BenchLeader

Gemma 4 31B vs Muse Ember

Full profiles: Gemma 4 31B (Google) and Muse Ember (Meta): every benchmark, price and rank.

Updated · Data from 9 sources

As of 16 Nov 2026, Gemma 4 31B and Muse Ember are neck and neck on quality (51.9 vs 52.1 on the BenchLeader Index, inside the ±8.7 margin), and Muse Ember is 1.3× cheaper at $0.200 vs $0.250 per 1M tokens blended. Choose Gemma 4 31B for reasoning (61 vs 51) and fast first answers (0.5 s vs 5.0 s); choose Muse Ember for knowledge (49 vs 24) and coding (60 vs 48), where it also streams 3×+ faster.

Key facts (as of 16 Nov 2026)

  • Gemma 4 31B scores 51.9 on the BenchLeader Index and Muse Ember scores 52.1 (BenchLeader, 16 Nov 2026).
  • Gemma 4 31B costs $0.250 per 1M tokens blended (list price, 16 Nov 2026).
  • Muse Ember costs $0.200 per 1M tokens blended (list price, 16 Nov 2026).
  • Muse Ember streams 3×+ faster than Gemma 4 31B (Artificial Analysis, 7-day median, 16 Nov 2026).
  • Of the 1 benchmarks both models have, Muse Ember leads 1 (BenchLeader, 16 Nov 2026).
  • On Arena WebDev, Gemma 4 31B is rated 1370 and Muse Ember 1609 (LMArena, as published by 16 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
CodingMuse Ember60 vs 48 category score; Arena WebDev 1609 vs 1370High
ReasoningGemma 4 31B61 vs 51 category scoreHigh
KnowledgeMuse Ember49 vs 24 category scoreHigh
Chat quality (human preference)–Only Gemma 4 31B has an Arena rating (54 category score)Not comparable
Lowest costMuse Ember$0.200 vs $0.250 per 1M blended; agentic coding session $0.008 vs $0.014–
Fastest first answerGemma 4 31B0.5 s (Gemma 4 31B) vs 5.0 s (Muse Ember (max)) 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

  • Gemma 4 31B and Muse Ember (max) are neck and neck on quality (51.9 vs 52.1, within the ±8.7 margin).
  • Gemma 4 31B is stronger in reasoning.
  • Muse Ember (max) is stronger in coding, knowledge.
  • Muse Ember (max) is 1.3× cheaper ($0.200 vs $0.250 per 1M blended).
  • Muse Ember (max) streams 6.8× faster (437 vs 64 tokens per second).

At a glance

SpecGemma 4 31BMuse Ember
DeveloperGoogleMeta
Released2 Apr 20269 Nov 2026
Context window (tokens)262,1441,048,576
Compared atGemma 4 31BMuse Ember (max)
Open weightsYesNo
Price in / out / cached input per 1M$0.200 / $0.400 / $0.250$0.100 / $0.500 / $0.0040

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.

CategoryGemma 4 31BMuse Ember (max)Leader
Reasoning61.051.1Gemma 4 31B
Coding48.260.0Muse Ember
Agents & tools–52.4not comparable
Maths64.7–not comparable
Knowledge24.448.8Muse Ember
Human preference54.3–not comparable
Multimodal62.0–not comparable

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 avg75ReasoningCodingKnowledgeGemma 4 31B, Reasoning: 61.0Gemma 4 31B, Coding: 48.2Gemma 4 31B, Knowledge: 24.4Muse Ember, Reasoning: 51.1Muse Ember, Coding: 60.0Muse Ember, Knowledge: 48.8

Not drawn, measured for fewer than two of these models: Agents & tools, Maths, Instruction following, Long context, Multimodal, Human preference.

Model, click to add or removeIndex

Where sources disagree

Across the 1 benchmarks both have, Gemma 4 31B leads 0, Muse Ember leads 1. Every overall index that rates both puts Muse Ember ahead.

Overall indexGemma 4 31BMuse Ember (max)Leader
BenchLeader Index51.952.1neck and neck
AA Intelligence Index v5.0.14.4†36.0Muse Ember

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.

MeasureGemma 4 31BMuse Ember (max)
Blended price per 1M tokens$0.250$0.200
Input / output per 1M$0.200 / $0.400$0.100 / $0.500
Cached input per 1M$0.250$0.0040
Price per task: chat reply$0.0002$0.0002
Price per task: summarize a 30-page report$0.0026$0.0015
Price per task: code edit$0.0018$0.0014
Price per task: agentic coding session$0.014$0.0080
Price per task: structured extraction$0.0005$0.0003
Agentic coding session, input mostly cached$0.016$0.0037
Cost per benchmark task (AA Index)–$0.136
Output tokens per task (AA Index)–84k
Of which reasoning–52k
Time per task (AA Index)–3 min
Output speed64 tok/s437 tok/s
Time to first answer0.5 s5.0 s
Time to a complete answer, last measured 13 Nov 2026–12.9 s

Each model is compared at its best-ranked reasoning-effort setting. Gemma 4 31B scores 51.9 and takes 1 s to its first answer token; Gemma 4 31B (no reasoning) scores 49.8 in 4 s, Gemma 4 31B (thinking) scores 46.6 in 52 s. Muse Ember (max) scores 52.1 and takes 5 s to its first answer token; Muse Ember (xhigh) scores 49.1 in 4 s. 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

94 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.

MetricPublisherGemma 4 31BMuse Ember (max)
BenchLeader IndexBenchLeader51.952.1
Coding scoreBenchLeader48.260.0
Human preference scoreBenchLeader54.3–
Knowledge scoreBenchLeader24.448.8
Maths scoreBenchLeader64.7–
Multimodal scoreBenchLeader62.0–
Reasoning scoreBenchLeader61.051.1
Agents & tools scoreBenchLeader–52.4
Blended price $/MBenchLeader$0.250$0.200
Output speedBenchLeader64 tok/s437 tok/s
Time to first answerBenchLeader0.5 s5.0 s
Context windowBenchLeader262,144 tokens1,048,576 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub75.8%†–
SimpleBenchSimpleBench–72.7%†
Arena Hard PromptsArena (LMArena)1475–
LiveBench 2.0 ReasoningLiveBench68.3%†–
GPQA Diamond (AA)Artificial Analysis76.3%†–
Humanity's Last Exam (AA)Artificial Analysis11.8%†–
HLE-Diamond (AA)Artificial Analysis7.2%†25.1%
Kagi LLM BenchmarkKagi LLM Benchmark63.5%–
CritPtArtificial Analysis0.0%†–
CritPt v2 hard subset (AA)Artificial Analysis4.0%†39.0%
Arena ExpertArena (LMArena)1498–
LMCAEpoch AI Benchmarking Hub39.3%–
DTBenchEpoch AI Benchmarking Hub82.7%–
ForecastBenchForecastBench61.1%–
Coding
SciCodeSciCode45.5%–
WeirdMLWeirdML52.3%–
Arena CodingArena (LMArena)1502–
Arena WebDevArena (LMArena)13701609
LiveBench 2.0 CodingLiveBench20.3%†–
Vibe Code Bench v1.1Vals AI–83.7%
SWE Atlas v1.1Scale AI SEAL–56.0%†
SWE Atlas v1.1: Codebase QnAScale AI SEAL–61.3%†
SWE Atlas v1.1: Test WritingScale AI SEAL–56.7%†
SWE Atlas v1.1: RefactoringScale AI SEAL–50.0%†
Surface Evolver BenchEpoch AI Benchmarking Hub30.6%–
Show all 94 benchmarks
MetricPublisherGemma 4 31BMuse Ember (max)
Coding
ALE-BenchEpoch AI Benchmarking Hub925.5–
Terminal-Bench 4.0 (AA)Artificial Analysis0.0%†40.9%
Terminal-Bench 2.1 (AA)Artificial Analysis29.2%†–
GameBench 2 by reasoning settingDuelLab GameBench 218.6†–
Design Arena WebsiteDesign Arena–1330†
FrontierCode 2.0 (AA)Artificial Analysis0.0%†27.2%
Agents & tools
Terminal-BenchTerminal-Bench–30.6%†
APEX-AgentsMercor–64.3%†
Arena AgentArena (LMArena)–1.7
LiveBench Long AgenticLiveBench8.5%†–
LiveBench BrowserLiveBench0.0%†–
Terminal-Bench HardArtificial Analysis30.3%†–
τ²-Bench Telecom (AA)Artificial Analysis65.5%†–
GDPval-AA v2.1, normalised scoreArtificial Analysis2.4%†–
GDPval-AA v2.1Artificial Analysis555†–
τ³-Banking (AA)Artificial Analysis8.9%†–
ITBench SRE (AA)Artificial Analysis37.3%†–
Finance Agent v2.1Vals AI–63.8%
Harvey's Legal Agent Benchmark v1.1Vals AI–25.0%
Legal Research BenchVals AI–49.0%
Tax Agent BenchVals AI–38.2%
Terminal-Bench 2.0 (Vals)Vals AI39.3%†–
Terminal-Bench 4.0 (Vals)Vals AI–39.4%
Arena Agent Task CompletionArena (LMArena)–-7.6
AutomationBenchArtificial Analysis4.9%†68.1%
GDP.pdf (AA)Artificial Analysis6.0%†22.8%
EnterpriseOps-GymArtificial Analysis28.4%†–
AA-Briefcase v1.1Artificial Analysis369†1520
Terminal-Bench-Science 0.1 (AA)Artificial Analysis0.0%†20.0%
FACTS SearchGoogle75.3%–
Maths
OTIS Mock AIMEEpoch AI Benchmarking Hub73.3%†–
Arena MathsArena (LMArena)1467–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub10.4%–
LiveBench 2.0 Data AnalysisLiveBench53.3%†–
LiveBench ResearchLiveBench38.1%†–
AA-Omniscience v1.1Artificial Analysis-48.5†7.4
CaseLaw v2Vals AI52.6%†–
Excel Modeling Benchmark v1.1Vals AI–72.2%
AA-Omniscience v1.1: accuracyArtificial Analysis19.9%†21.1%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis14.5%†82.6%
FACTS ParametricGoogle6.9%–
Instruction following
IFBenchArtificial Analysis53.5%†–
Arena Instruction FollowingArena (LMArena)1453–
Human preference
Arena TextArena (LMArena)1452–
EQ-Bench 4EQ-Bench1110–
EQ-Bench Creative Writing v3EQ-Bench1369–
Arena Creative WritingArena (LMArena)1418–
Arena Multi-turnArena (LMArena)1465–
Arena Longer QueriesArena (LMArena)1469–
Multimodal
Arena VisionArena (LMArena)1279–
LiveBench DesignLiveBench56.5%†–
MMMU-ProArtificial Analysis70.3%†–
MortgageTaxVals AI61.4%†–
SAGEVals AI82.8%†–
FACTS MultimodalGoogle42.3%–
Long context
AA-LCR v1.1Artificial Analysis46.7%†–
Arena DocumentArena (LMArena)1452–
MLCRArtificial Analysis–18.3%
FACTS GroundingGoogle75.8%–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub144.3–
LiveBench 2.0LiveBench32.4%†–
AA Intelligence Index v5.0.1Artificial Analysis4.4†36.0
AA Intelligence Index v4.3.2Artificial Analysis13.9†–
AA Progress Index v1Artificial Analysis233†–
Vals IndexVals AI–60.5
Vals Finance IndexVals AI–60.9%
Vals Legal IndexVals AI–75.7%
Safety & honesty
FORTRESSScale AI SEAL–11.9%†
Metadata
AA Openness IndexArtificial Analysis38.9†–

Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • Gemma 4 31B: BenchLeader Index 47.5 → 51.9.
  • Gemma 4 31B: 1 new result (FACTS Search).
  • Muse Ember (max): 1 new result (Arena Agent).
  • Muse Ember (max): 2 new results (MLCR, Arena WebDev).
  • Gemma 4 31B: BenchLeader Index 48.0 → 47.5.
  • Gemma 4 31B: 5 score revisions.
  • Gemma 4 31B: 1 score revision.
  • Gemma 4 31B: 1 score revision.
  • Gemma 4 31B: BenchLeader Index 48.5 → 48.0.
  • Gemma 4 31B: 3 score revisions.

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

Gemma 4 31B vs Muse Ember: questions

Is Gemma 4 31B better than Muse Ember?
Gemma 4 31B and Muse Ember (max) are neck and neck on quality (51.9 vs 52.1, within the ±8.7 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 16 Nov 2026, so check the category scores for your use.
Gemma 4 31B vs Muse Ember: which is cheaper, and will that change?
Muse Ember is cheaper today: $0.200 against $0.250 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Gemma 4 31B or Muse Ember better for coding?
Muse Ember scores higher in coding (60 vs 48 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1370 for Gemma 4 31B against 1609 for Muse Ember.
Which is faster, Gemma 4 31B or Muse Ember?
Muse Ember streams 3×+ faster (437 vs 64 output tokens per second, Artificial Analysis 7-day median).
Which is better for long documents?
Muse Ember accepts more context: 1,048,576 against 262,144 tokens for Gemma 4 31B.
More questions (3)
Which has lower latency?
Gemma 4 31B answers first: 0.5 s against 5.0 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 Gemma 4 31B vs Muse Ember?
Across the 1 benchmarks both have, Gemma 4 31B leads 0, Muse Ember leads 1. Every overall index that rates both puts Muse Ember ahead.
When was Muse Ember released?
Muse Ember was released on 9 Nov 2026.