Noometry

Model comparison

Claude Opus 4.7 vs MiniMax-M2.5

Claude Opus 4.7 is the stronger model overall, scoring 58.4 to 38.1 on the Noometry Index. MiniMax-M2.5 costs 19× less per token, which makes it the better buy when Claude Opus 4.7's lead doesn't matter for your workload.

Last verified . 29 shared benchmarks.

Claude Opus 4.7 Anthropic

58.4

Rank #17 Confirmed

MiniMax-M2.5 MiniMax

38.1

Rank #181 Confirmed

Summary

  • They share 29 benchmarks with published results for both. Claude Opus 4.7 scores higher in 9 categories and MiniMax-M2.5 in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Opus 4.7 leads 66.5 to 25.8.
  • The biggest single-benchmark swing is ARC-AGI-2: 75.8% for Claude Opus 4.7 and 4.9% for MiniMax-M2.5.
  • MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $5 / $25 for Claude Opus 4.7.
  • Claude Opus 4.7 accepts more context: 1M tokens versus 205K.
  • MiniMax-M2.5 has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4.7MiniMax-M2.5
ProviderAnthropicMiniMax
Noometry Index58.438.1
Released2026-04-142026-02-12
WeightsProprietaryOpen
Context window1M205K
Max output128K131K
Input $ / M tokens$5$0.30
Output $ / M tokens$25$1.20
Results tracked6633

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

Category by category

Coding Claude Opus 4.7 leads

Claude Opus 4.7: 59.9 (#10), MiniMax-M2.5: 47.9 (#53)

BenchmarkClaude Opus 4.7MiniMax-M2.5
LMArena WebDev15571386
LMArena Coding15191380
ALE-Bench1,323618.17
SWE-bench Verified83.5%—
FrontierCode38.5%—
SWE-bench Verified (bash only)—75.8%
SWE-bench Multilingual—68.3%
SciCode54.5%—
GSO44.1%—
WeirdML76.4%—
MirrorCode31.1%—

Agentic & Tool Use Claude Opus 4.7 leads

Claude Opus 4.7: 47.9 (#8), MiniMax-M2.5: 30.2 (#70)

BenchmarkClaude Opus 4.7MiniMax-M2.5
Terminal-Bench80.2%42.7%
Vending-Bench 210,937-23.16
APEX-Agents49.2%—
OSWorld 2.018.2%—
τ²-bench Banking40.2%—
PostTrainBench28.6%—
ExploitBench26.5%—
GBAEval43.8%—
GDP.pdf21%—
LMArena Search1233—

Reasoning Claude Opus 4.7 leads

Claude Opus 4.7: 53.7 (#24), MiniMax-M2.5: 17.6 (#281)

BenchmarkClaude Opus 4.7MiniMax-M2.5
ARC-AGI-275.8%4.9%
Kagi LLM Benchmark80.7%55.2%
NYT Connections (extended)39%16.8%
ARC-AGI-193.5%63.7%
LMArena Hard Prompts15071372
Epoch Capabilities Index156.39146.68
SimpleBench61.7%—
CritPt12%—
Chess Puzzles30%—
Thematic Generalization72.8%—
EBR-Bench19%—
Mystery Game Puzzles28%—
DTBench94.7%—
LMCA52.2%—
ForecastBench60.3—

Math Claude Opus 4.7 leads

Claude Opus 4.7: 66.5 (#20), MiniMax-M2.5: 25.8 (#242)

BenchmarkClaude Opus 4.7MiniMax-M2.5
ProofBench54%4%
LMArena Math14991378
FrontierMath (Tiers 1-3)70.2%—
FrontierMath Tier 431.7%—
MathArena Final-Answer Competitions73.6%—
OTIS Mock AIME 2024-202597.8%—
FrontierMath (Feb 2025 set)43.8%—
FrontierMath Tier 4 (v1)22.9%—

Knowledge Claude Opus 4.7 leads

Claude Opus 4.7: 62.6 (#20), MiniMax-M2.5: 38.6 (#132)

BenchmarkClaude Opus 4.7MiniMax-M2.5
Vectara Hallucination Rate12%9.1%
LMArena Expert15211378
GPQA Diamond90.2%—
Humanity's Last Exam36.2%—
SimpleQA Verified51.7%—

Multimodal Not comparable

Claude Opus 4.7: 41.5 (#29), MiniMax-M2.5: —

BenchmarkClaude Opus 4.7MiniMax-M2.5
LMArena Vision1317—
Blueprint-Bench 224.5%—
Furniture Assembly33.3%—
LMArena Document1495—

Multilingual Claude Opus 4.7 leads

Claude Opus 4.7: 57.5 (#9), MiniMax-M2.5: 47.3 (#147)

BenchmarkClaude Opus 4.7MiniMax-M2.5
LMArena Non-English14811338
LMArena Chinese15301392
LMArena French15051363
LMArena German14941361
LMArena Japanese14721169
LMArena Korean14661232
LMArena Russian14941359
LMArena Spanish14971354

Instruction Following Claude Opus 4.7 leads

Claude Opus 4.7: 78.6 (#9), MiniMax-M2.5: 71.7 (#143)

BenchmarkClaude Opus 4.7MiniMax-M2.5
LMArena Instruction Following14981353

Long Context Claude Opus 4.7 leads

Claude Opus 4.7: 46.1 (#24), MiniMax-M2.5: 37.4 (#211)

BenchmarkClaude Opus 4.7MiniMax-M2.5
LMArena Longer Query15051367
CL-bench—11.4%
CL-bench Life—6.3%

Writing & Preference Claude Opus 4.7 leads

Claude Opus 4.7: 75.3 (#8), MiniMax-M2.5: 54.1 (#149)

BenchmarkClaude Opus 4.7MiniMax-M2.5
LMArena Text14911359
LMArena Creative Writing14861331
EQ-Bench Creative Writing19141361
LMArena Multi-Turn15061364
EQ-Bench 41311—

Frequently asked questions

Is Claude Opus 4.7 better than MiniMax-M2.5?

Claude Opus 4.7 is the stronger model overall, scoring 58.4 to 38.1 on the Noometry Index. MiniMax-M2.5 costs 19× less per token, which makes it the better buy when Claude Opus 4.7's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.7 or MiniMax-M2.5?

MiniMax-M2.5 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Claude Opus 4.7 lists at $5 and $25.

Is Claude Opus 4.7 or MiniMax-M2.5 better for coding?

Claude Opus 4.7 scores higher on coding benchmarks: 59.9 versus 47.9 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 4.7 does, with 1M tokens against 205K.

How many benchmarks do Claude Opus 4.7 and MiniMax-M2.5 share?

29 benchmarks have published results for both models. Claude Opus 4.7 has 66 scored results on Noometry and MiniMax-M2.5 has 33.

Related comparisons

Go deeper