Noometry

Model comparison

Claude Sonnet 5 vs MiniMax-M2.7

Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 37.7 on the Noometry Index. MiniMax-M2.7 costs 7.6× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.

Last verified . 26 shared benchmarks.

Claude Sonnet 5 Anthropic

54.6

Rank #29 Confirmed

MiniMax-M2.7 MiniMax

37.7

Rank #196 Confirmed

Summary

  • They share 26 benchmarks with published results for both. Claude Sonnet 5 scores higher in 9 categories and MiniMax-M2.7 in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Sonnet 5 leads 66.2 to 25.9.
  • The biggest single-benchmark swing is ProofBench: 77% for Claude Sonnet 5 and 3% for MiniMax-M2.7.
  • MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
  • Claude Sonnet 5 accepts more context: 1M tokens versus 205K.
  • MiniMax-M2.7 has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 5MiniMax-M2.7
ProviderAnthropicMiniMax
Noometry Index54.637.7
Released2026-06-292026-03-18
WeightsProprietaryOpen
Context window1M205K
Max output128K131K
Input $ / M tokens$2$0.30
Output $ / M tokens$10$1.20
Results tracked5130

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

Category by category

Coding Claude Sonnet 5 leads

Claude Sonnet 5: 55.5 (#26), MiniMax-M2.7: 41.8 (#120)

BenchmarkClaude Sonnet 5MiniMax-M2.7
LMArena WebDev15411398
SciCode54.3%47%
WeirdML68.8%37%
LMArena Coding14831454
ALE-Bench1,463599.25
DeepSWE53.8%—
FrontierCode42.7%—
CursorBench34.1%—
GSO37.3%—

Agentic & Tool Use Claude Sonnet 5 leads

Claude Sonnet 5: 42.8 (#18), MiniMax-M2.7: 25.1 (#111)

BenchmarkClaude Sonnet 5MiniMax-M2.7
GBAEval65.3%0%
Terminal-Bench—45.1%
APEX-Agents54.5%—
ExploitBench—13.3%
LMArena Search1194—
Vending-Bench 26,378—

Reasoning Claude Sonnet 5 leads

Claude Sonnet 5: 49.1 (#39), MiniMax-M2.7: 19.7 (#253)

BenchmarkClaude Sonnet 5MiniMax-M2.7
NYT Connections (extended)75.1%24.7%
CritPt16.9%0.6%
LMArena Hard Prompts14611422
Epoch Capabilities Index156.21145.85
SimpleBench60.6%—
Chess Puzzles35%—
Thematic Generalization—39.3%
Mystery Game Puzzles35%—
DTBench92.5%—
LMCA50%—
Surface Evolver Bench60%—
Bench to the Future 30.14—
ForecastBench61.1—

Math Claude Sonnet 5 leads

Claude Sonnet 5: 66.2 (#27), MiniMax-M2.7: 25.9 (#263)

BenchmarkClaude Sonnet 5MiniMax-M2.7
ProofBench77%3%
LMArena Math14671420
FrontierMath (Tiers 1-3)65.6%—
FrontierMath Tier 429.3%—
OTIS Mock AIME 2024-202594.7%—

Knowledge Claude Sonnet 5 leads

Claude Sonnet 5: 55.6 (#47), MiniMax-M2.7: 37.7 (#152)

BenchmarkClaude Sonnet 5MiniMax-M2.7
LMArena Expert14901444
GPQA Diamond90.5%—
SimpleQA Verified33.7%—
Vectara Hallucination Rate—12.9%

Multimodal Not comparable

Claude Sonnet 5: 42.4 (#31), MiniMax-M2.7: —

BenchmarkClaude Sonnet 5MiniMax-M2.7
LMArena Vision1274—
Blueprint-Bench 224.9%—
LMArena Document1466—

Multilingual Claude Sonnet 5 leads

Claude Sonnet 5: 53.8 (#55), MiniMax-M2.7: 50.3 (#123)

BenchmarkClaude Sonnet 5MiniMax-M2.7
LMArena Non-English14311382
LMArena Chinese14771441
LMArena French14601421
LMArena German14401398
LMArena Japanese14221262
LMArena Korean14111313
LMArena Russian14511383
LMArena Spanish14371403

Instruction Following Claude Sonnet 5 leads

Claude Sonnet 5: 76.3 (#41), MiniMax-M2.7: 74.1 (#103)

BenchmarkClaude Sonnet 5MiniMax-M2.7
LMArena Instruction Following14521405

Long Context Claude Sonnet 5 leads

Claude Sonnet 5: 44.8 (#55), MiniMax-M2.7: 43.3 (#99)

BenchmarkClaude Sonnet 5MiniMax-M2.7
LMArena Longer Query14631419

Writing & Preference Claude Sonnet 5 leads

Claude Sonnet 5: 69.2 (#25), MiniMax-M2.7: 58.9 (#112)

BenchmarkClaude Sonnet 5MiniMax-M2.7
LMArena Text14421405
LMArena Creative Writing14161354
LMArena Multi-Turn14541412
EQ-Bench Creative Writing1794—
EQ-Bench 41236—

Frequently asked questions

Is Claude Sonnet 5 better than MiniMax-M2.7?

Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 37.7 on the Noometry Index. MiniMax-M2.7 costs 7.6× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.

Which is cheaper, Claude Sonnet 5 or MiniMax-M2.7?

MiniMax-M2.7 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Claude Sonnet 5 lists at $2 and $10.

Is Claude Sonnet 5 or MiniMax-M2.7 better for coding?

Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 41.8 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 5 does, with 1M tokens against 205K.

How many benchmarks do Claude Sonnet 5 and MiniMax-M2.7 share?

26 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and MiniMax-M2.7 has 30.

Related comparisons

Go deeper