Skip to main content

Model comparison

MiniMax M3 vs Qwen3.5-122B-A10B

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
9.3pts
← winning
60.5/100
2 category wins1 category wins

Verified leaderboard positions: MiniMax M3 #18; Qwen3.5-122B-A10B #25

BenchAlign evidence: MiniMax M3 supported; Qwen3.5-122B-A10B supported. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. MiniMax M3 and Qwen3.5-122B-A10B share 21 comparable benchmark results. 3 of 8 categories are comparable. 24 results are unique to MiniMax M3; 11 to Qwen3.5-122B-A10B.

Updated July 16, 2026
Shared results
21
MiniMax M3 only
24
Qwen3.5-122B-A10B only
11
Comparable categories
3 / 8

Pick MiniMax M3 if you want the stronger benchmark profile. Qwen3.5-122B-A10B only becomes the better choice if multimodal & grounded is the priority or you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 21 shared benchmark results across 6 evidence categories; 3 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 59. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

MiniMax M3's sharpest advantage is in agentic, where it averages 72.3 against 56.4. The single biggest benchmark swing on the page is BrowseComp, 83.5% to 63.8%. Qwen3.5-122B-A10B does hit back in multimodal & grounded, so the answer changes if that is the part of the workload you care about most.

MiniMax M3 is also the more expensive model on tokens at $0.30 input / $1.20 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Qwen3.5-122B-A10B. That is roughly Infinityx on output cost alone. Qwen3.5-122B-A10B 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 262K for Qwen3.5-122B-A10B.

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 Qwen3.5-122B-A10B
CategoryMiniMax M3ΔQwen3.5-122B-A10B
AgenticMiniMax M372.3Margin 15.9Qwen3.5-122B-A10B56.4
MultimodalMiniMax M364.9Margin 12.3Qwen3.5-122B-A10B77.2
CodingMiniMax M372.2Margin 0.2Qwen3.5-122B-A10B72.0
ReasoningMiniMax M3Not measuredMarginNo overlapQwen3.5-122B-A10B60.2
KnowledgeMiniMax M3Not measuredMarginNo overlapQwen3.5-122B-A10B83.6
MathMiniMax M385.7MarginNo overlapQwen3.5-122B-A10BNot measured
MultilingualMiniMax M3Not measuredMarginNo overlapQwen3.5-122B-A10B82.2
Inst. FollowingMiniMax M3Not measuredMarginNo overlapQwen3.5-122B-A10B93.4

Decisive benchmark drivers

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

More
A · MiniMax M3B · Qwen3.5-122B-A10B
  1. BrowseComp

    Agentic
    Source ↗
    A 83.5%B 63.8%
    Winner: MiniMax M3Δ 19.7
    BrowseComp: MiniMax M3 scored 83.5%; Qwen3.5-122B-A10B scored 63.8%. MiniMax M3 wins this benchmark.
  2. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 66%B 49.4%
    Winner: MiniMax M3Δ 16.6
    Terminal-Bench 2.0: MiniMax M3 scored 66%; Qwen3.5-122B-A10B scored 49.4%. MiniMax M3 wins this benchmark.
  3. OSWorld-Verified

    Agentic
    Source ↗
    A 70.1%B 58%
    Winner: MiniMax M3Δ 12.1
    OSWorld-Verified: MiniMax M3 scored 70.1%; Qwen3.5-122B-A10B scored 58%. MiniMax M3 wins this benchmark.
  4. SWE-bench Verified

    Coding
    Source ↗
    A 80.5%B 72%
    Winner: MiniMax M3Δ 8.5
    SWE-bench Verified: MiniMax M3 scored 80.5%; Qwen3.5-122B-A10B scored 72%. MiniMax M3 wins this benchmark.

Operational comparison

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

MetricMiniMax M3Qwen3.5-122B-A10BComparison
Input / output priceUSD per 1M tokensMiniMax M3$0.3 input / $1.2 outputQwen3.5-122B-A10B$0 input / $0 outputQwen3.5-122B-A10B has the lower combined listed price.
Generation speedtokens per secondMiniMax M3Not availableQwen3.5-122B-A10BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenMiniMax M3Not availableQwen3.5-122B-A10BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensMiniMax M31MQwen3.5-122B-A10B262KMiniMax M3 lists the larger context window.

Benchmark Deep Dive

AgenticMiniMax M3 wins
BenchmarkMiniMax M3Qwen3.5-122B-A10BResult
Terminal-Bench 2.0Source 66%49.4%MiniMax M3 leads
BrowseCompSource 83.5%63.8%MiniMax M3 leads
OSWorld-VerifiedSource 70.1%58%MiniMax M3 leads
MCP AtlasSource 74.2%Not comparable
Claw-EvalSource 74.5%Not comparable
AA Agentic IndexSource 35.4%20.7%MiniMax M3 leads
τ²-bench resultsSource 88.9%93.6%Qwen3.5-122B-A10B leads
GDPval-AASource 44.7%23.9%MiniMax M3 leads
GDPval-AASource 1395978MiniMax 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%Not comparable
AA Harvey LABSource 6.7%Not comparable
CodingMiniMax M3 wins
BenchmarkMiniMax M3Qwen3.5-122B-A10BResult
SWE-bench VerifiedSource 80.5%72%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%45.7%MiniMax M3 leads
Terminal-Bench HardSource 42.4%31.1%MiniMax M3 leads
AA-SciCodeSource 45.4%42.0%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 M3Qwen3.5-122B-A10BResult
AA-LCRSource 74.0%66.7%MiniMax M3 leads
CritPtSource 3.7%0.6%MiniMax M3 leads
LongBench v2Source 60.2%Not comparable
Knowledge
BenchmarkMiniMax M3Qwen3.5-122B-A10BResult
Artificial Analysis Intelligence IndexSource 44.4%32.3%MiniMax M3 leads
AA-GPQA DiamondSource 92.9%85.7%MiniMax M3 leads
AA-HLESource 37.1%23.4%MiniMax M3 leads
AA-Omniscience IndexSource 1.4%-39.6%MiniMax M3 leads
AA-Omniscience AccuracySource 15.0%24.7%Qwen3.5-122B-A10B leads
AA-Omniscience Hallucination RateSource 16.1%85.5%MiniMax M3 leads
AA Openness IndexSource 33.3%Not comparable
MMLU-ProSource 86.7%Not comparable
SuperGPQASource 67.1%Not comparable
GPQASource 86.6%Not comparable
Math
BenchmarkMiniMax M3Qwen3.5-122B-A10BResult
USAMO 2026Source 85.7%Not comparable
Multilingual
BenchmarkMiniMax M3Qwen3.5-122B-A10BResult
MMLU-ProXSource 82.2%Not comparable
MultimodalQwen3.5-122B-A10B wins
BenchmarkMiniMax M3Qwen3.5-122B-A10BResult
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%75.0%MiniMax M3 leads
MMMUSource 83.9%Not comparable
MMVUSource 74.7%Not comparable
MathVisionSource 86.2%Not comparable
CharXivSource 77.2%Not comparable
V*Source 93.2%Not comparable
Inst. Following
BenchmarkMiniMax M3Qwen3.5-122B-A10BResult
AA-IFBenchSource 82.9%75.7%MiniMax M3 leads
IFEvalSource 93.4%Not comparable
Frequently Asked Questions (4)

Which is better, MiniMax M3 or Qwen3.5-122B-A10B?

MiniMax M3 is ahead on BenchLM's provisional leaderboard, 70 to 59. The biggest single separator in this matchup is BrowseComp, where the scores are 83.5% and 63.8%.

Which is better for coding, MiniMax M3 or Qwen3.5-122B-A10B?

MiniMax M3 has the edge for coding in this comparison, averaging 72.2 versus 72. Inside this category, AA Coding Index is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, MiniMax M3 or Qwen3.5-122B-A10B?

MiniMax M3 has the edge for agentic tasks in this comparison, averaging 72.3 versus 56.4. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, MiniMax M3 or Qwen3.5-122B-A10B?

Qwen3.5-122B-A10B has the edge for multimodal and grounded tasks in this comparison, averaging 77.2 versus 64.9. Inside this category, AA-MMMU-Pro 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.