MetaReasoning modelMuse Spark 1.3
Muse Spark 1.3 is a Meta proprietary reasoning model, released 2 Sept 2026. Its best configuration (max reasoning effort) ranks #21 of 751 on the BenchLeader Index at 67.8 ±4.4, in the top 25. The ± is the point: 69 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in composite (85) and lowest in coding (65). At $2.00 per million tokens blended it is pricier than most ranked models. Output speed of 152 tokens per second puts it in the fastest quarter, with a first answer in 64.7 s. It has been measured at 7 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 2 Oct 2026.
- Blended price
- $2.00/M
- $1.25 in · $4.25 out
- Output speed
- 152 tok/s
- measured by Artificial Analysis
- First answer
- 65 s
- first token 4.79 s
- Context
- 1.0M
- Full answer
- 68 s
- median, reasoning included
- Cost per run
- $1.60
- one full Intelligence Index run
- Released
- 2 Sept 2026
- Overall index68
- Reasoning78
- Coding65
- Agents & tools70
- Maths65
- Knowledge73
- Human preference69
- Multimodal66
- Long context67
- Composite85
Versions
Meta has shipped 4 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| Muse Spark 1.3maxthis page | 2 Sept 2026 | 67.8 | #21 |
| Muse Spark 1.2xhigh | 5 Aug 2026 | 62.7 | #76 |
| Muse Spark 1.1 | 9 Jul 2026 | 64.2 | #55 |
| Muse Spark | 8 Apr 2026 | 64.8 | #46 |
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| minimal | – | – | 58 tok/s | 4.79 s | $0.0018 | |
| low | – | – | 58 tok/s | 4.79 s | $0.0018 | |
| medium | – | – | 58 tok/s | 4.79 s | $0.0018 | |
| high | – | – | 58 tok/s | 4.79 s | $0.0018 | |
| xhigh | 66.3 | #32 | 140 tok/s | 54 s | $0.0018 | Agents & tools 71 · Coding 61 · Composite 75 · Knowledge 72 · Long context 67 · Maths 63 · Multimodal 65 · Reasoning 85 |
| maxbest | 67.8 | #21 | 152 tok/s | 65 s | $0.0018 | Agents & tools 70 · Coding 65 · Composite 85 · Human preference 69 · Knowledge 73 · Long context 67 · Maths 65 · Multimodal 66 · Reasoning 78 |
| not stated | – | – | 58 tok/s | 4.79 s | $0.0018 | Agents & tools 57 · Knowledge 83 |
How its index has moved
9 Sept 2026 to 3 Oct 2026- max
- xhigh
The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | minimal | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| LMArena Hard Prompts | – | – | – | – | – | 1517#10 | – | LMArena | |
| LiveBench Reasoningnot in index | – | – | – | – | 89.7%#14 | – | – | LiveBench | |
| GPQA Diamond (AA)not in index | – | – | – | – | 94.1%#7 | 93.5%#14 | – | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | – | – | – | – | 47.5%#35 | 48.7%#29 | – | Artificial Analysis | |
| CritPt | – | – | – | – | 26.0%#37 | 24.9%#42 | – | Artificial Analysis | |
| MysteryMechanismnot in index | – | – | – | – | – | 36.0%#9 | – | Vals AI | |
| Chess Puzzlesnot in index | – | – | – | – | 35.0%#40 | 38.0%#32 | – | Epoch AI Benchmarking Hub | |
| Mystery Game Puzzlesnot in index | – | – | – | – | 14.1%#90 | 25.0%#42 | – | Epoch AI Benchmarking Hub | |
| LMCAnot in index | – | – | – | – | – | – | 53.9%#35 | Epoch AI Benchmarking Hub | |
| DTBenchnot in index | – | – | – | – | – | – | 96.5%#17 | Epoch AI Benchmarking Hub | |
| BTF-3not in index | – | – | – | – | 14.1%#5 | – | – | Epoch AI Benchmarking Hub |
Coding
| Benchmark | minimal | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| SciCode | – | – | – | – | 59.7%#8 | 58.8%#13 | – | SciCode | |
| LMArena Coding | – | – | – | – | – | 1539#11 | – | LMArena | |
| LMArena WebDev | – | – | – | – | 1624#18 | 1657#14 | – | LMArena | |
| LiveBench Codingnot in index | – | – | – | – | 81.1%#16 | – | – | LiveBench | |
| SciCode (AA)not in index | – | – | – | – | 59.7%#11 | 58.8%#16 | – | Artificial Analysis | |
| IOI | – | – | – | – | 43.9%#27 | 56.6%#17 | – | Vals AI | |
| Code Migrationnot in index | – | – | – | – | 27.6%#37 | 47.4%#12 | – | Vals AI | |
| Vibe Code Bench 1-100not in index | – | – | – | – | – | 20.5%#6 | – | Vals AI | |
| Vibe Code Bench v1.1not in index | – | – | – | – | 82.9%#15 | 85.9%#11 | – | Vals AI | |
| CursorBenchnot in index | 24.3%#51 | 29.3%#45 | 32.6%#39 | 33.4%#35 | 37.5%#27 | 41.6%#18 | – | Cursor | |
| Terminal-Bench 4.0 (AA)not in index | – | – | – | – | 16.7%#58 | 33.3%#35 | – | Artificial Analysis | |
| Terminal-Bench 2.1 (AA)not in index | – | – | – | – | 85.4%#25 | 84.3%#30 | – | Artificial Analysis |
Agents & tools
| Benchmark | minimal | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| APEX-Agents | – | – | – | – | – | – | 57.8%#13 | Mercor | |
| LMArena Agent | – | – | – | – | – | 4#16 | – | LMArena | |
| LiveBench Agentic Codingnot in index | – | – | – | – | 64.1%#8 | – | – | LiveBench | |
| Terminal-Bench 2.1 (Vals) | – | – | – | – | 72.3%#24 | 79.0%#11 | – | Vals AI | |
| GDPval (AA)not in index | – | – | – | – | 55.9%#18 | 58.6%#13 | – | Artificial Analysis | |
| τ²-Bench Banking (AA) | – | – | – | – | 47.2%#8 | 50.5%#3 | – | Artificial Analysis | |
| ITBench SRE (AA)not in index | – | – | – | – | – | 33.2%#29 | – | Artificial Analysis | |
| CUA-benchnot in index | – | – | – | – | – | 5.8%#6 | – | Vals AI | |
| CyberBenchnot in index | – | – | – | – | 69.4%#22 | 72.7%#13 | – | Vals AI | |
| Finance Agent v2not in index | – | – | – | – | 58.9%#6 | 60.0%#4 | – | Vals AI | |
| Harvey's Legal Agent Benchmarknot in index | – | – | – | – | 22.9%#3 | 23.8%#2 | – | Vals AI | |
| Legal Research Benchnot in index | – | – | – | – | 40.9%#22 | 55.3%#1 | – | Vals AI | |
| Tax Agent Benchnot in index | – | – | – | – | 71.9%#7 | 72.4%#6 | – | Vals AI | |
| Terminal-Bench 4.0 (Vals)not in index | – | – | – | – | 10.6%#29 | 24.8%#15 | – | Vals AI | |
| Terminal-Bench Sciencenot in index | – | – | – | – | 4.3%#17 | 10.0%#11 | – | Vals AI | |
| AutomationBenchnot in index | – | – | – | – | 56.8%#27 | 57.9%#25 | – | Artificial Analysis | |
| GDP.pdfnot in index | – | – | – | – | 24.2%#18 | 26.6%#10 | – | Artificial Analysis | |
| Harvey LABnot in index | – | – | – | – | 95.5%#1 | – | – | Harvey | |
| AA-Briefcasenot in index | – | – | – | – | 1487#27 | 1583#12 | – | Artificial Analysis |
Maths
| Benchmark | minimal | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| FrontierMath Tiers 1–3 | – | – | – | – | 74.4%#19 | 74.0%#20 | – | Epoch AI Benchmarking Hub | |
| FrontierMath Tier 4 | – | – | – | – | 41.5%#28 | 46.3%#25 | – | Epoch AI Benchmarking Hub | |
| OTIS Mock AIME | – | – | – | – | 99.2%#14 | – | – | Epoch AI Benchmarking Hub | |
| LiveBench Mathematicsnot in index | – | – | – | – | 96.0%#12 | – | – | LiveBench | |
| LMArena Maths | – | – | – | – | – | 1509#9 | – | LMArena |
Knowledge
| Benchmark | minimal | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| LiveBench Data Analysisnot in index | – | – | – | – | 79.6%#11 | – | – | LiveBench | |
| AA-Omniscience | – | – | – | – | 23.1#53 | 25#50 | – | Artificial Analysis | |
| PRBench Finance | – | – | – | – | – | – | 59.5%#1 | Scale AI SEAL | |
| PRBench Legal | – | – | – | – | – | – | 61.6%#1 | Scale AI SEAL | |
| Excel Modeling Benchmarknot in index | – | – | – | – | 62.7%#29 | 67.4%#15 | – | Vals AI | |
| DrugDiscoveryBenchnot in index | – | – | – | 62.2%#2 | – | – | – | Scale AI SEAL | |
| GDP.pdfnot in index | – | – | – | – | 27.6%#7 | – | 27.6%#7 | Epoch AI Benchmarking Hub | |
| AA-Omniscience: accuracynot in index | – | – | – | – | 41.5%#107 | 43.6%#96 | – | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | – | – | – | – | 68.5%#47 | 67.1%#52 | – | Artificial Analysis |
Instruction following
| Benchmark | minimal | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| LiveBench Languagenot in index | – | – | – | – | 82.8%#23 | – | – | LiveBench | |
| LiveBench Instruction Followingnot in index | – | – | – | – | 78.0%#4 | – | – | LiveBench | |
| LMArena Instruction Followingnot in index | – | – | – | – | – | 1486#16 | – | LMArena |
Human preference
| Benchmark | minimal | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| LMArena Text | – | – | – | – | – | 1494#9 | – | LMArena | |
| LMArena Creative Writingnot in index | – | – | – | – | – | 1459#28 | – | LMArena | |
| LMArena Multi-turnnot in index | – | – | – | – | – | 1490#22 | – | LMArena | |
| LMArena Longer Queriesnot in index | – | – | – | – | – | 1499#16 | – | LMArena |
Multimodal
| Benchmark | minimal | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| LMArena Vision | – | – | – | – | – | 1310#11 | – | LMArena | |
| MMMU-Pro | – | – | – | – | 82.0%#34 | – | – | Artificial Analysis |
Long context
| Benchmark | minimal | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| AA-LCR | – | – | – | – | 83.0%#24 | 83.0%#24 | – | Artificial Analysis | |
| LMArena Documentnot in index | – | – | – | – | – | 1468#19 | – | LMArena | |
| MLCRnot in index | – | – | – | – | – | 43.3%#11 | – | Artificial Analysis |
Composite
| Benchmark | minimal | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| Epoch Capabilities Indexnot in index | – | – | – | – | – | – | 156.9#17 | Epoch AI Benchmarking Hub | |
| LiveBench | – | – | – | – | 81.6%#7 | – | – | LiveBench | |
| AA Intelligence Index | – | – | – | – | 45.1#34 | 48.1#23 | – | Artificial Analysis | |
| Vals Indexnot in index | – | – | – | – | 53.2#18 | 58.2#9 | – | Vals AI |
Where it wins
Benchmarks where this configuration ranks in the top five of every configuration measured.
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Meta | 60 tok/s | 4.79 s | $1.25 | $4.25 | 1.0M | – |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.150 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0018 | $0.0014 | 1.1 min |
| Summarise a 30-page report | 12,000 / 600 | $0.018 | $0.0077 | 1.1 min |
| Code edit | 6,000 / 1,500 | $0.014 | $0.0089 | 1.2 min |
| Agentic coding session | 60,000 / 4,000 | $0.092 | $0.043 | 1.5 min |
| Structured extraction | 2,000 / 200 | $0.0034 | $0.0017 | 1.1 min |
See also
Data as of 4 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “Muse Spark 1.3: benchmarks, pricing, speed and rank”, https://www.benchleader.com/models/muse-spark-1-3, data as of 4 Oct 2026.