Noometry

Model comparison

Claude 3 Haiku vs MiniMax-M3

MiniMax-M3 is the stronger model overall, scoring 43.8 to 25.9 on the Noometry Index.

Last verified . 24 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

MiniMax-M3 MiniMax

43.8

Rank #85 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and MiniMax-M3 in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 17.3.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 71.1% for MiniMax-M3.
  • MiniMax-M3 has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuMiniMax-M3
ProviderAnthropicMiniMax
Noometry Index25.943.8
Released2024-03-072026-06-01
WeightsProprietaryOpen
Context window—1M
Max output—512K
Input $ / M tokens—$0.30
Output $ / M tokens—$1.20
Results tracked3741

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

Category by category

Coding MiniMax-M3 leads

Claude 3 Haiku: 26.4 (#325), MiniMax-M3: 41.8 (#118)

BenchmarkClaude 3 HaikuMiniMax-M3
LMArena Coding11991469
FrontierCode—14.7%
LMArena WebDev—1482
SciCode—47.1%
WeirdML9.8%—
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
ALE-Bench—640.02
HumanEval+68.9%—
MBPP+68.8%—

Agentic & Tool Use Not comparable

Claude 3 Haiku: —, MiniMax-M3: 22.6 (#130)

BenchmarkClaude 3 HaikuMiniMax-M3
APEX-Agents—37.7%
OSWorld 2.0—4.6%
GBAEval—0.9%
Vending-Bench 2—2,158

Reasoning MiniMax-M3 leads

Claude 3 Haiku: 16.3 (#307), MiniMax-M3: 30.1 (#87)

BenchmarkClaude 3 HaikuMiniMax-M3
LMArena Hard Prompts11741447
DTBench50.1%78.9%
LMCA8.8%33.7%
Epoch Capabilities Index118.35146.95
ForecastBench53.261.4
SimpleBench—45.8%
Kagi LLM Benchmark34.2%—
NYT Connections (extended)—65.1%
CritPt—3.7%
Chess Puzzles—14%
Mystery Game Puzzles—8%
Surface Evolver Bench—55%
WinoGrande74.2%—

Math MiniMax-M3 leads

Claude 3 Haiku: 9.8 (#319), MiniMax-M3: 40.0 (#95)

BenchmarkClaude 3 HaikuMiniMax-M3
OTIS Mock AIME 2024-20251.8%71.1%
LMArena Math11881429
ProofBench—18%
MATH Level 514.9%—

Knowledge MiniMax-M3 leads

Claude 3 Haiku: 17.3 (#285), MiniMax-M3: 58.4 (#35)

BenchmarkClaude 3 HaikuMiniMax-M3
GPQA Diamond36.3%90.9%
LMArena Expert11481461
Confabulations34.2%—
MMLU73.8%—

Multimodal MiniMax-M3 leads

Claude 3 Haiku: 23.6 (#128), MiniMax-M3: 40.2 (#51)

BenchmarkClaude 3 HaikuMiniMax-M3
LMArena Vision9501253
LMArena Document—1435
ScienceQA72%—

Multilingual MiniMax-M3 leads

Claude 3 Haiku: 36.0 (#243), MiniMax-M3: 53.0 (#75)

BenchmarkClaude 3 HaikuMiniMax-M3
LMArena Non-English11781420
LMArena Chinese11551463
LMArena French11951447
LMArena German11741426
LMArena Japanese11021381
LMArena Korean11091372
LMArena Russian12041428
LMArena Spanish11661432

Instruction Following MiniMax-M3 leads

Claude 3 Haiku: 61.3 (#247), MiniMax-M3: 75.5 (#62)

BenchmarkClaude 3 HaikuMiniMax-M3
LMArena Instruction Following11731433

Long Context MiniMax-M3 leads

Claude 3 Haiku: 36.1 (#237), MiniMax-M3: 44.2 (#72)

BenchmarkClaude 3 HaikuMiniMax-M3
LMArena Longer Query11901445

Writing & Preference MiniMax-M3 leads

Claude 3 Haiku: 29.7 (#291), MiniMax-M3: 62.1 (#83)

BenchmarkClaude 3 HaikuMiniMax-M3
LMArena Text11951433
LMArena Creative Writing11571404
LMArena Multi-Turn11901442
EQ-Bench Creative Writing717—
EQ-Bench 4—1150

Frequently asked questions

Is Claude 3 Haiku better than MiniMax-M3?

MiniMax-M3 is the stronger model overall, scoring 43.8 to 25.9 on the Noometry Index.

Is Claude 3 Haiku or MiniMax-M3 better for coding?

MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 26.4 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and MiniMax-M3 share?

24 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and MiniMax-M3 has 41.

Related comparisons

Go deeper