Noometry

Model comparison

MiniMax-M2.5 vs Step 3.7 Flash

MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 37.3 on the Noometry Index.

Last verified . 2 shared benchmarks.

MiniMax-M2.5 MiniMax

38.3

Rank #188 Confirmed

Step 3.7 Flash StepFun

37.3

Rank #207 Reported

Summary

  • They share 2 benchmarks with published results for both. MiniMax-M2.5 scores higher in 1 category and Step 3.7 Flash in 2 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in math, where Step 3.7 Flash leads 42.9 to 26.9.
  • The biggest single-benchmark swing is NYT Connections (extended): 16.8% for MiniMax-M2.5 and 39.7% for Step 3.7 Flash.
  • Step 3.7 Flash is cheaper at $0.18 / $1.11 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.5.
  • Step 3.7 Flash accepts more context: 256K tokens versus 205K.

Side by side

MiniMax-M2.5Step 3.7 Flash
ProviderMiniMaxStepFun
Noometry Index38.337.3
Released2026-02-122026-05-29
WeightsOpenOpen
Context window205K256K
Max output131K256K
Input $ / M tokens$0.30$0.18
Output $ / M tokens$1.20$1.11
Results tracked335

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

Category by category

Coding MiniMax-M2.5 leads

MiniMax-M2.5: 48.1 (#58), Step 3.7 Flash: 40.0 (#150)

BenchmarkMiniMax-M2.5Step 3.7 Flash
ALE-Bench618.17694.12
SWE-bench Verified (bash only)75.8%—
LMArena WebDev1387—
SWE-bench Multilingual68.3%—
SciCode—40%
LMArena Coding1381—

Agentic & Tool Use Not comparable

MiniMax-M2.5: 30.4 (#77), Step 3.7 Flash: —

BenchmarkMiniMax-M2.5Step 3.7 Flash
Terminal-Bench42.7%—
Vending-Bench 2-23.16—

Reasoning Step 3.7 Flash leads

MiniMax-M2.5: 17.5 (#292), Step 3.7 Flash: 21.6 (#219)

BenchmarkMiniMax-M2.5Step 3.7 Flash
NYT Connections (extended)16.8%39.7%
ARC-AGI-24.9%—
Kagi LLM Benchmark55.2%—
ARC-AGI-163.7%—
CritPt—2.3%
LMArena Hard Prompts1372—
Epoch Capabilities Index146.68—

Math Step 3.7 Flash leads

MiniMax-M2.5: 26.9 (#253), Step 3.7 Flash: 42.9 (#82)

BenchmarkMiniMax-M2.5Step 3.7 Flash
MathArena Final-Answer Competitions—68.5%
ProofBench4%—
LMArena Math1378—

Knowledge Not comparable

MiniMax-M2.5: 39.2 (#135), Step 3.7 Flash: —

BenchmarkMiniMax-M2.5Step 3.7 Flash
Vectara Hallucination Rate9.1%—
LMArena Expert1379—

Multilingual Not comparable

MiniMax-M2.5: 47.1 (#152), Step 3.7 Flash: —

BenchmarkMiniMax-M2.5Step 3.7 Flash
LMArena Non-English1338—
LMArena Chinese1393—
LMArena French1362—
LMArena German1362—
LMArena Japanese1171—
LMArena Korean1232—
LMArena Russian1358—
LMArena Spanish1354—

Instruction Following Not comparable

MiniMax-M2.5: 71.5 (#148), Step 3.7 Flash: —

BenchmarkMiniMax-M2.5Step 3.7 Flash
LMArena Instruction Following1353—

Long Context Not comparable

MiniMax-M2.5: 37.5 (#216), Step 3.7 Flash: —

BenchmarkMiniMax-M2.5Step 3.7 Flash
CL-bench11.4%—
CL-bench Life6.3%—
LMArena Longer Query1366—

Writing & Preference Not comparable

MiniMax-M2.5: 53.9 (#153), Step 3.7 Flash: —

BenchmarkMiniMax-M2.5Step 3.7 Flash
LMArena Text1359—
LMArena Creative Writing1331—
EQ-Bench Creative Writing1361—
LMArena Multi-Turn1364—

Frequently asked questions

Is MiniMax-M2.5 better than Step 3.7 Flash?

MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 37.3 on the Noometry Index.

Which is cheaper, MiniMax-M2.5 or Step 3.7 Flash?

Step 3.7 Flash is cheaper. It lists at $0.18 per million input tokens and $1.11 per million output tokens; MiniMax-M2.5 lists at $0.30 and $1.20.

Is MiniMax-M2.5 or Step 3.7 Flash better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 40.0 in the Noometry coding category.

Which has the bigger context window?

Step 3.7 Flash does, with 256K tokens against 205K.

How many benchmarks do MiniMax-M2.5 and Step 3.7 Flash share?

2 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Step 3.7 Flash has 5.

Related comparisons

Go deeper