Skip to main content

Model comparison

Mistral Medium 3.5 128B vs Muse Spark 1.1

Data verified

Head-to-head evidence from 16 shared benchmark results across 4 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

No comparison
77.44/100
1 category wins0 category wins

Public leaderboard positions: Mistral Medium 3.5 128B unranked (Not scored); Muse Spark 1.1 #6 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Mistral Medium 3.5 128B and Muse Spark 1.1 share 16 comparable benchmark results. 1 of 8 categories are comparable. 9 results are unique to Mistral Medium 3.5 128B; 23 to Muse Spark 1.1.

Updated July 23, 2026
Shared results
16
Mistral Medium 3.5 128B only
9
Muse Spark 1.1 only
23
Comparable categories
1 / 8

Treat this as a split decision. Mistral Medium 3.5 128B makes more sense if coding is the priority; Muse Spark 1.1 is the better fit if you need the larger 1M context window.

Confidence note. This is a partial-evidence comparison with 16 shared benchmark results across 4 evidence categories; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Mistral Medium 3.5 128B and Muse Spark 1.1 finish on the same BenchAlign overall score, so this is less about a single winner and more about where the edge shows up. The BenchAlign headline says tie; the benchmark table is where the real choice happens.

Muse Spark 1.1 gives you the larger context window at 1M, compared with 256K for Mistral Medium 3.5 128B.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for Mistral Medium 3.5 128B and Muse Spark 1.1
CategoryMistral Medium 3.5 128BΔMuse Spark 1.1
CodingMistral Medium 3.5 128B77.6Margin 16.1Muse Spark 1.161.5
AgenticMistral Medium 3.5 128BNot measuredMarginNo overlapMuse Spark 1.180.4
KnowledgeMistral Medium 3.5 128BNot measuredMarginNo overlapMuse Spark 1.162.1
MultimodalMistral Medium 3.5 128BNot measuredMarginNo overlapMuse Spark 1.188.4

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricMistral Medium 3.5 128BMuse Spark 1.1Comparison
Input / output priceUSD per 1M tokensMistral Medium 3.5 128B$1.5 input / $7.5 outputMuse Spark 1.1Not availableA complete price comparison is not available.
Generation speedtokens per secondMistral Medium 3.5 128BNot availableMuse Spark 1.1Not availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenMistral Medium 3.5 128BNot availableMuse Spark 1.1Not availableA complete latency comparison is not available.
Context windowmaximum listed tokensMistral Medium 3.5 128B256KMuse Spark 1.11MMuse Spark 1.1 lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkMistral Medium 3.5 128BMuse Spark 1.1Result
τ³-bench resultsSource 91.4%Not comparable
AA Agentic IndexSource 19.0%37.5%Muse Spark 1.1 leads
τ²-bench resultsSource 94.2%Not comparable
GDPval-AASource 21.4%43.7%Muse Spark 1.1 leads
GDPval-AASource 9291374Muse Spark 1.1 leads
Gert LabsSource 39.10%Not comparable
AA BriefcaseSource 506863Muse Spark 1.1 leads
AA EnterpriseOps-GymSource 33.7%Not comparable
AA Harvey LABSource 69.1%93.1%Muse Spark 1.1 leads
AA Tau3 BankingSource 14.4%25.2%Muse Spark 1.1 leads
terminalBenchHardSource 33.3%Not comparable
Terminal-Bench 2.0Source 80%Not comparable
MCP AtlasSource 88.1%Not comparable
ToolathlonSource 75.6%Not comparable
OSWorld-VerifiedSource 80.8%Not comparable
DeepSearchQASource 84.9%Not comparable
CyberGymSource 59.0%Not comparable
Finance Agent v2Source 57.2%Not comparable
deepSweSource 53.3%Not comparable
OSWorld 2.0Source 14.2%Not comparable
JobBenchSource 54.7%Not comparable
CybenchSource 92.9%Not comparable
ExploitGymSource 0.8%Not comparable
AA AutomationBenchSource 42.8%Not comparable
aaTerminalBench21Source 77.9%Not comparable
CodingMistral Medium 3.5 128B wins
BenchmarkMistral Medium 3.5 128BMuse Spark 1.1Result
SWE-bench VerifiedSource 77.6%Not comparable
AA Coding IndexSource 46.9%71.3%Muse Spark 1.1 leads
AA-SciCodeSource 39.6%58.2%Muse Spark 1.1 leads
Terminal-Bench 2.0Source 80.0%Not comparable
SWE-bench ProSource 61.5%Not comparable
Reasoning
BenchmarkMistral Medium 3.5 128BMuse Spark 1.1Result
AA-LCRSource 61.0%63.3%Muse Spark 1.1 leads
CritPtSource 0.0%15.1%Muse Spark 1.1 leads
MRCR 1MSource 54.1%Not comparable
Knowledge
BenchmarkMistral Medium 3.5 128BMuse Spark 1.1Result
Artificial Analysis Intelligence IndexSource 29.9%50.6%Muse Spark 1.1 leads
AA-GPQA DiamondSource 74.8%89.8%Muse Spark 1.1 leads
AA-HLESource 12.8%45.1%Muse Spark 1.1 leads
AA-Omniscience IndexSource -36.3%18.0%Muse Spark 1.1 leads
AA-Omniscience AccuracySource 25.1%40.6%Muse Spark 1.1 leads
AA-Omniscience Hallucination RateSource 82.0%38.1%Muse Spark 1.1 leads
AA Openness IndexSource 33.3%Not comparable
HLESource 62.1%Not comparable
HLE w/o toolsSource 52.2%Not comparable
HealthBench ProfessionalSource 59.3%Not comparable
Multimodal
BenchmarkMistral Medium 3.5 128BMuse Spark 1.1Result
AA-MMMU-ProSource 64.9%Not comparable
CharXivSource 88.4%Not comparable
BabyVisionSource 76.3%Not comparable
Design Arena WebsiteSource 1299Not comparable
Inst. Following
BenchmarkMistral Medium 3.5 128BMuse Spark 1.1Result
AA-IFBenchSource 68.8%Not comparable
Frequently Asked Questions (2)

Which is better, Mistral Medium 3.5 128B or Muse Spark 1.1?

Mistral Medium 3.5 128B and Muse Spark 1.1 are tied on the BenchAlign overall score, so the right pick depends on which category matters most for your use case.

Which is better for coding, Mistral Medium 3.5 128B or Muse Spark 1.1?

Mistral Medium 3.5 128B has the edge for coding in this comparison, averaging 77.6 versus 61.5. Inside this category, AA Coding Index is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 23, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.