Model comparison

MiniMax-M3 vs Nemotron 4 340b Instruct

MiniMax-M3 is the stronger model overall, scoring 43.8 to 35.9 on the Noometry Index.

Last verified . 17 shared benchmarks.

MiniMax-M3 MiniMax

43.8

Rank #85 Confirmed

Nemotron 4 340b Instruct NVIDIA

35.9

Rank #223 Confirmed

Summary

  • They share 17 benchmarks with published results for both. MiniMax-M3 scores higher in 8 categories and Nemotron 4 340b Instruct in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 32.0.

Side by side

MiniMax-M3 and Nemotron 4 340b Instruct specifications
MiniMax-M3Nemotron 4 340b Instruct
ProviderMiniMaxNVIDIA
Noometry Index43.835.9
Released2026-06-012024-06-14
WeightsOpenOpen
Context window1M—
Max output512K—
Input $ / M tokens$0.30—
Output $ / M tokens$1.20—
Results tracked4117

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

Category by category

Coding MiniMax-M3 leads

MiniMax-M3: 41.8 (#118), Nemotron 4 340b Instruct: 35.2 (#228)

Coding benchmarks
BenchmarkMiniMax-M3Nemotron 4 340b Instruct
LMArena Coding14691209
FrontierCode14.7%—
LMArena WebDev1482—
SciCode47.1%—
ALE-Bench640.02—

Agentic & Tool Use Not comparable

MiniMax-M3: 22.6 (#130), Nemotron 4 340b Instruct: —

Agentic & Tool Use benchmarks
BenchmarkMiniMax-M3Nemotron 4 340b Instruct
APEX-Agents37.7%—
OSWorld 2.04.6%—
GBAEval0.9%—
Vending-Bench 22,158—

Reasoning MiniMax-M3 leads

MiniMax-M3: 30.1 (#87), Nemotron 4 340b Instruct: 23.4 (#178)

Reasoning benchmarks
BenchmarkMiniMax-M3Nemotron 4 340b Instruct
LMArena Hard Prompts14471202
SimpleBench45.8%—
NYT Connections (extended)65.1%—
CritPt3.7%—
Chess Puzzles14%—
Mystery Game Puzzles8%—
DTBench78.9%—
LMCA33.7%—
Surface Evolver Bench55%—
Epoch Capabilities Index146.95—
ForecastBench61.4—

Math MiniMax-M3 leads

MiniMax-M3: 40.0 (#95), Nemotron 4 340b Instruct: 34.3 (#195)

Math benchmarks
BenchmarkMiniMax-M3Nemotron 4 340b Instruct
LMArena Math14291216
OTIS Mock AIME 2024-202571.1%—
ProofBench18%—

Knowledge MiniMax-M3 leads

MiniMax-M3: 58.4 (#35), Nemotron 4 340b Instruct: 32.0 (#216)

Knowledge benchmarks
BenchmarkMiniMax-M3Nemotron 4 340b Instruct
LMArena Expert14611171
GPQA Diamond90.9%—

Multimodal Not comparable

MiniMax-M3: 40.2 (#51), Nemotron 4 340b Instruct: —

Multimodal benchmarks
BenchmarkMiniMax-M3Nemotron 4 340b Instruct
LMArena Vision1253—
LMArena Document1435—

Multilingual MiniMax-M3 leads

MiniMax-M3: 53.0 (#75), Nemotron 4 340b Instruct: 37.9 (#233)

Multilingual benchmarks
BenchmarkMiniMax-M3Nemotron 4 340b Instruct
LMArena Non-English14201206
LMArena Chinese14631214
LMArena French14471197
LMArena German14261192
LMArena Japanese13811128
LMArena Korean13721148
LMArena Russian14281219
LMArena Spanish14321195

Instruction Following MiniMax-M3 leads

MiniMax-M3: 75.5 (#62), Nemotron 4 340b Instruct: 63.1 (#232)

Instruction Following benchmarks
BenchmarkMiniMax-M3Nemotron 4 340b Instruct
LMArena Instruction Following14331203

Long Context MiniMax-M3 leads

MiniMax-M3: 44.2 (#72), Nemotron 4 340b Instruct: 37.1 (#221)

Long Context benchmarks
BenchmarkMiniMax-M3Nemotron 4 340b Instruct
LMArena Longer Query14451225

Writing & Preference MiniMax-M3 leads

MiniMax-M3: 62.1 (#83), Nemotron 4 340b Instruct: 42.7 (#233)

Writing & Preference benchmarks
BenchmarkMiniMax-M3Nemotron 4 340b Instruct
LMArena Text14331225
LMArena Creative Writing14041203
LMArena Multi-Turn14421214
EQ-Bench 41150—

Frequently asked questions

Is MiniMax-M3 better than Nemotron 4 340b Instruct?

MiniMax-M3 is the stronger model overall, scoring 43.8 to 35.9 on the Noometry Index.

Is MiniMax-M3 or Nemotron 4 340b Instruct better for coding?

MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 35.2 in the Noometry coding category.

How many benchmarks do MiniMax-M3 and Nemotron 4 340b Instruct share?

17 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Nemotron 4 340b Instruct has 17.

Related comparisons

Go deeper