Noometry

Model comparison

Claude Sonnet 4.5 vs MiniMax-M3

Claude Sonnet 4.5 and MiniMax-M3 score almost the same on the Noometry Index (44.1 vs 43.8), so choose on price, context window or the category you care about most.

Last verified . 34 shared benchmarks.

Claude Sonnet 4.5 Anthropic

44.1

Rank #81 Confirmed

MiniMax-M3 MiniMax

43.8

Rank #85 Confirmed

Summary

  • They share 34 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 5 categories and MiniMax-M3 in 5 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in agentic & tool use, where Claude Sonnet 4.5 leads 38.3 to 22.6.
  • The biggest single-benchmark swing is NYT Connections (extended): 37.3% for Claude Sonnet 4.5 and 65.1% for MiniMax-M3.
  • MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
  • MiniMax-M3 accepts more context: 1M tokens versus 200K.
  • MiniMax-M3 has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4.5MiniMax-M3
ProviderAnthropicMiniMax
Noometry Index44.143.8
Released2025-09-292026-06-01
WeightsProprietaryOpen
Context window200K1M
Max output64K512K
Input $ / M tokens$3$0.30
Output $ / M tokens$15$1.20
Results tracked7341

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 47.3 (#61), MiniMax-M3: 41.8 (#118)

BenchmarkClaude Sonnet 4.5MiniMax-M3
LMArena WebDev13931482
SciCode44.7%47.1%
LMArena Coding14891469
ALE-Bench796.15640.02
SWE-bench Verified71.3%—
FrontierCode—14.7%
SWE-bench Verified (bash only)71.4%—
SWE-bench Multilingual67%—
GSO14.7%—
WeirdML47.7%—
AlgoTune1.52—

Agentic & Tool Use Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 38.3 (#32), MiniMax-M3: 22.6 (#130)

BenchmarkClaude Sonnet 4.5MiniMax-M3
Vending-Bench 23,8392,158
Terminal-Bench46.5%—
APEX-Agents—37.7%
Berkeley Function Calling Leaderboard73.2%—
OSWorld 2.0—4.6%
GDPval42.5%—
Remote Labor Index2.1%—
τ²-bench Airline72%—
τ²-bench Banking25.3%—
τ²-bench Retail72.4%—
τ²-bench Telecom84.9%—
Cybench60%—
DeepResearch Bench52.6%—
OSWorld62.9%—
GBAEval—0.9%
LMArena Search1159—
METR Time Horizons67.4%—

Reasoning MiniMax-M3 leads

Claude Sonnet 4.5: 26.9 (#125), MiniMax-M3: 30.1 (#87)

BenchmarkClaude Sonnet 4.5MiniMax-M3
SimpleBench54.3%45.8%
NYT Connections (extended)37.3%65.1%
CritPt1.1%3.7%
Chess Puzzles12%14%
LMArena Hard Prompts14621447
Mystery Game Puzzles17%8%
DTBench83.2%78.9%
LMCA38.8%33.7%
Epoch Capabilities Index146.84146.95
ForecastBench61.961.4
ARC-AGI-213.6%—
Kagi LLM Benchmark57.9%—
ARC-AGI-163.7%—
EnigmaEval6%—
EBR-Bench2.4%—
Surface Evolver Bench—55%

Math MiniMax-M3 leads

Claude Sonnet 4.5: 32.3 (#216), MiniMax-M3: 40.0 (#95)

BenchmarkClaude Sonnet 4.5MiniMax-M3
OTIS Mock AIME 2024-202577.8%71.1%
ProofBench19%18%
LMArena Math14491429
FrontierMath (Tiers 1-3)23.9%—
FrontierMath Tier 42.4%—
Omni-MATH55.3%—
MATH Level 597.7%—
FrontierMath (Feb 2025 set)15.2%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge MiniMax-M3 leads

Claude Sonnet 4.5: 48.4 (#76), MiniMax-M3: 58.4 (#35)

BenchmarkClaude Sonnet 4.5MiniMax-M3
GPQA Diamond82.3%90.9%
LMArena Expert14821461
Humanity's Last Exam13.7%—
SimpleQA Verified30.7%—
MMLU-Pro86.9%—
Vectara Hallucination Rate12%—
GPQA (HELM)68.6%—

Multimodal MiniMax-M3 leads

Claude Sonnet 4.5: 34.8 (#89), MiniMax-M3: 40.2 (#51)

BenchmarkClaude Sonnet 4.5MiniMax-M3
LMArena Document14501435
LMArena Vision—1253
VPCT39.8%—

Multilingual Too close to call

Claude Sonnet 4.5: 53.4 (#69), MiniMax-M3: 53.0 (#75)

BenchmarkClaude Sonnet 4.5MiniMax-M3
LMArena Non-English14251420
LMArena Chinese14591463
LMArena French14581447
LMArena German14271426
LMArena Japanese13901381
LMArena Korean14031372
LMArena Russian14371428
LMArena Spanish14571432

Instruction Following Too close to call

Claude Sonnet 4.5: 75.0 (#78), MiniMax-M3: 75.5 (#62)

BenchmarkClaude Sonnet 4.5MiniMax-M3
LMArena Instruction Following14591433
IFEval85%—

Long Context Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 45.2 (#46), MiniMax-M3: 44.2 (#72)

BenchmarkClaude Sonnet 4.5MiniMax-M3
LMArena Longer Query14761445

Writing & Preference Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 66.5 (#34), MiniMax-M3: 62.1 (#83)

BenchmarkClaude Sonnet 4.5MiniMax-M3
LMArena Text14391433
LMArena Creative Writing14421404
LMArena Multi-Turn14651442
EQ-Bench Creative Writing1678—
WildBench85.4%—
EQ-Bench 4—1150

Frequently asked questions

Is Claude Sonnet 4.5 better than MiniMax-M3?

Claude Sonnet 4.5 and MiniMax-M3 score almost the same on the Noometry Index (44.1 vs 43.8), so choose on price, context window or the category you care about most.

Which is cheaper, Claude Sonnet 4.5 or MiniMax-M3?

MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

Is Claude Sonnet 4.5 or MiniMax-M3 better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 41.8 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M3 does, with 1M tokens against 200K.

How many benchmarks do Claude Sonnet 4.5 and MiniMax-M3 share?

34 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and MiniMax-M3 has 41.

Related comparisons

Go deeper