Noometry

Model comparison

Claude 3 Haiku vs MiniMax-M2.7

MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 25.9 on the Noometry Index.

Last verified . 19 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

MiniMax-M2.7 MiniMax

37.7

Rank #196 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and MiniMax-M2.7 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where MiniMax-M2.7 leads 58.9 to 29.7.
  • The biggest single-benchmark swing is WeirdML: 9.8% for Claude 3 Haiku and 37% for MiniMax-M2.7.
  • MiniMax-M2.7 has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuMiniMax-M2.7
ProviderAnthropicMiniMax
Noometry Index25.937.7
Released2024-03-072026-03-18
WeightsProprietaryOpen
Context window—205K
Max output—131K
Input $ / M tokens—$0.30
Output $ / M tokens—$1.20
Results tracked3730

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

Category by category

Coding MiniMax-M2.7 leads

Claude 3 Haiku: 26.4 (#325), MiniMax-M2.7: 41.8 (#120)

BenchmarkClaude 3 HaikuMiniMax-M2.7
WeirdML9.8%37%
LMArena Coding11991454
LMArena WebDev—1398
SciCode—47%
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
ALE-Bench—599.25
HumanEval+68.9%—
MBPP+68.8%—

Agentic & Tool Use Not comparable

Claude 3 Haiku: —, MiniMax-M2.7: 25.1 (#111)

BenchmarkClaude 3 HaikuMiniMax-M2.7
Terminal-Bench—45.1%
ExploitBench—13.3%
GBAEval—0%

Reasoning MiniMax-M2.7 leads

Claude 3 Haiku: 16.3 (#307), MiniMax-M2.7: 19.7 (#253)

BenchmarkClaude 3 HaikuMiniMax-M2.7
LMArena Hard Prompts11741422
Epoch Capabilities Index118.35145.85
Kagi LLM Benchmark34.2%—
NYT Connections (extended)—24.7%
CritPt—0.6%
Thematic Generalization—39.3%
DTBench50.1%—
LMCA8.8%—
ForecastBench53.2—
WinoGrande74.2%—

Math MiniMax-M2.7 leads

Claude 3 Haiku: 9.8 (#319), MiniMax-M2.7: 25.9 (#263)

BenchmarkClaude 3 HaikuMiniMax-M2.7
LMArena Math11881420
OTIS Mock AIME 2024-20251.8%—
ProofBench—3%
MATH Level 514.9%—

Knowledge MiniMax-M2.7 leads

Claude 3 Haiku: 17.3 (#285), MiniMax-M2.7: 37.7 (#152)

BenchmarkClaude 3 HaikuMiniMax-M2.7
LMArena Expert11481444
GPQA Diamond36.3%—
Confabulations34.2%—
Vectara Hallucination Rate—12.9%
MMLU73.8%—

Multimodal Not comparable

Claude 3 Haiku: 23.6 (#128), MiniMax-M2.7: —

BenchmarkClaude 3 HaikuMiniMax-M2.7
LMArena Vision950—
ScienceQA72%—

Multilingual MiniMax-M2.7 leads

Claude 3 Haiku: 36.0 (#243), MiniMax-M2.7: 50.3 (#123)

BenchmarkClaude 3 HaikuMiniMax-M2.7
LMArena Non-English11781382
LMArena Chinese11551441
LMArena French11951421
LMArena German11741398
LMArena Japanese11021262
LMArena Korean11091313
LMArena Russian12041383
LMArena Spanish11661403

Instruction Following MiniMax-M2.7 leads

Claude 3 Haiku: 61.3 (#247), MiniMax-M2.7: 74.1 (#103)

BenchmarkClaude 3 HaikuMiniMax-M2.7
LMArena Instruction Following11731405

Long Context MiniMax-M2.7 leads

Claude 3 Haiku: 36.1 (#237), MiniMax-M2.7: 43.3 (#99)

BenchmarkClaude 3 HaikuMiniMax-M2.7
LMArena Longer Query11901419

Writing & Preference MiniMax-M2.7 leads

Claude 3 Haiku: 29.7 (#291), MiniMax-M2.7: 58.9 (#112)

BenchmarkClaude 3 HaikuMiniMax-M2.7
LMArena Text11951405
LMArena Creative Writing11571354
LMArena Multi-Turn11901412
EQ-Bench Creative Writing717—

Frequently asked questions

Is Claude 3 Haiku better than MiniMax-M2.7?

MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 25.9 on the Noometry Index.

Is Claude 3 Haiku or MiniMax-M2.7 better for coding?

MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 26.4 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and MiniMax-M2.7 share?

19 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and MiniMax-M2.7 has 30.

Related comparisons

Go deeper