BenchLeader

Inkling Small vs Muse Ember

Full profiles: Inkling Small (Thinking Machines) and Muse Ember (Meta): every benchmark, price and rank.

Updated · Data from 9 sources

As of 16 Nov 2026, Inkling Small and Muse Ember are neck and neck on quality (52.0 vs 52.1 on the BenchLeader Index, inside the ±6.4 margin), and Muse Ember is 2.6× cheaper at $0.200 vs $0.525 per 1M tokens blended. Choose Inkling Small for knowledge (54 vs 49); choose Muse Ember for fast first answers (5.0 s vs 15.6 s) and coding (60 vs 46), reasoning (51 vs 43), and agents & tools (52 vs 46), where it also streams 3×+ faster.

Key facts (as of 16 Nov 2026)

  • Inkling Small scores 52.0 on the BenchLeader Index and Muse Ember scores 52.1 (BenchLeader, 16 Nov 2026).
  • Inkling Small costs $0.525 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 Inkling Small (Artificial Analysis, 7-day median, 16 Nov 2026).
  • Of the 24 benchmarks both models have, Muse Ember leads 23 (BenchLeader, 16 Nov 2026).
  • On Arena WebDev, Inkling Small is rated 1408 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 46 category score; Arena WebDev 1609 vs 1408High
Agents & tool useMuse Ember52 vs 46 category score; Arena Agent 1.7 vs -18.1Medium
ReasoningMuse Ember51 vs 43 category score; HLE-Diamond (AA) 25.1% vs 12.1%High
KnowledgeInkling Small54 vs 49 category score; AA-Omniscience v1.1 -9.5 vs 7.4Medium
Chat quality (human preference)–Only Inkling Small has an Arena rating (58 category score)Not comparable
Lowest costMuse Ember$0.200 vs $0.525 per 1M blended; agentic coding session $0.008 vs $0.023–
Fastest first answerMuse Ember5.0 s (Muse Ember (max)) vs 15.6 s (Inkling Small) 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

  • Inkling Small and Muse Ember (max) are neck and neck on quality (52.0 vs 52.1, within the ±6.4 margin).
  • Inkling Small is stronger in knowledge.
  • Muse Ember (max) is stronger in agents & tools, coding, reasoning.
  • Muse Ember (max) is 2.6× cheaper ($0.200 vs $0.525 per 1M blended).
  • Muse Ember (max) streams 3.8× faster (437 vs 116 tokens per second).

At a glance

SpecInkling SmallMuse Ember
DeveloperThinking MachinesMeta
Released15 Jul 20269 Nov 2026
Context window (tokens)65,5361,048,576
Compared atInkling SmallMuse Ember (max)
Open weightsYesNo
Price in / out / cached input per 1M$0.300 / $1.20 / $0.116$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.

CategoryInkling SmallMuse Ember (max)Leader
Reasoning43.251.1Muse Ember
Coding45.660.0Muse Ember
Agents & tools45.752.4Muse Ember
Maths53.0–not comparable
Knowledge54.348.8Inkling Small
Human preference57.8–not comparable
Multimodal56.3–not comparable
Long context62.4–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 avg75ReasoningCodingAgents & toolsKnowledgeInkling Small, Reasoning: 43.2Inkling Small, Coding: 45.6Inkling Small, Agents & tools: 45.7Inkling Small, Knowledge: 54.3Muse Ember, Reasoning: 51.1Muse Ember, Coding: 60.0Muse Ember, Agents & tools: 52.4Muse Ember, Knowledge: 48.8

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

Model, click to add or removeIndex

Where sources disagree

Across the 24 benchmarks both have, Inkling Small leads 1, Muse Ember leads 23. Every overall index that rates both puts Muse Ember ahead.

Overall indexInkling SmallMuse Ember (max)Leader
BenchLeader Index52.052.1neck and neck
AA Intelligence Index v5.0.112.936.0Muse Ember
Vals Index27.660.5Muse 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.

MeasureInkling SmallMuse Ember (max)
Blended price per 1M tokens$0.525$0.200
Input / output per 1M$0.300 / $1.20$0.100 / $0.500
Cached input per 1M$0.116$0.0040
Price per task: chat reply$0.0005$0.0002
Price per task: summarize a 30-page report$0.0043$0.0015
Price per task: code edit$0.0036$0.0014
Price per task: agentic coding session$0.023$0.0080
Price per task: structured extraction$0.0008$0.0003
Agentic coding session, input mostly cached$0.015$0.0037
Cost per benchmark task (AA Index)$0.203$0.136
Output tokens per task (AA Index)37k84k
Of which reasoning25k52k
Time per task (AA Index)5 min3 min
Output speed116 tok/s437 tok/s
Time to first answer15.6 s5.0 s
Time to a complete answer, last measured 13 Nov 2026–12.9 s

Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $0.203 on Inkling Small and $0.136 on Muse Ember (max), and Muse Ember (max) wrote 2.3× as many output tokens for the same work, which a per-token price hides.

Each model is compared at its best-ranked reasoning-effort setting. Inkling Small scores 52.0 and takes 16 s to its first answer token; Inkling Small (xhigh) scores 47.3 in 16 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

101 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.

MetricPublisherInkling SmallMuse Ember (max)
BenchLeader IndexBenchLeader52.052.1
Agents & tools scoreBenchLeader45.752.4
Coding scoreBenchLeader45.660.0
Human preference scoreBenchLeader57.8–
Knowledge scoreBenchLeader54.348.8
Long context scoreBenchLeader62.4–
Maths scoreBenchLeader53.0–
Multimodal scoreBenchLeader56.3–
Reasoning scoreBenchLeader43.251.1
Blended price $/MBenchLeader$0.525$0.200
Output speedBenchLeader116 tok/s437 tok/s
Time to first answerBenchLeader15.6 s5.0 s
Context windowBenchLeader65,536 tokens1,048,576 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub88.5%†–
SimpleBenchSimpleBench–72.7%†
Arena Hard PromptsArena (LMArena)1428–
GPQA Diamond (AA)Artificial Analysis89.5%–
Humanity's Last Exam (AA)Artificial Analysis33.3%–
HLE-Diamond (AA)Artificial Analysis12.1%25.1%
GPQA Diamond (Vals)Vals AI83.6%–
ARC-AGI-1ARC Prize84.0%†–
ARC-AGI-2ARC Prize40.1%†–
CritPtArtificial Analysis8.3%–
CritPt v2 hard subset (AA)Artificial Analysis18.5%39.0%
Arena ExpertArena (LMArena)1441–
Mystery Game PuzzlesEpoch AI Benchmarking Hub6.0%†–
Coding
SciCodeSciCode49.6%–
Arena CodingArena (LMArena)1472–
Arena WebDevArena (LMArena)14081609
LiveCodeBenchVals AI85.9%–
IOIVals AI9.3%–
SWE-bench (Vals)Vals AI82.2%–
Code MigrationVals AI13.7%–
Code Migration v1.1Vals AI10.4%–
ProgramBenchVals AI0.5%–
Vibe Code Bench v1.1Vals AI19.1%83.7%
SWE Atlas v1.1Scale AI SEAL–56.0%†
SWE Atlas v1.1: Codebase QnAScale AI SEAL–61.3%†
Show all 101 benchmarks
MetricPublisherInkling SmallMuse Ember (max)
Coding
SWE Atlas v1.1: Test WritingScale AI SEAL–56.7%†
SWE Atlas v1.1: RefactoringScale AI SEAL–50.0%†
Terminal-Bench 4.0 (AA)Artificial Analysis1.0%40.9%
Terminal-Bench 2.1 (AA)Artificial Analysis55.1%–
GameBench 2 OverallDuelLab GameBench 229.2–
GameBench 2 by reasoning settingDuelLab GameBench 228.1†–
Design Arena WebsiteDesign Arena–1330†
FrontierCode 1.1 (AA)Artificial Analysis0.6%–
FrontierCode 2.0 (AA)Artificial Analysis4.8%27.2%
Agents & tools
Terminal-BenchTerminal-Bench0.9%†30.6%†
APEX-AgentsMercor–64.3%†
Arena AgentArena (LMArena)-18.11.7
Terminal-Bench 2.1 (Vals)Vals AI55.1%–
MCP AtlasScale AI SEAL79.2%–
GDPval-AA v2.1, normalised scoreArtificial Analysis31.2%–
GDPval-AA v2.1Artificial Analysis1133–
τ³-Banking (AA)Artificial Analysis18.8%–
Analyst Agent (AA)Artificial Analysis27.5%–
CyberBenchVals AI64.1%–
Finance Agent v2Vals AI41.3%–
Finance Agent v2.1Vals AI44.8%63.8%
Harvey's Legal Agent Benchmark v1.1Vals AI2.9%25.0%
Harvey's Legal Agent Benchmark v1Vals AI1.7%–
Legal Research BenchVals AI25.5%49.0%
SkillsBenchVals AI33.6%–
Tax Agent BenchVals AI15.4%38.2%
Terminal-Bench 4.0 (Vals)Vals AI0.0%39.4%
Arena Agent Task CompletionArena (LMArena)-27.6-7.6
AutomationBenchArtificial Analysis4.8%68.1%
GDP.pdf (AA)Artificial Analysis11.2%22.8%
Harvey LAB-AA v1.1Harvey0.0%–
EnterpriseOps-GymArtificial Analysis42.7%–
AA-Briefcase v1.1Artificial Analysis9121520
Terminal-Bench-Science 0.1 (AA)Artificial Analysis0.0%20.0%
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub46.3%†–
FrontierMath Tier 4Epoch AI Benchmarking Hub17.1%†–
OTIS Mock AIMEEpoch AI Benchmarking Hub90.0%†–
ProofBenchVals AI6.0%–
Arena MathsArena (LMArena)1452–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub19.1%†–
AA-Omniscience v1.1Artificial Analysis-9.57.4
MMLU-ProVals AI85.6%–
LegalBenchVals AI83.0%–
CorpFinVals AI69.6%–
TaxEvalVals AI75.5%–
Excel Modeling BenchmarkVals AI31.8%–
Excel Modeling Benchmark v1.1Vals AI40.8%72.2%
MedCodeVals AI37.9%–
MedScribeVals AI84.1%–
Public Benefits Bench v1.1Vals AI59.4%–
AA-Omniscience v1.1: accuracyArtificial Analysis31.8%21.1%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis39.5%82.6%
Instruction following
Arena Instruction FollowingArena (LMArena)1397–
Human preference
Arena TextArena (LMArena)1405–
EQ-Bench Creative Writing v3EQ-Bench1491–
Arena Creative WritingArena (LMArena)1319–
Arena Multi-turnArena (LMArena)1414–
Arena Longer QueriesArena (LMArena)1401–
Multimodal
Arena VisionArena (LMArena)1236–
MMMU-ProArtificial Analysis74.0%–
MortgageTaxVals AI62.3%–
AudioMCScale AI SEAL54.9%–
AudioMC (text output)Scale AI SEAL54.9%–
Long context
AA-LCR v1.1Artificial Analysis75.7%–
MLCRArtificial Analysis7.8%18.3%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub150.8–
AA Intelligence Index v5.0.1Artificial Analysis12.936.0
AA Intelligence Index v4.3.2Artificial Analysis25.7–
AA Progress Index v1Artificial Analysis282.7–
Vals IndexVals AI27.660.5
Vals Finance IndexVals AI36.3%60.9%
Vals Multimodal IndexVals AI50.0%–
Vals Router IndexVals AI27.6%–
Vals Legal IndexVals AI57.8%75.7%
Safety & honesty
FORTRESSScale AI SEAL–11.9%†
Metadata
AA Openness IndexArtificial Analysis33.3–

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

  • Inkling Small: 1 score revision.
  • Muse Ember (max): 1 new result (Arena Agent).
  • Inkling Small: 1 score revision.
  • Muse Ember (max): 2 new results (MLCR, Arena WebDev).
  • Inkling Small: 1 score revision.
  • Inkling Small: 1 score revision.
  • Inkling Small: 1 score revision.
  • Inkling Small: BenchLeader Index 54.9 → 51.9.
  • Inkling Small: 5 new results (AA Intelligence Index v5.0.1, AA Progress Index v1, HLE-Diamond (AA)…); 3 score revisions; Inkling Small cost per task moved from $0.089/M to $0.20/M (127% up).
  • Inkling Small: 1 new result (AA-Briefcase v1.1).

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

Inkling Small vs Muse Ember: questions

Is Inkling Small better than Muse Ember?
Inkling Small and Muse Ember (max) are neck and neck on quality (52.0 vs 52.1, within the ±6.4 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.
Inkling Small vs Muse Ember: which is cheaper, and will that change?
Muse Ember is cheaper today: $0.200 against $0.525 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Inkling Small or Muse Ember better for coding?
Muse Ember scores higher in coding (60 vs 46 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1408 for Inkling Small against 1609 for Muse Ember.
Which is faster, Inkling Small or Muse Ember?
Muse Ember streams 3×+ faster (437 vs 116 output tokens per second, Artificial Analysis 7-day median).
Is Inkling Small or Muse Ember better for agents and tool use?
Muse Ember scores higher in agentic tasks (52 vs 46 on the category index, where 50 is average). On Arena Agent, the top shared agents & tools benchmark, it is -18.1 for Inkling Small against 1.7 for Muse Ember.
More questions (4)
Which is better for long documents?
Muse Ember accepts more context: 1,048,576 against 65,536 tokens for Inkling Small.
Which has lower latency?
Muse Ember answers first: 5.0 s against 15.6 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 Inkling Small vs Muse Ember?
Across the 24 benchmarks both have, Inkling Small leads 1, Muse Ember leads 23. Every overall index that rates both puts Muse Ember ahead.
When was Muse Ember released?
Muse Ember was released on 9 Nov 2026.