Noometry

Model comparison

Claude Opus 5 vs MiniMax-M2.7

Claude Opus 5 is the stronger model overall, scoring 67.8 to 37.7 on the Noometry Index. MiniMax-M2.7 costs 19× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.

Last verified . 26 shared benchmarks.

Claude Opus 5 Anthropic

67.8

Rank #4 Confirmed

MiniMax-M2.7 MiniMax

37.7

Rank #196 Confirmed

Summary

  • They share 26 benchmarks with published results for both. Claude Opus 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 Opus 5 leads 86.2 to 25.9.
  • The biggest single-benchmark swing is ProofBench: 99% for Claude Opus 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 5.
  • Claude Opus 5 accepts more context: 1M tokens versus 205K.
  • MiniMax-M2.7 has downloadable open weights; the other is API-only.

Side by side

Claude Opus 5MiniMax-M2.7
ProviderAnthropicMiniMax
Noometry Index67.837.7
Released2026-07-242026-03-18
WeightsProprietaryOpen
Context window1M205K
Max output128K131K
Input $ / M tokens$5$0.30
Output $ / M tokens$25$1.20
Results tracked5730

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

Category by category

Coding Claude Opus 5 leads

Claude Opus 5: 67.5 (#5), MiniMax-M2.7: 41.8 (#120)

BenchmarkClaude Opus 5MiniMax-M2.7
LMArena WebDev16911398
SciCode56.4%47%
WeirdML91.8%37%
LMArena Coding15341454
ALE-Bench2,165599.25
DeepSWE73.6%—
FrontierCode53.4%—
CursorBench46.6%—
FrontierSWE52%—

Agentic & Tool Use Claude Opus 5 leads

Claude Opus 5: 55.6 (#1), MiniMax-M2.7: 25.1 (#111)

BenchmarkClaude Opus 5MiniMax-M2.7
GBAEval79.6%0%
Terminal-Bench—45.1%
APEX-Agents65.8%—
OSWorld 2.031.4%—
τ²-bench Banking48.7%—
PostTrainBench35%—
BALROG63.4%—
ExploitBench—13.3%
GDP.pdf24%—
Vending-Bench 211,182—

Reasoning Claude Opus 5 leads

Claude Opus 5: 77.2 (#4), MiniMax-M2.7: 19.7 (#253)

BenchmarkClaude Opus 5MiniMax-M2.7
NYT Connections (extended)94.3%24.7%
CritPt29.1%0.6%
LMArena Hard Prompts15261422
Epoch Capabilities Index162.78145.85
ARC-AGI-290.4%—
SimpleBench80.6%—
ARC-AGI-197.5%—
Chess Puzzles42%—
Thematic Generalization—39.3%
EBR-Bench45.7%—
Mystery Game Puzzles59%—
DTBench97.9%—
LMCA64.5%—
Bench to the Future 30.12—

Math Claude Opus 5 leads

Claude Opus 5: 86.2 (#8), MiniMax-M2.7: 25.9 (#263)

BenchmarkClaude Opus 5MiniMax-M2.7
ProofBench99%3%
LMArena Math15311420
FrontierMath (Tiers 1-3)85.6%—
FrontierMath Tier 473.2%—
OTIS Mock AIME 2024-202598.9%—

Knowledge Claude Opus 5 leads

Claude Opus 5: 66.8 (#9), MiniMax-M2.7: 37.7 (#152)

BenchmarkClaude Opus 5MiniMax-M2.7
LMArena Expert15571444
GPQA Diamond93.9%—
SimpleQA Verified59.9%—
Vectara Hallucination Rate—12.9%

Multimodal Not comparable

Claude Opus 5: 50.8 (#8), MiniMax-M2.7: —

BenchmarkClaude Opus 5MiniMax-M2.7
LMArena Vision1319—
Blueprint-Bench 230.4%—
Furniture Assembly60.8%—
LMArena Document1516—

Multilingual Claude Opus 5 leads

Claude Opus 5: 58.8 (#4), MiniMax-M2.7: 50.3 (#123)

BenchmarkClaude Opus 5MiniMax-M2.7
LMArena Non-English15011382
LMArena Chinese15741441
LMArena French15191421
LMArena German15241398
LMArena Japanese15161262
LMArena Korean15211313
LMArena Russian15071383
LMArena Spanish15191403

Instruction Following Claude Opus 5 leads

Claude Opus 5: 79.2 (#7), MiniMax-M2.7: 74.1 (#103)

BenchmarkClaude Opus 5MiniMax-M2.7
LMArena Instruction Following15171405

Long Context Claude Opus 5 leads

Claude Opus 5: 46.5 (#21), MiniMax-M2.7: 43.3 (#99)

BenchmarkClaude Opus 5MiniMax-M2.7
LMArena Longer Query15151419

Writing & Preference Claude Opus 5 leads

Claude Opus 5: 79.2 (#1), MiniMax-M2.7: 58.9 (#112)

BenchmarkClaude Opus 5MiniMax-M2.7
LMArena Text15071405
LMArena Creative Writing14911354
LMArena Multi-Turn14991412
EQ-Bench Creative Writing2133—
EQ-Bench 41385—

Frequently asked questions

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

Claude Opus 5 is the stronger model overall, scoring 67.8 to 37.7 on the Noometry Index. MiniMax-M2.7 costs 19× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.

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

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

Claude Opus 5 scores higher on coding benchmarks: 67.5 versus 41.8 in the Noometry coding category.

Which has the bigger context window?

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

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

26 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and MiniMax-M2.7 has 30.

Related comparisons

Go deeper