Noometry

Model comparison

Claude 3.5 Haiku vs MiniMax-M2

MiniMax-M2 is the stronger model overall, scoring 37.4 to 29.2 on the Noometry Index.

Last verified . 15 shared benchmarks.

Claude 3.5 Haiku Anthropic

29.2

Rank #315 Confirmed

MiniMax-M2 MiniMax

37.4

Rank #204 Confirmed

Summary

  • They share 15 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 1 category and MiniMax-M2 in 8 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where MiniMax-M2 leads 37.3 to 14.7.
  • MiniMax-M2 has downloadable open weights; the other is API-only.

Side by side

Claude 3.5 HaikuMiniMax-M2
ProviderAnthropicMiniMax
Noometry Index29.237.4
Released2024-10-222025-10-27
WeightsProprietaryOpen
Context window—205K
Max output—131K
Input $ / M tokens—$0.30
Output $ / M tokens—$1.20
Results tracked4921

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

Category by category

Coding MiniMax-M2 leads

Claude 3.5 Haiku: 32.9 (#265), MiniMax-M2: 39.3 (#159)

BenchmarkClaude 3.5 HaikuMiniMax-M2
LMArena Coding12861370
SWE-bench Verified (bash only)—61%
Aider Polyglot28%—
LMArena WebDev—1297
SciCode27.4%—
WeirdML30.7%—
BigCodeBench Instruct46.1%—
LiveBench Coding51.4%—
BigCodeBench Complete59%—
CadEval32%—

Agentic & Tool Use Claude 3.5 Haiku leads

Claude 3.5 Haiku: 28.0 (#95), MiniMax-M2: 25.1 (#109)

BenchmarkClaude 3.5 HaikuMiniMax-M2
Terminal-Bench—30%
BALROG19.3%—
Vending-Bench 2—160.6

Reasoning MiniMax-M2 leads

Claude 3.5 Haiku: 17.7 (#290), MiniMax-M2: 19.4 (#258)

BenchmarkClaude 3.5 HaikuMiniMax-M2
LMArena Hard Prompts12511357
Kagi LLM Benchmark—57.8%
NYT Connections (extended)—14.8%
CritPt0%—
LiveBench Reasoning28.1%—
DTBench56.7%—
LiveBench Data Analysis48.5%—
Epoch Capabilities Index127.15—
LiveBench43.5%—

Math MiniMax-M2 leads

Claude 3.5 Haiku: 14.7 (#300), MiniMax-M2: 37.3 (#160)

BenchmarkClaude 3.5 HaikuMiniMax-M2
LMArena Math12441352
OTIS Mock AIME 2024-20254.3%—
Omni-MATH22.4%—
LiveBench Math35.5%—
MATH Level 546.4%—
FrontierMath (Feb 2025 set)0.3%—

Knowledge MiniMax-M2 leads

Claude 3.5 Haiku: 18.7 (#281), MiniMax-M2: 37.0 (#163)

BenchmarkClaude 3.5 HaikuMiniMax-M2
LMArena Expert12081337
GPQA Diamond38.1%—
MMLU-Pro60.5%—
Confabulations36.7%—
GPQA (HELM)36.3%—
MMLU74.3%—

Multimodal Not comparable

Claude 3.5 Haiku: 26.8 (#117), MiniMax-M2: —

BenchmarkClaude 3.5 HaikuMiniMax-M2
LMArena Vision1092—
GeoBench34%—

Multilingual MiniMax-M2 leads

Claude 3.5 Haiku: 40.0 (#218), MiniMax-M2: 45.3 (#171)

BenchmarkClaude 3.5 HaikuMiniMax-M2
LMArena Non-English12381313
LMArena Chinese12291366
LMArena French12641335
LMArena German12371355
LMArena Russian12531331
LMArena Spanish12611326
LMArena Japanese1175—
LMArena Korean1173—

Instruction Following MiniMax-M2 leads

Claude 3.5 Haiku: 62.9 (#234), MiniMax-M2: 70.2 (#166)

BenchmarkClaude 3.5 HaikuMiniMax-M2
LMArena Instruction Following12411328
LiveBench Instruction Following61.9%—
IFEval79.2%—

Long Context MiniMax-M2 leads

Claude 3.5 Haiku: 38.3 (#200), MiniMax-M2: 40.5 (#153)

BenchmarkClaude 3.5 HaikuMiniMax-M2
LMArena Longer Query12611331

Writing & Preference MiniMax-M2 leads

Claude 3.5 Haiku: 42.7 (#234), MiniMax-M2: 53.0 (#162)

BenchmarkClaude 3.5 HaikuMiniMax-M2
LMArena Text12551340
LMArena Creative Writing12331286
LMArena Multi-Turn12651361
Short-Story Creative Writing73.5%—
EQ-Bench Creative Writing1146—
WildBench76%—
LiveBench Language35.4%—

Frequently asked questions

Is Claude 3.5 Haiku better than MiniMax-M2?

MiniMax-M2 is the stronger model overall, scoring 37.4 to 29.2 on the Noometry Index.

Is Claude 3.5 Haiku or MiniMax-M2 better for coding?

MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 32.9 in the Noometry coding category.

How many benchmarks do Claude 3.5 Haiku and MiniMax-M2 share?

15 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and MiniMax-M2 has 21.

Related comparisons

Go deeper