Noometry

Model comparison

MiniMax-M3 vs Step 3.7 Flash

MiniMax-M3 is the stronger model overall, scoring 43.8 to 37.3 on the Noometry Index.

Last verified . 4 shared benchmarks.

MiniMax-M3 MiniMax

43.8

Rank #85 Confirmed

Step 3.7 Flash StepFun

37.3

Rank #207 Reported

Summary

  • They share 4 benchmarks with published results for both. MiniMax-M3 scores higher in 2 categories and Step 3.7 Flash in 1 category; 3 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where MiniMax-M3 leads 30.1 to 21.6.
  • The biggest single-benchmark swing is NYT Connections (extended): 65.1% for MiniMax-M3 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-M3.
  • MiniMax-M3 accepts more context: 1M tokens versus 256K.

Side by side

MiniMax-M3Step 3.7 Flash
ProviderMiniMaxStepFun
Noometry Index43.837.3
Released2026-06-012026-05-29
WeightsOpenOpen
Context window1M256K
Max output512K256K
Input $ / M tokens$0.30$0.18
Output $ / M tokens$1.20$1.11
Results tracked415

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

Category by category

Coding MiniMax-M3 leads

MiniMax-M3: 41.8 (#118), Step 3.7 Flash: 40.0 (#150)

BenchmarkMiniMax-M3Step 3.7 Flash
SciCode47.1%40%
ALE-Bench640.02694.12
FrontierCode14.7%—
LMArena WebDev1482—
LMArena Coding1469—

Agentic & Tool Use Not comparable

MiniMax-M3: 22.6 (#130), Step 3.7 Flash: —

BenchmarkMiniMax-M3Step 3.7 Flash
APEX-Agents37.7%—
OSWorld 2.04.6%—
GBAEval0.9%—
Vending-Bench 22,158—

Reasoning MiniMax-M3 leads

MiniMax-M3: 30.1 (#87), Step 3.7 Flash: 21.6 (#219)

BenchmarkMiniMax-M3Step 3.7 Flash
NYT Connections (extended)65.1%39.7%
CritPt3.7%2.3%
SimpleBench45.8%—
Chess Puzzles14%—
LMArena Hard Prompts1447—
Mystery Game Puzzles8%—
DTBench78.9%—
LMCA33.7%—
Surface Evolver Bench55%—
Epoch Capabilities Index146.95—
ForecastBench61.4—

Math Step 3.7 Flash leads

MiniMax-M3: 40.0 (#95), Step 3.7 Flash: 42.9 (#82)

BenchmarkMiniMax-M3Step 3.7 Flash
MathArena Final-Answer Competitions—68.5%
OTIS Mock AIME 2024-202571.1%—
ProofBench18%—
LMArena Math1429—

Knowledge Not comparable

MiniMax-M3: 58.4 (#35), Step 3.7 Flash: —

BenchmarkMiniMax-M3Step 3.7 Flash
GPQA Diamond90.9%—
LMArena Expert1461—

Multimodal Not comparable

MiniMax-M3: 40.2 (#51), Step 3.7 Flash: —

BenchmarkMiniMax-M3Step 3.7 Flash
LMArena Vision1253—
LMArena Document1435—

Multilingual Not comparable

MiniMax-M3: 53.0 (#75), Step 3.7 Flash: —

BenchmarkMiniMax-M3Step 3.7 Flash
LMArena Non-English1420—
LMArena Chinese1463—
LMArena French1447—
LMArena German1426—
LMArena Japanese1381—
LMArena Korean1372—
LMArena Russian1428—
LMArena Spanish1432—

Instruction Following Not comparable

MiniMax-M3: 75.5 (#62), Step 3.7 Flash: —

BenchmarkMiniMax-M3Step 3.7 Flash
LMArena Instruction Following1433—

Long Context Not comparable

MiniMax-M3: 44.2 (#72), Step 3.7 Flash: —

BenchmarkMiniMax-M3Step 3.7 Flash
LMArena Longer Query1445—

Writing & Preference Not comparable

MiniMax-M3: 62.1 (#83), Step 3.7 Flash: —

BenchmarkMiniMax-M3Step 3.7 Flash
LMArena Text1433—
LMArena Creative Writing1404—
EQ-Bench 41150—
LMArena Multi-Turn1442—

Frequently asked questions

Is MiniMax-M3 better than Step 3.7 Flash?

MiniMax-M3 is the stronger model overall, scoring 43.8 to 37.3 on the Noometry Index.

Which is cheaper, MiniMax-M3 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-M3 lists at $0.30 and $1.20.

Is MiniMax-M3 or Step 3.7 Flash better for coding?

MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 40.0 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M3 does, with 1M tokens against 256K.

How many benchmarks do MiniMax-M3 and Step 3.7 Flash share?

4 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Step 3.7 Flash has 5.

Related comparisons

Go deeper