon
Coding67.155.0Gemini 4 Argon
Agents & tools57.555.5Gemini 4 Argon
Maths69.967.2Gemini 4 Argon
Knowledge72.364.7Gemini 4 Argon
Human preference72.268.7Gemini 4 Argon
Multimodal–65.3not comparable
Long context64.564.2level

On one chart

Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.

2550 avg75ReasoningCodingAgents & toolsMathsKnowledgeLong contextHumanpreferenceGemini 4 Argon, Reasoning: 69.9Gemini 4 Argon, Coding: 67.1Gemini 4 Argon, Agents & tools: 57.5Gemini 4 Argon, Maths: 69.9Gemini 4 Argon, Knowledge: 72.3Gemini 4 Argon, Long context: 64.5Gemini 4 Argon, Human preference: 72.2Muse Spark 1.2, Reasoning: 68.3Muse Spark 1.2, Coding: 55.0Muse Spark 1.2, Agents & tools: 55.5Muse Spark 1.2, Maths: 67.2Muse Spark 1.2, Knowledge: 64.7Muse Spark 1.2, Long context: 64.2Muse Spark 1.2, Human preference: 68.7

Not drawn, measured for fewer than two of these models: Instruction following, Multimodal.

ModelIndex

Where sources disagree

Across the 44 benchmarks both have, Gemini 4 Argon leads 41, Muse Spark 1.2 leads 3. Every overall index that rates both puts Gemini 4 Argon ahead.

Overall indexGemini 4 Argon (high)Muse Spark 1.2 (xhigh)Leader
BenchLeader Index65.661.7Gemini 4 Argon
Arena Text15221494Gemini 4 Argon

Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).

Price, speed and latency

List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.

MeasureGemini 4 Argon (high)Muse Spark 1.2 (xhigh)
Blended price per 1M tokens, until 30 Nov 2026$4.00$2.00
Input / output per 1M$2.00 / $10.00$1.25 / $4.25
Blended price per 1M from 1 Dec 2026$8.00$2.00
Input / output per 1M from 1 Dec 2026$4.00 / $20.00$1.25 / $4.25
Cached input per 1M$0.100$0.150
Price per task: chat reply$0.0038$0.0018
Price per task: summarize a 30-page report$0.030$0.018
Price per task: code edit$0.027$0.014
Price per task: agentic coding session$0.160$0.092
Price per task: structured extraction$0.0060$0.0034
Agentic coding session, input mostly cached$0.074$0.043
Cost per benchmark task (AA Index)$9.95–
Output tokens per task (AA Index)116k–
Of which reasoning68k–
Time per task (AA Index)29 min–
Output speed68 tok/s192 tok/s
Time to first answer37.6 s7.9 s
Time to a complete answer108.0 s26.6 s

Each model is compared at its best-ranked reasoning-effort setting. Gemini 4 Argon (high) scores 65.6 and takes 38 s to its first answer token; Gemini 4 Argon scores 63.2 in 5 s. Muse Spark 1.2 (xhigh) scores 61.7 and takes 8 s to its first answer token. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.

Every benchmark

145 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.

MetricPublisherGemini 4 Argon (high)Muse Spark 1.2 (xhigh)
BenchLeader IndexBenchLeader65.661.7
Agents & tools scoreBenchLeader57.555.5
Coding scoreBenchLeader67.155.0
Human preference scoreBenchLeader72.268.7
Knowledge scoreBenchLeader72.364.7
Long context scoreBenchLeader64.564.2
Maths scoreBenchLeader69.967.2
Reasoning scoreBenchLeader69.968.3
Multimodal scoreBenchLeader–65.3
Blended price $/MBenchLeader$4.00$2.00
Output speedBenchLeader68 tok/s192 tok/s
Time to first answerBenchLeader37.6 s7.9 s
Context windowBenchLeader1,048,576 tokens1,048,576 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub96.4%–
SimpleBenchSimpleBench–74.5%†
Arena Hard PromptsArena (LMArena)15461515
LiveBench 2.0 ReasoningLiveBench95.1%†–
LiveBench 1.0 ReasoningLiveBench–90.0%
GPQA Diamond (AA)Artificial Analysis–90.4%
Humanity's Last Exam (AA)Artificial Analysis57.1%45.5%
HLE-Diamond (AA)Artificial Analysis56.7%–
ARC-AGI-1ARC Prize98.5%–
ARC-AGI-2ARC Prize91.3%–
ARC-AGI-3ARC Prize97.3%–
CritPtArtificial Analysis27.1%17.7%
CritPt v2 hard subset (AA)Artificial Analysis52.5%–
MysteryMechanismVals AI45.5%–
Chess PuzzlesEpoch AI Benchmarking Hub59.0%27.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub64.0%–
LMCAEpoch AI Benchmarking Hub63.7%48.4%
DTBenchEpoch AI Benchmarking Hub97.3%94.7%
Coding
SciCodeSciCode61.8%57.4%
WeirdMLWeirdML–60.3%
FrontierCodeCognition47.5%†–
Arena CodingArena (LMArena)15531543
Arena WebDevArena (LMArena)16831534
LiveBench 2.0 CodingLiveBench85.7%†–
LiveBench 1.0 CodingLiveBench–77.5%
Show all 145 benchmarks
MetricPublisherGemini 4 Argon (high)Muse Spark 1.2 (xhigh)
Coding
IOIVals AI100.0%21.8%
SWE-bench (Vals)Vals AI–86.6%
Code MigrationVals AI68.2%29.9%
Code Migration v1.1Vals AI70.8%–
ProgramBenchVals AI2.5%0.5%
SWE-bench MultimodalVals AI56.0%–
Vibe Code Bench 1-100Vals AI21.2%–
Vibe Code Bench v1.1Vals AI91.9%79.1%
MirrorCodeEpoch AI Benchmarking Hub58.9%–
DeepSWE v1.1Epoch AI Benchmarking Hub–54.9%
CursorBenchCursor52.9%–
ALE-BenchEpoch AI Benchmarking Hub2100.1–
FrontierSWEEpoch AI Benchmarking Hub55.0%12.0%
Terminal-Bench 4.0 (AA)Artificial Analysis57.1%7.1%
Terminal-Bench 2.1 (AA)Artificial Analysis–80.2%
Startrise FrontendStartrise71.0%†70.3%†
GameBench 2 OverallDuelLab GameBench 281.7†51.7†
GameBench 2 by reasoning settingDuelLab GameBench 289.057.4
Design Arena WebsiteDesign Arena1314†1310†
FrontierCode 1.1 (AA)Artificial Analysis43.5%–
FrontierCode 2.0 (AA)Artificial Analysis25.7%–
Agents & tools
Remote Labor IndexScale AI / CAIS17.1%†–
APEX-AgentsMercor82.4%†45.4%†
Arena AgentArena (LMArena)10.8-8
LiveBench Long AgenticLiveBench58.5%†–
LiveBench BrowserLiveBench82.8%†–
LiveBench Agentic CodingLiveBench–57.6%
Terminal-Bench 2.1 (Vals)Vals AI57.7%69.7%
MCP AtlasScale AI SEAL90.7%†–
HiL-BenchScale AI SEAL62.0%†–
GDPval-AA v2.1, normalised scoreArtificial Analysis56.2%–
GDPval-AA v2.1Artificial Analysis1633–
τ³-Banking (AA)Artificial Analysis–34.9%
Analyst Agent (AA)Artificial Analysis48.8%–
CUA-benchVals AI4.8%–
CyberBenchVals AI77.9%69.5%
Finance Agent v2Vals AI65.4%60.6%
Finance Agent v2.1Vals AI67.7%–
Harvey's Legal Agent Benchmark v1.1Vals AI27.1%–
Harvey's Legal Agent Benchmark v1Vals AI19.6%25.4%
Legal Research BenchVals AI54.8%43.8%
Robo-benchVals AI0.8%–
SkillsBenchVals AI–53.0%
SREBenchVals AI44.3%0.0%
Tax Agent BenchVals AI49.2%32.8%
Terminal-Bench 4.0 (Vals)Vals AI57.6%6.1%
Terminal-Bench ScienceVals AI44.3%–
Time Horizon Index: KSPVals AI52.5%–
Vending-Bench 2Andon Labs13718.2†–
AutomationBenchArtificial Analysis77.5%40.6%
GDP.pdf (AA)Artificial Analysis21.8%17.4%
Harvey LAB-AA v1.1Harvey3.9%–
EnterpriseOps-GymArtificial Analysis–47.3%
AA-Briefcase v1.1Artificial Analysis14841324
GDPxGDPx by SemiAnalysis7.3%–
Design Arena AgenticDesign Arena1277†1178†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis52.9%–
FACTS SearchGoogle89.9%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub86.0%–
FrontierMath Tier 4Epoch AI Benchmarking Hub78.0%–
OTIS Mock AIMEEpoch AI Benchmarking Hub100.0%–
ProofBenchVals AI99.0%†43.0%†
LiveBench MathematicsLiveBench–91.2%
Arena MathsArena (LMArena)15311490
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub76.0%60.3%
LiveBench 2.0 Data AnalysisLiveBench85.2%†–
LiveBench ResearchLiveBench86.8%†–
LiveBench 1.0 Data AnalysisLiveBench–76.5%
AA-Omniscience v1.1Artificial Analysis46.1–
MMLU-ProVals AI–88.3%
LegalBenchVals AI88.3%85.3%
CorpFinVals AI–70.9%
TaxEvalVals AI–80.4%
PRBench FinanceScale AI SEAL49.9%†–
PRBench LegalScale AI SEAL49.4%†–
BioMysteryBenchVals AI76.3%64.8%
Excel Modeling BenchmarkVals AI75.2%57.0%
Excel Modeling Benchmark v1.1Vals AI74.8%–
MedCodeVals AI58.8%49.4%
MedScribeVals AI87.4%90.1%
Public Benefits Bench v1.1Vals AI69.8%68.5%
DrugDiscoveryBenchScale AI SEAL65.4%–
EBR-benchEpoch AI Benchmarking Hub64.8%–
GDP.pdfEpoch AI Benchmarking Hub28.4%16.0%
AA-Omniscience v1.1: accuracyArtificial Analysis48.3%–
AA-Omniscience v1.1: non-hallucinationArtificial Analysis95.7%–
HealthBench Professional (AA)OpenAI55.0%–
Instruction following
LiveBench LanguageLiveBench–78.6%
LiveBench Instruction FollowingLiveBench–74.3%
MultiChallengeScale AI SEAL78.7%†–
Arena Instruction FollowingArena (LMArena)15291479
Human preference
Arena TextArena (LMArena)15221494
EQ-Bench 4EQ-Bench1236†–
Arena Creative WritingArena (LMArena)15251443
Arena Multi-turnArena (LMArena)15461512
Arena Longer QueriesArena (LMArena)15441491
Multimodal
Arena VisionArena (LMArena)–1305
LiveBench DesignLiveBench69.2%†–
MMMU-Pro (Vals)Vals AI–86.1%
MortgageTaxVals AI–65.4%
SAGEVals AI89.5%–
AudioMCScale AI SEAL58.4%–
AudioMC (text output)Scale AI SEAL58.4%–
Blueprint-Bench 2Epoch AI Benchmarking Hub54.5%†–
Code2Video-AAArtificial Analysis1259–
AA-3DArtificial Analysis1147–
Long context
AA-LCR v1.1Artificial Analysis79.7%79.0%
MLCRArtificial Analysis13.9%7.2%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub166.5†155†
LiveBench 2.0LiveBench77.7%†–
LiveBench 1.0LiveBench–78.0%
AA Intelligence Index v5.0Artificial Analysis50.4–
AA Intelligence Index v4.3.2Artificial Analysis52.639.6
AA Progress Index v1Artificial Analysis341.8309.1
Vals IndexVals AI69.4–
Vals Finance IndexVals AI66.0%–
Vals RSI IndexVals AI30.6%–
Vals Science IndexVals AI55.4%–
Vals Multimodal IndexVals AI–69.8%†
Vals Router IndexVals AI69.2%†–

Data as of 2026-11-10. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261103-eaea31df94e6 (https://benchmarks.duellab.org/releases/gb2-20261103-eaea31df94e6/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • Gemini 4 Argon: list price moves to $4.00 / $20.00 per 1M input / output tokens (announced).
  • Gemini 4 Argon (high): 4 score revisions.
  • Gemini 4 Argon (high): 1 score revision.
  • Gemini 4 Argon (high): cost per task moved from $7.68/M to $9.95/M (29% up).
  • Gemini 4 Argon (high): 1 score revision.
  • Muse Spark 1.2 (xhigh): 1 score revision.
  • Gemini 4 Argon (high): 2 score revisions; input price moved from $2.00/M to $4.00/M (100% up); output price moved from $10.00/M to $20.00/M (100% up); cost per task moved from $3.84/M to $7.68/M (100% up).
  • Muse Spark 1.2 (xhigh): 1 score revision.
  • Gemini 4 Argon (high): BenchLeader Index 66.8 → 65.9.
  • Muse Spark 1.2 (xhigh): BenchLeader Index 62.2 → 61.6.

Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs

Gemini 4 Argon vs Muse Spark 1.2: questions

Is Gemini 4 Argon better than Muse Spark 1.2?
Gemini 4 Argon (high) leads on quality: 65.6 vs 61.7. The BenchLeader Index combines every independent quality benchmark; Gemini 4 Argon (high) is ahead overall as of 10 Nov 2026, but check the category scores for your use.
Gemini 4 Argon vs Muse Spark 1.2: which is cheaper, and will that change?
Muse Spark 1.2 is cheaper today: $2.00 against $4.00 per million tokens, blended at three input tokens per output token. Gemini 4 Argon's current price runs until 30 Nov 2026, then $8.00.
Is Gemini 4 Argon or Muse Spark 1.2 better for coding?
Gemini 4 Argon scores higher in coding (67 vs 55 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1683 for Gemini 4 Argon against 1534 for Muse Spark 1.2.
Which is faster, Gemini 4 Argon or Muse Spark 1.2?
Muse Spark 1.2 streams 3×+ faster (192 vs 68 output tokens per second, Artificial Analysis 7-day median).
Is Gemini 4 Argon or Muse Spark 1.2 better for agents and tool use?
Gemini 4 Argon scores higher in agentic tasks (58 vs 56 on the category index, where 50 is average). On Arena Agent, the top shared agents & tools benchmark, it is 10.8 for Gemini 4 Argon against -8 for Muse Spark 1.2.
More questions (4)
Which is better for long documents?
They are level on long-context benchmarks (65 vs 64). Both accept 1,048,576 tokens of context.
Which has lower latency?
Muse Spark 1.2 answers first: 7.9 s against 37.6 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
Do independent benchmarks agree on Gemini 4 Argon vs Muse Spark 1.2?
Across the 44 benchmarks both have, Gemini 4 Argon leads 41, Muse Spark 1.2 leads 3. Every overall index that rates both puts Gemini 4 Argon ahead.
When was Gemini 4 Argon released?
Gemini 4 Argon became generally available on 13 Oct 2026, after first appearing on 30 Sep 2026.