Skip to main content

Model comparison

MiniMax M3 vs ZAYA1-74B-Preview

Data verified

Head-to-head evidence from 1 shared benchmark result across 1 category. Overall scores shown here use the public BenchAlign v5 ranking lane.

MiniMax
69.8/100
Margin
14.8pts
← winning
55/100
2 category wins0 category wins

Verified leaderboard positions: MiniMax M3 #18; ZAYA1-74B-Preview unranked

BenchAlign evidence: MiniMax M3 supported; ZAYA1-74B-Preview not scored. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. MiniMax M3 and ZAYA1-74B-Preview share 1 comparable benchmark result. 2 of 8 categories are comparable. 44 results are unique to MiniMax M3; 6 to ZAYA1-74B-Preview.

Updated July 16, 2026
Shared results
1
MiniMax M3 only
44
ZAYA1-74B-Preview only
6
Comparable categories
2 / 8

Pick MiniMax M3 if you want the stronger benchmark profile. ZAYA1-74B-Preview only becomes the better choice if you want the cheaper token bill or you want the stronger reasoning-first profile.

Confidence note. This is a partial-evidence comparison with 1 shared benchmark result across 1 evidence category; 2 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 55. 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 coding, where it averages 72.2 against 53.2. The single biggest benchmark swing on the page is SWE-bench Verified, 80.5% to 53.2%.

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 ZAYA1-74B-Preview. That is roughly Infinityx on output cost alone. ZAYA1-74B-Preview 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 ZAYA1-74B-Preview.

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 ZAYA1-74B-Preview
CategoryMiniMax M3ΔZAYA1-74B-Preview
CodingMiniMax M372.2Margin 19.0ZAYA1-74B-Preview53.2
MathMiniMax M385.7Margin 9.3ZAYA1-74B-Preview76.4
AgenticMiniMax M372.3MarginNo overlapZAYA1-74B-PreviewNot measured
KnowledgeMiniMax M3Not measuredMarginNo overlapZAYA1-74B-Preview66.1
MultimodalMiniMax M364.9MarginNo overlapZAYA1-74B-PreviewNot measured

Decisive benchmark drivers

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

More
A · MiniMax M3B · ZAYA1-74B-Preview
  1. SWE-bench Verified

    Coding
    Source ↗
    A 80.5%B 53.2%
    Winner: MiniMax M3Δ 27.3
    SWE-bench Verified: MiniMax M3 scored 80.5%; ZAYA1-74B-Preview scored 53.2%. MiniMax M3 wins this benchmark.

Operational comparison

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

MetricMiniMax M3ZAYA1-74B-PreviewComparison
Input / output priceUSD per 1M tokensMiniMax M3$0.3 input / $1.2 outputZAYA1-74B-Preview$0 input / $0 outputZAYA1-74B-Preview has the lower combined listed price.
Generation speedtokens per secondMiniMax M3Not availableZAYA1-74B-PreviewNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenMiniMax M3Not availableZAYA1-74B-PreviewNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensMiniMax M31MZAYA1-74B-Preview256KMiniMax M3 lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkMiniMax M3ZAYA1-74B-PreviewResult
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%Not comparable
τ²-bench resultsSource 88.9%Not comparable
GDPval-AASource 44.7%Not comparable
GDPval-AASource 1395Not comparable
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
τ²-bench AirlineSource 56.1%Not comparable
CodingMiniMax M3 wins
BenchmarkMiniMax M3ZAYA1-74B-PreviewResult
SWE-bench VerifiedSource 80.5%53.2%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%Not comparable
Terminal-Bench HardSource 42.4%Not comparable
AA-SciCodeSource 45.4%Not comparable
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
LiveCodeBench v6Source 65.7%Not comparable
Reasoning
BenchmarkMiniMax M3ZAYA1-74B-PreviewResult
AA-LCRSource 74.0%Not comparable
CritPtSource 3.7%Not comparable
Knowledge
BenchmarkMiniMax M3ZAYA1-74B-PreviewResult
Artificial Analysis Intelligence IndexSource 44.4%Not comparable
AA-GPQA DiamondSource 92.9%Not comparable
AA-HLESource 37.1%Not comparable
AA-Omniscience IndexSource 1.4%Not comparable
AA-Omniscience AccuracySource 15.0%Not comparable
AA-Omniscience Hallucination RateSource 16.1%Not comparable
AA Openness IndexSource 33.3%Not comparable
MMLU-ProSource 68.1%Not comparable
GPQASource 57.3%Not comparable
GPQA-DSource 57.3%Not comparable
MathMiniMax M3 wins
BenchmarkMiniMax M3ZAYA1-74B-PreviewResult
USAMO 2026Source 85.7%Not comparable
AIME26Source 76.4%Not comparable
Multimodal
BenchmarkMiniMax M3ZAYA1-74B-PreviewResult
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%Not comparable
Inst. Following
BenchmarkMiniMax M3ZAYA1-74B-PreviewResult
AA-IFBenchSource 82.9%Not comparable
Frequently Asked Questions (3)

Which is better, MiniMax M3 or ZAYA1-74B-Preview?

MiniMax M3 is ahead on BenchLM's provisional leaderboard, 70 to 55. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 80.5% and 53.2%.

Which is better for coding, MiniMax M3 or ZAYA1-74B-Preview?

MiniMax M3 has the edge for coding in this comparison, averaging 72.2 versus 53.2. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.

Which is better for math, MiniMax M3 or ZAYA1-74B-Preview?

MiniMax M3 has the edge for math in this comparison, averaging 85.7 versus 76.4. ZAYA1-74B-Preview stays close enough that the answer can still flip depending on your workload.

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.