Skip to main content

Model comparison

MiniMax M3 vs Mistral Medium 3.5 128B

Data verified

Head-to-head evidence from 21 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

MiniMax
69.8/100
Margin
8.8pts
← winning
0 category wins1 category wins

Verified leaderboard positions: MiniMax M3 #18; Mistral Medium 3.5 128B unranked

BenchAlign evidence: MiniMax M3 supported; Mistral Medium 3.5 128B not scored. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. MiniMax M3 and Mistral Medium 3.5 128B share 21 comparable benchmark results. 1 of 8 categories are comparable. 24 results are unique to MiniMax M3; 3 to Mistral Medium 3.5 128B.

Updated July 16, 2026
Shared results
21
MiniMax M3 only
24
Mistral Medium 3.5 128B only
3
Comparable categories
1 / 8

Pick MiniMax M3 if you want the stronger benchmark profile. Mistral Medium 3.5 128B only becomes the better choice if coding is the priority or you want the stronger reasoning-first profile.

Confidence note. This is a partial-evidence comparison with 21 shared benchmark results across 6 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

MiniMax M3 is clearly ahead on the provisional aggregate, 70 to 61. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Mistral Medium 3.5 128B is also the more expensive model on tokens at $1.50 input / $7.50 output per 1M tokens, versus $0.30 input / $1.20 output per 1M tokens for MiniMax M3. That is roughly 6.3x on output cost alone. Mistral Medium 3.5 128B is the reasoning model in the pair, while MiniMax M3 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. MiniMax M3 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 MiniMax M3 and Mistral Medium 3.5 128B
CategoryMiniMax M3ΔMistral Medium 3.5 128B
CodingMiniMax M372.2Margin 5.4Mistral Medium 3.5 128B77.6
AgenticMiniMax M372.3MarginNo overlapMistral Medium 3.5 128BNot measured
MathMiniMax M385.7MarginNo overlapMistral Medium 3.5 128BNot measured
MultimodalMiniMax M364.9MarginNo overlapMistral Medium 3.5 128BNot measured

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · MiniMax M3B · Mistral Medium 3.5 128B
  1. SWE-bench Verified

    Coding
    Source ↗
    A 80.5%B 77.6%
    Winner: MiniMax M3Δ 2.9
    SWE-bench Verified: MiniMax M3 scored 80.5%; Mistral Medium 3.5 128B scored 77.6%. MiniMax M3 wins this benchmark.

Operational comparison

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

MetricMiniMax M3Mistral Medium 3.5 128BComparison
Input / output priceUSD per 1M tokensMiniMax M3$0.3 input / $1.2 outputMistral Medium 3.5 128B$1.5 input / $7.5 outputMiniMax M3 has the lower combined listed price.
Generation speedtokens per secondMiniMax M3Not availableMistral Medium 3.5 128BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenMiniMax M3Not availableMistral Medium 3.5 128BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensMiniMax M31MMistral Medium 3.5 128B256KMiniMax M3 lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkMiniMax M3Mistral Medium 3.5 128BResult
Terminal-Bench 2.0Source 66%Not comparable
BrowseCompSource 83.5%Not comparable
OSWorld-VerifiedSource 70.1%Not comparable
MCP AtlasSource 74.2%Not comparable
Claw-EvalSource 74.5%Not comparable
AA Agentic IndexSource 35.4%19.0%MiniMax M3 leads
τ²-bench resultsSource 88.9%94.2%Mistral Medium 3.5 128B leads
GDPval-AASource 44.7%21.4%MiniMax M3 leads
GDPval-AASource 1395929MiniMax M3 leads
GDPval rubricsSource 74.7%Not comparable
BankerToolBenchSource 76.1%Not comparable
ResearchClawBenchSource 19.8%Not comparable
OSWorld 2.0Source 4.6%Not comparable
AA BriefcaseSource 1110Not comparable
AA EnterpriseOps-GymSource 32.1%33.7%Mistral Medium 3.5 128B leads
AA Harvey LABSource 6.7%0.8%MiniMax M3 leads
τ³-bench resultsSource 91.4%Not comparable
Gert LabsSource 39.10%Not comparable
AA Tau3 BankingSource 14.4%Not comparable
CodingMistral Medium 3.5 128B wins
BenchmarkMiniMax M3Mistral Medium 3.5 128BResult
SWE-bench VerifiedSource 80.5%77.6%MiniMax M3 leads
SWE-bench ProSource 59%Not comparable
Terminal-Bench 2.0Source 66.0%Not comparable
NL2RepoSource 42.1%Not comparable
AA Coding IndexSource 58.6%46.9%MiniMax M3 leads
Terminal-Bench HardSource 42.4%33.3%MiniMax M3 leads
AA-SciCodeSource 45.4%39.6%MiniMax M3 leads
VIBE V2Source 50.1%Not comparable
SVG-BenchSource 63.7%Not comparable
KernelBench HardSource 28.8%Not comparable
AA Terminal-Bench 2.1Source 65.2%Not comparable
Reasoning
BenchmarkMiniMax M3Mistral Medium 3.5 128BResult
AA-LCRSource 74.0%61.0%MiniMax M3 leads
CritPtSource 3.7%0.0%MiniMax M3 leads
Knowledge
BenchmarkMiniMax M3Mistral Medium 3.5 128BResult
Artificial Analysis Intelligence IndexSource 44.4%29.9%MiniMax M3 leads
AA-GPQA DiamondSource 92.9%74.8%MiniMax M3 leads
AA-HLESource 37.1%12.8%MiniMax M3 leads
AA-Omniscience IndexSource 1.4%-36.3%MiniMax M3 leads
AA-Omniscience AccuracySource 15.0%25.1%Mistral Medium 3.5 128B leads
AA-Omniscience Hallucination RateSource 16.1%82.0%MiniMax M3 leads
AA Openness IndexSource 33.3%33.3%Tie
Math
BenchmarkMiniMax M3Mistral Medium 3.5 128BResult
USAMO 2026Source 85.7%Not comparable
Multimodal
BenchmarkMiniMax M3Mistral Medium 3.5 128BResult
OfficeQA ProSource 45.1%Not comparable
OmniDocBench 1.5Source 91.6%Not comparable
MMMU-ProSource 78.1%Not comparable
VideoMMMUSource 84.6%Not comparable
Video-MME (with subtitle)Source 85.4%Not comparable
Design Arena WebsiteSource 1294Not comparable
AA-MMMU-ProSource 78.6%64.9%MiniMax M3 leads
Inst. Following
BenchmarkMiniMax M3Mistral Medium 3.5 128BResult
AA-IFBenchSource 82.9%68.8%MiniMax M3 leads
Frequently Asked Questions (2)

Which is better, MiniMax M3 or Mistral Medium 3.5 128B?

MiniMax M3 is ahead on BenchLM's provisional leaderboard, 70 to 61. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 80.5% and 77.6%.

Which is better for coding, MiniMax M3 or Mistral Medium 3.5 128B?

Mistral Medium 3.5 128B has the edge for coding in this comparison, averaging 77.6 versus 72.2. Inside this category, AA Coding Index is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 16, 2026

The AI models change fast. We track them for you.

A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.