Noometry

Model comparison

Claude 3 Haiku vs MiniMax-M2.1

MiniMax-M2.1 is the stronger model overall, scoring 38.4 to 25.7 on the Noometry Index.

Last verified . 17 shared benchmarks.

Claude 3 Haiku Anthropic

25.7

Rank #333 Confirmed

MiniMax-M2.1 MiniMax

38.4

Rank #177 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and MiniMax-M2.1 in 8 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where MiniMax-M2.1 leads 58.5 to 29.8.
  • MiniMax-M2.1 has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuMiniMax-M2.1
ProviderAnthropicMiniMax
Noometry Index25.738.4
Released2024-03-072025-12-23
WeightsProprietaryOpen
Context window—205K
Max output—131K
Input $ / M tokens—$0.30
Output $ / M tokens—$1.20
Results tracked3722

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

Category by category

Coding MiniMax-M2.1 leads

Claude 3 Haiku: 26.1 (#320), MiniMax-M2.1: 40.1 (#132)

BenchmarkClaude 3 HaikuMiniMax-M2.1
LMArena Coding11991421
LMArena WebDev—1384
WeirdML9.8%—
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
ALE-Bench—623.83
HumanEval+68.9%—
MBPP+68.8%—

Agentic & Tool Use Not comparable

Claude 3 Haiku: —, MiniMax-M2.1: 27.7 (#91)

BenchmarkClaude 3 HaikuMiniMax-M2.1
Terminal-Bench—36.6%

Reasoning Too close to call

Claude 3 Haiku: 15.7 (#303), MiniMax-M2.1: 15.8 (#301)

BenchmarkClaude 3 HaikuMiniMax-M2.1
LMArena Hard Prompts11741410
Kagi LLM Benchmark34.2%—
NYT Connections (extended)—11.2%
DTBench50.1%—
LMCA8.8%—
Epoch Capabilities Index118.3—
ForecastBench53.2—
WinoGrande74.2%—

Math MiniMax-M2.1 leads

Claude 3 Haiku: 9.2 (#313), MiniMax-M2.1: 35.6 (#142)

BenchmarkClaude 3 HaikuMiniMax-M2.1
LMArena Math11881396
OTIS Mock AIME 2024-20251.8%—
MATH Level 514.9%—

Knowledge MiniMax-M2.1 leads

Claude 3 Haiku: 17.3 (#280), MiniMax-M2.1: 37.7 (#143)

BenchmarkClaude 3 HaikuMiniMax-M2.1
LMArena Expert11481432
GPQA Diamond36.3%—
Confabulations34.2%—
Vectara Hallucination Rate—11.8%
MMLU73.8%—

Multimodal Not comparable

Claude 3 Haiku: 23.1 (#123), MiniMax-M2.1: —

BenchmarkClaude 3 HaikuMiniMax-M2.1
LMArena Vision950—
ScienceQA72%—

Multilingual MiniMax-M2.1 leads

Claude 3 Haiku: 36.1 (#238), MiniMax-M2.1: 50.2 (#123)

BenchmarkClaude 3 HaikuMiniMax-M2.1
LMArena Non-English11781378
LMArena Chinese11551430
LMArena French11941405
LMArena German11741380
LMArena Japanese11021287
LMArena Korean11081297
LMArena Russian12041386
LMArena Spanish11651396

Instruction Following MiniMax-M2.1 leads

Claude 3 Haiku: 61.5 (#242), MiniMax-M2.1: 74.0 (#108)

BenchmarkClaude 3 HaikuMiniMax-M2.1
LMArena Instruction Following11741399

Long Context MiniMax-M2.1 leads

Claude 3 Haiku: 36.1 (#232), MiniMax-M2.1: 43.2 (#98)

BenchmarkClaude 3 HaikuMiniMax-M2.1
LMArena Longer Query11911416

Writing & Preference MiniMax-M2.1 leads

Claude 3 Haiku: 29.8 (#286), MiniMax-M2.1: 58.5 (#114)

BenchmarkClaude 3 HaikuMiniMax-M2.1
LMArena Text11951392
LMArena Creative Writing11571362
LMArena Multi-Turn11901396
EQ-Bench Creative Writing717—

Frequently asked questions

Is Claude 3 Haiku better than MiniMax-M2.1?

MiniMax-M2.1 is the stronger model overall, scoring 38.4 to 25.7 on the Noometry Index.

Is Claude 3 Haiku or MiniMax-M2.1 better for coding?

MiniMax-M2.1 scores higher on coding benchmarks: 40.1 versus 26.1 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and MiniMax-M2.1 share?

17 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and MiniMax-M2.1 has 22.

Related comparisons

Go deeper