Noometry

Model comparison

Claude 3 Haiku vs MiniMax-M2

MiniMax-M2 is the stronger model overall, scoring 37.4 to 25.9 on the Noometry Index.

Last verified . 16 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

MiniMax-M2 MiniMax

37.4

Rank #204 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and MiniMax-M2 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where MiniMax-M2 leads 37.3 to 9.8.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 34.2% for Claude 3 Haiku and 57.8% for MiniMax-M2.
  • MiniMax-M2 has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuMiniMax-M2
ProviderAnthropicMiniMax
Noometry Index25.937.4
Released2024-03-072025-10-27
WeightsProprietaryOpen
Context window—205K
Max output—131K
Input $ / M tokens—$0.30
Output $ / M tokens—$1.20
Results tracked3721

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

Category by category

Coding MiniMax-M2 leads

Claude 3 Haiku: 26.4 (#325), MiniMax-M2: 39.3 (#159)

BenchmarkClaude 3 HaikuMiniMax-M2
LMArena Coding11991370
SWE-bench Verified (bash only)—61%
LMArena WebDev—1297
WeirdML9.8%—
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Agentic & Tool Use Not comparable

Claude 3 Haiku: —, MiniMax-M2: 25.1 (#109)

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

Reasoning MiniMax-M2 leads

Claude 3 Haiku: 16.3 (#307), MiniMax-M2: 19.4 (#258)

BenchmarkClaude 3 HaikuMiniMax-M2
Kagi LLM Benchmark34.2%57.8%
LMArena Hard Prompts11741357
NYT Connections (extended)—14.8%
DTBench50.1%—
LMCA8.8%—
Epoch Capabilities Index118.35—
ForecastBench53.2—
WinoGrande74.2%—

Math MiniMax-M2 leads

Claude 3 Haiku: 9.8 (#319), MiniMax-M2: 37.3 (#160)

BenchmarkClaude 3 HaikuMiniMax-M2
LMArena Math11881352
OTIS Mock AIME 2024-20251.8%—
MATH Level 514.9%—

Knowledge MiniMax-M2 leads

Claude 3 Haiku: 17.3 (#285), MiniMax-M2: 37.0 (#163)

BenchmarkClaude 3 HaikuMiniMax-M2
LMArena Expert11481337
GPQA Diamond36.3%—
Confabulations34.2%—
MMLU73.8%—

Multimodal Not comparable

Claude 3 Haiku: 23.6 (#128), MiniMax-M2: —

BenchmarkClaude 3 HaikuMiniMax-M2
LMArena Vision950—
ScienceQA72%—

Multilingual MiniMax-M2 leads

Claude 3 Haiku: 36.0 (#243), MiniMax-M2: 45.3 (#171)

BenchmarkClaude 3 HaikuMiniMax-M2
LMArena Non-English11781313
LMArena Chinese11551366
LMArena French11951335
LMArena German11741355
LMArena Russian12041331
LMArena Spanish11661326
LMArena Japanese1102—
LMArena Korean1109—

Instruction Following MiniMax-M2 leads

Claude 3 Haiku: 61.3 (#247), MiniMax-M2: 70.2 (#166)

BenchmarkClaude 3 HaikuMiniMax-M2
LMArena Instruction Following11731328

Long Context MiniMax-M2 leads

Claude 3 Haiku: 36.1 (#237), MiniMax-M2: 40.5 (#153)

BenchmarkClaude 3 HaikuMiniMax-M2
LMArena Longer Query11901331

Writing & Preference MiniMax-M2 leads

Claude 3 Haiku: 29.7 (#291), MiniMax-M2: 53.0 (#162)

BenchmarkClaude 3 HaikuMiniMax-M2
LMArena Text11951340
LMArena Creative Writing11571286
LMArena Multi-Turn11901361
EQ-Bench Creative Writing717—

Frequently asked questions

Is Claude 3 Haiku better than MiniMax-M2?

MiniMax-M2 is the stronger model overall, scoring 37.4 to 25.9 on the Noometry Index.

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

MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 26.4 in the Noometry coding category.

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

16 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and MiniMax-M2 has 21.

Related comparisons

Go deeper