Noometry

Model comparison

Claude 3 Sonnet vs MiniMax-M2.5

MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 29.0 on the Noometry Index.

Last verified . 18 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

MiniMax-M2.5 MiniMax

38.3

Rank #188 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Claude 3 Sonnet scores higher in 1 category and MiniMax-M2.5 in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in coding, where MiniMax-M2.5 leads 48.1 to 29.6.
  • MiniMax-M2.5 has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetMiniMax-M2.5
ProviderAnthropicMiniMax
Noometry Index29.038.3
Released2024-02-292026-02-12
WeightsProprietaryOpen
Context window—205K
Max output—131K
Input $ / M tokens—$0.30
Output $ / M tokens—$1.20
Results tracked3033

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

Category by category

Coding MiniMax-M2.5 leads

Claude 3 Sonnet: 29.6 (#302), MiniMax-M2.5: 48.1 (#58)

BenchmarkClaude 3 SonnetMiniMax-M2.5
LMArena Coding12231381
SWE-bench Verified (bash only)—75.8%
LMArena WebDev—1387
SWE-bench Multilingual—68.3%
WeirdML10.2%—
BigCodeBench Instruct42.7%—
BigCodeBench Complete53.8%—
ALE-Bench—618.17
HumanEval+64%—
MBPP+69.3%—

Agentic & Tool Use Not comparable

Claude 3 Sonnet: —, MiniMax-M2.5: 30.4 (#77)

BenchmarkClaude 3 SonnetMiniMax-M2.5
Terminal-Bench—42.7%
Vending-Bench 2—-23.16

Reasoning Claude 3 Sonnet leads

Claude 3 Sonnet: 20.5 (#237), MiniMax-M2.5: 17.5 (#292)

BenchmarkClaude 3 SonnetMiniMax-M2.5
LMArena Hard Prompts11971372
Epoch Capabilities Index120.7146.68
ARC-AGI-2—4.9%
Kagi LLM Benchmark—55.2%
NYT Connections (extended)—16.8%
ARC-AGI-1—63.7%
DTBench53.6%—
WinoGrande75.1%—

Math MiniMax-M2.5 leads

Claude 3 Sonnet: 10.7 (#310), MiniMax-M2.5: 26.9 (#253)

BenchmarkClaude 3 SonnetMiniMax-M2.5
LMArena Math12131378
OTIS Mock AIME 2024-20252.5%—
ProofBench—4%
MATH Level 518.2%—

Knowledge MiniMax-M2.5 leads

Claude 3 Sonnet: 21.1 (#276), MiniMax-M2.5: 39.2 (#135)

BenchmarkClaude 3 SonnetMiniMax-M2.5
LMArena Expert11731379
GPQA Diamond40.6%—
Vectara Hallucination Rate—9.1%
MMLU75.9%—

Multimodal Not comparable

Claude 3 Sonnet: 25.2 (#125), MiniMax-M2.5: —

BenchmarkClaude 3 SonnetMiniMax-M2.5
LMArena Vision984—

Multilingual MiniMax-M2.5 leads

Claude 3 Sonnet: 37.8 (#234), MiniMax-M2.5: 47.1 (#152)

BenchmarkClaude 3 SonnetMiniMax-M2.5
LMArena Non-English12051338
LMArena Chinese11891393
LMArena French12291362
LMArena German12041362
LMArena Japanese11311171
LMArena Korean11281232
LMArena Russian12271358
LMArena Spanish12041354

Instruction Following MiniMax-M2.5 leads

Claude 3 Sonnet: 62.8 (#235), MiniMax-M2.5: 71.5 (#148)

BenchmarkClaude 3 SonnetMiniMax-M2.5
LMArena Instruction Following11991353

Long Context Too close to call

Claude 3 Sonnet: 36.7 (#228), MiniMax-M2.5: 37.5 (#216)

BenchmarkClaude 3 SonnetMiniMax-M2.5
LMArena Longer Query12111366
CL-bench—11.4%
CL-bench Life—6.3%

Writing & Preference MiniMax-M2.5 leads

Claude 3 Sonnet: 42.1 (#238), MiniMax-M2.5: 53.9 (#153)

BenchmarkClaude 3 SonnetMiniMax-M2.5
LMArena Text12181359
LMArena Creative Writing11861331
LMArena Multi-Turn12271364
EQ-Bench Creative Writing—1361

Frequently asked questions

Is Claude 3 Sonnet better than MiniMax-M2.5?

MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 29.0 on the Noometry Index.

Is Claude 3 Sonnet or MiniMax-M2.5 better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 29.6 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and MiniMax-M2.5 share?

18 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and MiniMax-M2.5 has 33.

Related comparisons

Go deeper