Noometry

Model comparison

Claude Opus 4.5 vs MiniMax-M2.7

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 37.4 on the Noometry Index. MiniMax-M2.7 costs 19× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

Last verified . 25 shared benchmarks.

Claude Opus 4.5 Anthropic

50.5

Rank #39 Confirmed

MiniMax-M2.7 MiniMax

37.4

Rank #188 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Claude Opus 4.5 scores higher in 9 categories and MiniMax-M2.7 in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Opus 4.5 leads 42.5 to 19.0.
  • The biggest single-benchmark swing is ProofBench: 36% for Claude Opus 4.5 and 3% for MiniMax-M2.7.
  • MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $5 / $25 for Claude Opus 4.5.
  • MiniMax-M2.7 accepts more context: 205K tokens versus 200K.
  • MiniMax-M2.7 has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4.5MiniMax-M2.7
ProviderAnthropicMiniMax
Noometry Index50.537.4
Released2025-11-012026-03-18
WeightsProprietaryOpen
Context window200K205K
Max output64K131K
Input $ / M tokens$5$0.30
Output $ / M tokens$25$1.20
Results tracked6930

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

Category by category

Coding Claude Opus 4.5 leads

Claude Opus 4.5: 55.4 (#21), MiniMax-M2.7: 41.4 (#115)

BenchmarkClaude Opus 4.5MiniMax-M2.7
LMArena WebDev14931397
WeirdML63.7%37%
LMArena Coding15041454
ALE-Bench1,025599.25
SWE-bench Verified76.7%—
SWE-bench Verified (bash only)76.8%—
SWE-bench Multilingual70.7%—
SciCode—47%
GSO26.5%—
AlgoTune1.77—

Agentic & Tool Use Claude Opus 4.5 leads

Claude Opus 4.5: 47.2 (#11), MiniMax-M2.7: 24.9 (#103)

BenchmarkClaude Opus 4.5MiniMax-M2.7
Terminal-Bench63.1%45.1%
Berkeley Function Calling Leaderboard77.5%—
GDPval45.5%—
Remote Labor Index3.8%—
τ²-bench Airline84%—
τ²-bench Banking24.7%—
τ²-bench Retail79.6%—
τ²-bench Telecom92.3%—
Cybench82%—
DeepResearch Bench54.8%—
OSWorld66.3%—
BALROG43.5%—
ExploitBench—13.3%
GBAEval—0%
LMArena Search1180—
METR Time Horizons75%—
Vending-Bench 24,967—

Reasoning Claude Opus 4.5 leads

Claude Opus 4.5: 42.5 (#43), MiniMax-M2.7: 19.0 (#248)

BenchmarkClaude Opus 4.5MiniMax-M2.7
NYT Connections (extended)52.5%24.7%
LMArena Hard Prompts14761422
Epoch Capabilities Index150.1145.84
ARC-AGI-237.6%—
SimpleBench62%—
Kagi LLM Benchmark80.2%—
ARC-AGI-180%—
CritPt—0.6%
Chess Puzzles12%—
EnigmaEval11.9%—
Thematic Generalization—39.3%
EBR-Bench14.3%—
Mystery Game Puzzles22%—
DTBench89.9%—
LMCA44.5%—
ForecastBench60.7—

Math Claude Opus 4.5 leads

Claude Opus 4.5: 38.5 (#85), MiniMax-M2.7: 24.9 (#254)

BenchmarkClaude Opus 4.5MiniMax-M2.7
ProofBench36%3%
LMArena Math14631420
FrontierMath (Tiers 1-3)34.4%—
FrontierMath Tier 44.9%—
OTIS Mock AIME 2024-202586.1%—
FrontierMath (Feb 2025 set)20.7%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Claude Opus 4.5 leads

Claude Opus 4.5: 56.4 (#38), MiniMax-M2.7: 37.1 (#151)

BenchmarkClaude Opus 4.5MiniMax-M2.7
Vectara Hallucination Rate10.9%12.9%
LMArena Expert14881443
GPQA Diamond86%—
Humanity's Last Exam25.2%—
SimpleQA Verified45.7%—

Multimodal Not comparable

Claude Opus 4.5: 31.1 (#99), MiniMax-M2.7: —

BenchmarkClaude Opus 4.5MiniMax-M2.7
GeoBench75%—
VPCT40%—
Furniture Assembly28.3%—
LMArena Document1462—

Multilingual Claude Opus 4.5 leads

Claude Opus 4.5: 54.5 (#45), MiniMax-M2.7: 50.5 (#120)

BenchmarkClaude Opus 4.5MiniMax-M2.7
LMArena Non-English14381382
LMArena Chinese14701439
LMArena French14711422
LMArena German14491398
LMArena Japanese14151261
LMArena Korean14241313
LMArena Russian14481383
LMArena Spanish14551403

Instruction Following Claude Opus 4.5 leads

Claude Opus 4.5: 77.7 (#20), MiniMax-M2.7: 74.2 (#101)

BenchmarkClaude Opus 4.5MiniMax-M2.7
LMArena Instruction Following14781404

Long Context Claude Opus 4.5 leads

Claude Opus 4.5: 46.4 (#21), MiniMax-M2.7: 43.3 (#94)

BenchmarkClaude Opus 4.5MiniMax-M2.7
LMArena Longer Query14801419
CL-bench21.1%—

Writing & Preference Claude Opus 4.5 leads

Claude Opus 4.5: 68.2 (#28), MiniMax-M2.7: 59.1 (#107)

BenchmarkClaude Opus 4.5MiniMax-M2.7
LMArena Text14511404
LMArena Creative Writing14451354
LMArena Multi-Turn14661413
EQ-Bench Creative Writing1687—

Frequently asked questions

Is Claude Opus 4.5 better than MiniMax-M2.7?

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 37.4 on the Noometry Index. MiniMax-M2.7 costs 19× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.5 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 Opus 4.5 lists at $5 and $25.

Is Claude Opus 4.5 or MiniMax-M2.7 better for coding?

Claude Opus 4.5 scores higher on coding benchmarks: 55.4 versus 41.4 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M2.7 does, with 205K tokens against 200K.

How many benchmarks do Claude Opus 4.5 and MiniMax-M2.7 share?

25 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and MiniMax-M2.7 has 30.

Related comparisons

Go deeper