Muse Spark 1.3 benchmarks

Muse Spark 1.3 is a proprietary model from Meta, released 2 Sep 2026. It ranks 5th of 51 on our overall leaderboard and 6th of 51 for reasoning. At A$2.81 per million tokens (blended), it costs about 1.3× cheaper than the median model we track. It writes about 248 tokens a second, and answers start after 35 s on average, thinking included. None of the major cloud platforms offer it in an Australian region yet.

#5 OF 51 OVERALLA$2.81 / 1M TOKENS1M CONTEXTUPDATED 23 SEP 2026
CONTEXT WINDOW
1,048,576 tokens
INPUT
text, image, video, audio
WEIGHTS
Proprietary
RELEASED
2 Sep 2026
OUTPUT SPEED
248 tok/s
ANSWER STARTS AFTER
35 s (thinking included)
META DOCS
§ 02 — RESULTS

Benchmark results.

Independent test scores are for the max effort setting. “Among tracked” ranks Muse Spark 1.3 against the 51 models on this site; LMArena ranks run across its full leaderboard.

ALL RESULTS8 OF 8 CORE SIGNALS
Muse Spark 1.3 benchmark results
BENCHMARKRESULTAMONG TRACKEDSOURCE DETAIL
INDEPENDENT TESTS · ARTIFICIAL ANALYSIS
AA Intelligence Index48.1#6 of 51max effort
AA Coding Index75.8#12 of 42max effort
GPQA Diamond93.5%#8 of 44max effort
Humanity’s Last Exam48.7%#8 of 51max effort
AA-LCR83.0%#12 of 51max effort
Terminal-Bench 2.184.3%#14 of 42max effort
τ²-Bench (banking)50.5%#2 of 41max effort
SciCode58.8%#8 of 46max effort
BLIND HUMAN VOTES · LMARENA
LMArena Text4,723 votes · ±91493#6 of 42#8 of 402 on LMArena · 13 Sep 2026
LMArena WebDev5,239 votes · ±101657#6 of 45#8 of 129 on LMArena · 22 Sep 2026
LMArena Vision1,804 votes · ±151294#5 of 33#6 of 152 on LMArena · 13 Sep 2026
LMArena Document1,006 votes · ±181468#15 of 26#19 of 44 on LMArena · 13 Sep 2026
LMArena Agent31,052 sessions#15#13 of 37#15 of 46 on LMArena · 15 Sep 2026
§ 03 — COST

What Muse Spark 1.3 costs in Australian dollars.

List prices converted at the snapshot’s RBA rate, excluding GST. Reasoning models are billed for their thinking as output tokens, so heavier settings cost more than the job estimates show.

LIST PRICE
Muse Spark 1.3 price per million tokens
PER MILLION TOKENSAUDUSD LIST
Input tokensA$1.75US$1.25
Output tokensA$5.97US$4.25
Blended (3 in : 1 out)A$2.81US$2.00
EVERYDAY JOBSESTIMATES
Estimated cost of common jobs in Australian dollars
JOBCOST (AUD)MEDIAN MODEL
Customer support replyPER 1,000 REPLIESA$5.30A$6.58
Summarise a 30-page documentPER 100 DOCUMENTSA$3.99A$4.74
Agentic coding taskPER 10 TASKSA$3.11A$3.72
SETTINGSMEASURED SEPARATELY
Muse Spark 1.3 settings compared
SETTINGINTELLIGENCEA$ / 1MSPEED
max effort48.1A$2.81248 tok/s
xhigh effort45.1A$2.81337 tok/s
§ 04 — AUSTRALIA

Running Muse Spark 1.3 in Australia.

None of the major cloud platforms offer it in an Australian region yet. How the platforms compare →

AUSTRALIAN CLOUD REGIONS
Muse Spark 1.3 availability in Australian cloud regions
PLATFORMAVAILABILITYDETAIL
AWS Bedrock · SydneyNOT OFFERED
AWS Bedrock · MelbourneNOT OFFERED
Azure · Australia EastNOT OFFERED
Google Vertex AI · SydneyNOT OFFERED
§ 06 — QUESTIONS

Muse Spark 1.3, answered.

Muse Spark 1.3 lists at US$1.25 per million input tokens and US$4.25 per million output tokens — A$1.75 and A$5.97 at A$1 = US$0.7123 (RBA, 22 Sep 2026), excluding GST. A typical customer support reply works out at about A$5.30 per 1,000 replies, before any reasoning tokens.

None of the major cloud platforms offer it in an Australian region yet. Availability comes from the cloud providers’ own documentation; check your provider’s current terms before relying on it for data-residency obligations.

It ranks 6th of 42 on our coding ranking, with an Artificial Analysis Coding Index of 75.8 and an LMArena WebDev rating of 1657 (8th of 129). The current leader is Claude Fable 5.1.

It ranks 5th of 41 on our agents ranking, completing 50.5% of τ²-Bench banking customer-service tasks and 84.3% of Terminal-Bench 2.1 tasks.

Artificial Analysis measures Muse Spark 1.3 at about 248 tok/s of output, with the answer starting after 35 s on average once thinking time is included (max effort setting).

Meta documents a context window of 1,048,576 tokens (1M). On AA-LCR, which tests reasoning across ~100,000-token document sets, it scores 83.0%.

PUT THE COMPARISON TO WORK

Need help choosing and using AI for your business?