Noometry

Model comparison

Claude Haiku 4.5 vs MiniMax-M2.7

Claude Haiku 4.5 is the stronger model overall, scoring 39.3 to 37.4 on the Noometry Index. MiniMax-M2.7 costs 3.8× less per token, which makes it the better buy when Claude Haiku 4.5's lead doesn't matter for your workload.

Last verified . 27 shared benchmarks.

Claude Haiku 4.5 Anthropic

39.3

Rank #155 Confirmed

MiniMax-M2.7 MiniMax

37.4

Rank #188 Confirmed

Summary

  • They share 27 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 5 categories and MiniMax-M2.7 in 4 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Haiku 4.5 leads 43.0 to 24.9.
  • The biggest single-benchmark swing is NYT Connections (extended): 14.3% for Claude Haiku 4.5 and 24.7% for MiniMax-M2.7.
  • MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
  • MiniMax-M2.7 accepts more context: 205K tokens versus 200K.
  • MiniMax-M2.7 has downloadable open weights; the other is API-only.

Side by side

Claude Haiku 4.5MiniMax-M2.7
ProviderAnthropicMiniMax
Noometry Index39.337.4
Released2025-10-152026-03-18
WeightsProprietaryOpen
Context window200K205K
Max output64K131K
Input $ / M tokens$1$0.30
Output $ / M tokens$5$1.20
Results tracked5330

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

Category by category

Coding Claude Haiku 4.5 leads

Claude Haiku 4.5: 43.9 (#71), MiniMax-M2.7: 41.4 (#115)

BenchmarkClaude Haiku 4.5MiniMax-M2.7
LMArena WebDev13301397
SciCode43.3%47%
WeirdML45.4%37%
LMArena Coding14541454
ALE-Bench653.48599.25
SWE-bench Verified (bash only)66.6%—
SWE-bench Multilingual64.7%—

Agentic & Tool Use Claude Haiku 4.5 leads

Claude Haiku 4.5: 33.5 (#50), MiniMax-M2.7: 24.9 (#103)

BenchmarkClaude Haiku 4.5MiniMax-M2.7
Terminal-Bench35.5%45.1%
ExploitBench13.7%13.3%
Berkeley Function Calling Leaderboard68.7%—
DeepResearch Bench45.5%—
BALROG31.2%—
GBAEval—0%
Vending-Bench 2458.89—

Reasoning MiniMax-M2.7 leads

Claude Haiku 4.5: 15.1 (#310), MiniMax-M2.7: 19.0 (#248)

BenchmarkClaude Haiku 4.5MiniMax-M2.7
NYT Connections (extended)14.3%24.7%
CritPt0%0.6%
LMArena Hard Prompts14201422
Epoch Capabilities Index142.42145.84
ARC-AGI-24%—
ARC-AGI-147.7%—
Chess Puzzles8%—
Thematic Generalization—39.3%
DTBench73.6%—
LMCA30.9%—
ForecastBench61.4—

Math Claude Haiku 4.5 leads

Claude Haiku 4.5: 43.0 (#69), MiniMax-M2.7: 24.9 (#254)

BenchmarkClaude Haiku 4.5MiniMax-M2.7
LMArena Math13951420
OTIS Mock AIME 2024-202566.7%—
ProofBench—3%
Omni-MATH56.1%—
MATH Level 596.4%—
FrontierMath (Feb 2025 set)5.9%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge Too close to call

Claude Haiku 4.5: 37.6 (#146), MiniMax-M2.7: 37.1 (#151)

BenchmarkClaude Haiku 4.5MiniMax-M2.7
Vectara Hallucination Rate9.8%12.9%
LMArena Expert14431443
GPQA Diamond71.2%—
SimpleQA Verified13.2%—
MMLU-Pro77.7%—
GPQA (HELM)60.5%—

Multimodal Not comparable

Claude Haiku 4.5: 27.0 (#111), MiniMax-M2.7: —

BenchmarkClaude Haiku 4.5MiniMax-M2.7
Blueprint-Bench 20%—
LMArena Document1420—

Multilingual Too close to call

Claude Haiku 4.5: 50.1 (#124), MiniMax-M2.7: 50.5 (#120)

BenchmarkClaude Haiku 4.5MiniMax-M2.7
LMArena Non-English13761382
LMArena Chinese14151439
LMArena French14081422
LMArena German13771398
LMArena Japanese13391261
LMArena Korean13461313
LMArena Russian13801383
LMArena Spanish14201403

Instruction Following MiniMax-M2.7 leads

Claude Haiku 4.5: 71.6 (#144), MiniMax-M2.7: 74.2 (#101)

BenchmarkClaude Haiku 4.5MiniMax-M2.7
LMArena Instruction Following14141404
IFEval80.1%—

Long Context Too close to call

Claude Haiku 4.5: 43.6 (#86), MiniMax-M2.7: 43.3 (#94)

BenchmarkClaude Haiku 4.5MiniMax-M2.7
LMArena Longer Query14271419

Writing & Preference MiniMax-M2.7 leads

Claude Haiku 4.5: 58.1 (#119), MiniMax-M2.7: 59.1 (#107)

BenchmarkClaude Haiku 4.5MiniMax-M2.7
LMArena Text13961404
LMArena Creative Writing13711354
LMArena Multi-Turn14091413
WildBench83.9%—
EQ-Bench 41064—

Frequently asked questions

Is Claude Haiku 4.5 better than MiniMax-M2.7?

Claude Haiku 4.5 is the stronger model overall, scoring 39.3 to 37.4 on the Noometry Index. MiniMax-M2.7 costs 3.8× less per token, which makes it the better buy when Claude Haiku 4.5's lead doesn't matter for your workload.

Which is cheaper, Claude Haiku 4.5 or MiniMax-M2.7?

MiniMax-M2.7 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.

Is Claude Haiku 4.5 or MiniMax-M2.7 better for coding?

Claude Haiku 4.5 scores higher on coding benchmarks: 43.9 versus 41.4 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M2.7 does, with 205K tokens against 200K.

How many benchmarks do Claude Haiku 4.5 and MiniMax-M2.7 share?

27 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and MiniMax-M2.7 has 30.

Related comparisons

Go deeper