Muse Spark 1.3
- Input
- $1.25/M tok
- Output
- $4.25/M tok
- Blended
- $2.00/M tok · 3:1
- Speed
- 124tok/s
- Context
- 1Mtokens
- Cost per task
- ~$1.8/taskest.
Rankings
Coding
Verified#19 / 137rank by quality72.4±4.5quality / 1004/7 benchmarks measuredSpeed frontierWriting & chat
Verified#11 / 162rank by quality78.1±4.6quality / 1003/5 benchmarks measuredPrice frontierSpeed frontierVision
Verified#11 / 98rank by quality77.7±4.8quality / 1003/6 benchmarks measuredHard reasoning
Verified#14 / 218rank by quality81.5±3.7quality / 1003/4 benchmarks measuredSpeed frontierAgents
Verified#7 / 187rank by quality85.3±5.9quality / 1003/7 benchmarks measuredPrice frontierSpeed frontier
Benchmark scores
~ italic, dashed = no published score yet, estimated from related benchmarks.
Coding
SWE-bench VerifiedEstimated
~#2 of 21 (estimated)~88.1%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#6 of 24 (estimated)~71.3%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #5Claude Opus 579.2%
- ~#6Muse Spark 1.3Estimated71.3%
- #6Intern-S2-397B68.5%
No published score — estimated from related benchmarks
DeepSWE v1.1Verified
#11 of 4571.7%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #10MiMo-V2.6-Pro71.9%
- #11Muse Spark 1.371.7%
- #12Claude Sonnet 5.571.0%
artificialanalysis.ai · 2026-09-24
Terminal-Bench 4.0Verified
#19 of 10133.3%
- #1Kimi K3.1 Pro67.2%
- #2Claude Sonnet 5.563.6%
- #19Ling 3.1 Flash33.3%
- #19Muse Spark 1.333.3%
- #19Step 5 Preview33.3%
artificialanalysis.ai · 2026-09-24
LiveCodeBenchEstimated
~#10 of 28 (estimated)~87.1%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #9Nemotron 3.5 Super VL NVFP487.4%
- ~#10Muse Spark 1.3Estimated87.1%
- #10Ternary Bonsai 27B82.8%
No published score — estimated from related benchmarks
SciCodeVerified
#13 of 11858.8%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #12Step 5 Preview58.9%
- #13Muse Spark 1.358.8%
- #14Gemini 3.1 Pro58.7%
artificialanalysis.ai · 2026-09-24
Writing & chat
IFBenchEstimated
~#12 of 140 (estimated)~79.2%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #11Qwen3.8 27B79.5%
- ~#12Muse Spark 1.3Estimated79.2%
- #12Ripple-65B Preview79.2%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Few votesVerified
#5 of 561484 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #4Gemini 3.8 FlashFew votes1486
- #5Muse Spark 1.3Few votes1484
- #6Claude Opus 51480
lmarena.ai · 2026-10-08
LMArena Text (Elo)Verified
#5 of 561493 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #4Gemini 3.8 Flash1497
- #5Muse Spark 1.31493
- #6Claude Opus 51490
lmarena.ai · 2026-09-24
#9 of 251906 Elo
eqbench.com · 2026-09-24
Vision
MMMU-ProVerified
#10 of 8782.0%
- #1Claude Opus 5.587.7%
- #2GPT-6 Astra86.9%
- #9Gemini 3.1 Pro82.4%
- #10Muse Spark 1.382.0%
- #11Intern-S2-397B81.7%
artificialanalysis.ai · 2026-09-24
CharXiv ReasoningEstimated
~#4 of 12 (estimated)~84.0%
- #1Gemini 3.8 Flash86.2%
- #2Kimi K384.8%
- #3Qwen3.8 Flash-Next84.6%
- ~#4Muse Spark 1.3Estimated84.0%
- #4Qwen3.8-Omni-Flash83.5%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#4 of 8 (estimated)~90.5%
- #1MiniMax-M391.6%
- #2Kimi K391.1%
- #2Qwen3.8 27B91.1%
- ~#4Muse Spark 1.3Estimated90.5%
- #4Gemini 3.1 Pro85.3%
No published score — estimated from related benchmarks
GDP.pdf (AA)Verified
#5 of 4726.6%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #4Muse Wonder30.6%
- #5Muse Spark 1.326.6%
- #6Claude Fable 5.126.2%
artificialanalysis.ai · 2026-09-24
ChartographyVerified
#12 of 2427.6%
- #1Claude Fable 5.273.4%
- #2GPT-6 Astra71.0%
- #10Qwen3.8 Max (0902)29.1%
- #12Muse Spark 1.327.6%
- #13Claude Opus 527.3%
surgehq.ai · 2026-09-24
Hard reasoning
GPQA DiamondVerified
#5 of 19293.5%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #5Kimi K393.5%
- #5Muse Spark 1.393.5%
- #5Qwen3.8 2.4T A95B93.5%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#13 of 19848.7%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #12MiMo-V2.6-Pro49.4%
- #13Muse Spark 1.348.7%
- #14MiniMax-M3.1-Flash48.0%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#2 of 34 (estimated)~98.7%
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Estimated
~#2 of 120 (estimated)~98.3%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#3 of 15 (estimated)~83.7%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~57.8%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#4 of 22 (estimated)~91.0%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #3Kimi K391.2%
- ~#4Muse Spark 1.3Estimated91.0%
- #4Claude Opus 590.8%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Verified
#9 of 911681 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #8MiMo-V2.6-Pro1682
- #9Muse Spark 1.31681
- #10Qwen3.8 Max (0902)1668
artificialanalysis.ai · 2026-10-10
AutomationBench-AAVerified
#19 of 8457.9%
- #1Claude Fable 5.276.4%
- #2Muse Wonder Full71.3%
- #18Kimi K358.3%
- #19Muse Spark 1.357.9%
- #20Qwen3.8 2.4T A95B57.2%
artificialanalysis.ai · 2026-09-24
Not comparable across labs (1)
Kept for reference, not counted in rankings: these use a lab-specific task set, answer key or scoring, so scores can't be compared fairly across labs. Only published scores are shown.