Noometry

Model comparison

Claude Opus 4.8 vs MiniMax-M3

Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 43.8 on the Noometry Index. MiniMax-M3 costs 19× less per token, which makes it the better buy when Claude Opus 4.8's lead doesn't matter for your workload.

Last verified . 41 shared benchmarks.

Claude Opus 4.8 Anthropic

60.7

Rank #13 Confirmed

MiniMax-M3 MiniMax

43.8

Rank #85 Confirmed

Summary

  • They share 41 benchmarks with published results for both. Claude Opus 4.8 scores higher in 10 categories and MiniMax-M3 in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Opus 4.8 leads 78.4 to 40.0.
  • The biggest single-benchmark swing is GBAEval: 70.9% for Claude Opus 4.8 and 0.9% for MiniMax-M3.
  • MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $5 / $25 for Claude Opus 4.8.
  • MiniMax-M3 has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4.8MiniMax-M3
ProviderAnthropicMiniMax
Noometry Index60.743.8
Released2026-05-282026-06-01
WeightsProprietaryOpen
Context window1M1M
Max output128K512K
Input $ / M tokens$5$0.30
Output $ / M tokens$25$1.20
Results tracked6541

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

Category by category

Coding Claude Opus 4.8 leads

Claude Opus 4.8: 59.9 (#12), MiniMax-M3: 41.8 (#118)

BenchmarkClaude Opus 4.8MiniMax-M3
FrontierCode46.5%14.7%
LMArena WebDev15561482
SciCode53.5%47.1%
LMArena Coding14901469
ALE-Bench1,564640.02
DeepSWE59%—
GSO47.1%—
WeirdML82.9%—

Agentic & Tool Use Claude Opus 4.8 leads

Claude Opus 4.8: 47.6 (#11), MiniMax-M3: 22.6 (#130)

BenchmarkClaude Opus 4.8MiniMax-M3
APEX-Agents48.9%37.7%
OSWorld 2.020.6%4.6%
GBAEval70.9%0.9%
Vending-Bench 25,7872,158
Remote Labor Index8.3%—
τ²-bench Banking39.7%—
DeepResearch Bench50.2%—
PostTrainBench33.8%—
GDP.pdf24%—
LMArena Search1204—

Reasoning Claude Opus 4.8 leads

Claude Opus 4.8: 64.7 (#16), MiniMax-M3: 30.1 (#87)

BenchmarkClaude Opus 4.8MiniMax-M3
SimpleBench64.8%45.8%
NYT Connections (extended)91.1%65.1%
CritPt20.9%3.7%
Chess Puzzles34%14%
LMArena Hard Prompts14821447
Mystery Game Puzzles36%8%
DTBench94.9%78.9%
LMCA57.5%33.7%
Surface Evolver Bench87.5%55%
Epoch Capabilities Index158.21146.95
ForecastBench59.961.4
ARC-AGI-272.1%—
Kagi LLM Benchmark88.8%—
ARC-AGI-192.5%—
EnigmaEval23.5%—
EBR-Bench28.6%—
Bench to the Future 30.14—

Math Claude Opus 4.8 leads

Claude Opus 4.8: 78.4 (#13), MiniMax-M3: 40.0 (#95)

BenchmarkClaude Opus 4.8MiniMax-M3
OTIS Mock AIME 2024-202598.3%71.1%
ProofBench69%18%
LMArena Math14871429
FrontierMath (Tiers 1-3)80%—
FrontierMath Tier 456.1%—
MathArena Final-Answer Competitions91.8%—
FrontierMath (Feb 2025 set)47.2%—
FrontierMath Tier 4 (v1)31.3%—

Knowledge Claude Opus 4.8 leads

Claude Opus 4.8: 61.3 (#29), MiniMax-M3: 58.4 (#35)

BenchmarkClaude Opus 4.8MiniMax-M3
GPQA Diamond91%90.9%
LMArena Expert15021461
SimpleQA Verified53%—

Multimodal Claude Opus 4.8 leads

Claude Opus 4.8: 42.9 (#26), MiniMax-M3: 40.2 (#51)

BenchmarkClaude Opus 4.8MiniMax-M3
LMArena Vision12941253
LMArena Document14751435
Blueprint-Bench 214.5%—
Furniture Assembly42.5%—

Multilingual Claude Opus 4.8 leads

Claude Opus 4.8: 55.2 (#33), MiniMax-M3: 53.0 (#75)

BenchmarkClaude Opus 4.8MiniMax-M3
LMArena Non-English14501420
LMArena Chinese15071463
LMArena French14811447
LMArena German14721426
LMArena Japanese14401381
LMArena Korean14321372
LMArena Russian14741428
LMArena Spanish14661432

Instruction Following Claude Opus 4.8 leads

Claude Opus 4.8: 77.4 (#24), MiniMax-M3: 75.5 (#62)

BenchmarkClaude Opus 4.8MiniMax-M3
LMArena Instruction Following14761433

Long Context Claude Opus 4.8 leads

Claude Opus 4.8: 45.4 (#35), MiniMax-M3: 44.2 (#72)

BenchmarkClaude Opus 4.8MiniMax-M3
LMArena Longer Query14831445

Writing & Preference Claude Opus 4.8 leads

Claude Opus 4.8: 72.0 (#16), MiniMax-M3: 62.1 (#83)

BenchmarkClaude Opus 4.8MiniMax-M3
LMArena Text14611433
LMArena Creative Writing14541404
EQ-Bench 412811150
LMArena Multi-Turn14761442
EQ-Bench Creative Writing1840—

Frequently asked questions

Is Claude Opus 4.8 better than MiniMax-M3?

Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 43.8 on the Noometry Index. MiniMax-M3 costs 19× less per token, which makes it the better buy when Claude Opus 4.8's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.8 or MiniMax-M3?

MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Claude Opus 4.8 lists at $5 and $25.

Is Claude Opus 4.8 or MiniMax-M3 better for coding?

Claude Opus 4.8 scores higher on coding benchmarks: 59.9 versus 41.8 in the Noometry coding category.

Which has the bigger context window?

Both accept 1M tokens.

How many benchmarks do Claude Opus 4.8 and MiniMax-M3 share?

41 benchmarks have published results for both models. Claude Opus 4.8 has 65 scored results on Noometry and MiniMax-M3 has 41.

Related comparisons

Go deeper