Model comparison
MiniMax-M3 vs Nemotron 3.5 Lightning
MiniMax-M3 is the stronger model overall, scoring 43.8 to 40.0 on the Noometry Index. Nemotron 3.5 Lightning costs 6.0× less per token, which makes it the better buy when MiniMax-M3's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
MiniMax
NVIDIASummary
- They share 17 benchmarks with published results for both. MiniMax-M3 scores higher in 8 categories and Nemotron 3.5 Lightning in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 37.5.
- Nemotron 3.5 Lightning is cheaper at $0.05 / $0.20 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M3.
- MiniMax-M3 accepts more context: 1M tokens versus 262K.
Side by side
| MiniMax-M3 | Nemotron 3.5 Lightning | |
|---|---|---|
| Provider | MiniMax | NVIDIA |
| Noometry Index | 43.8 | 40.0 |
| Released | 2026-06-01 | 2026-08-11 |
| Weights | Open | Open |
| Context window | 1M | 262K |
| Max output | 512K | 262K |
| Input $ / M tokens | $0.30 | $0.05 |
| Output $ / M tokens | $1.20 | $0.20 |
| Results tracked | 41 | 18 |
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 3.5 Lightning: 40.4 (#141)
| Benchmark | MiniMax-M3 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Coding | 1469 | 1375 |
| FrontierCode | 14.7% | — |
| LMArena WebDev | 1482 | — |
| SciCode | 47.1% | — |
| ALE-Bench | 640.02 | — |
Agentic & Tool Use Not comparable
MiniMax-M3: 22.6 (#130), Nemotron 3.5 Lightning: —
| Benchmark | MiniMax-M3 | Nemotron 3.5 Lightning |
|---|---|---|
| APEX-Agents | 37.7% | — |
| OSWorld 2.0 | 4.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 2,158 | — |
Reasoning MiniMax-M3 leads
MiniMax-M3: 30.1 (#87), Nemotron 3.5 Lightning: 26.8 (#127)
| Benchmark | MiniMax-M3 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1337 |
| SimpleBench | 45.8% | — |
| NYT Connections (extended) | 65.1% | — |
| CritPt | 3.7% | — |
| Chess Puzzles | 14% | — |
| Mystery Game Puzzles | 8% | — |
| DTBench | 78.9% | — |
| LMCA | 33.7% | — |
| Surface Evolver Bench | 55% | — |
| Epoch Capabilities Index | 146.95 | — |
| ForecastBench | 61.4 | — |
Math MiniMax-M3 leads
MiniMax-M3: 40.0 (#95), Nemotron 3.5 Lightning: 37.5 (#155)
| Benchmark | MiniMax-M3 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Math | 1429 | 1359 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | 18% | — |
Knowledge MiniMax-M3 leads
MiniMax-M3: 58.4 (#35), Nemotron 3.5 Lightning: 37.5 (#154)
| Benchmark | MiniMax-M3 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Expert | 1461 | 1356 |
| GPQA Diamond | 90.9% | — |
Multimodal Not comparable
MiniMax-M3: 40.2 (#51), Nemotron 3.5 Lightning: —
| Benchmark | MiniMax-M3 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Vision | 1253 | — |
| LMArena Document | 1435 | — |
Multilingual MiniMax-M3 leads
MiniMax-M3: 53.0 (#75), Nemotron 3.5 Lightning: 44.0 (#180)
| Benchmark | MiniMax-M3 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Non-English | 1420 | 1295 |
| LMArena Chinese | 1463 | 1359 |
| LMArena French | 1447 | 1366 |
| LMArena German | 1426 | 1282 |
| LMArena Japanese | 1381 | 1206 |
| LMArena Korean | 1372 | 1238 |
| LMArena Russian | 1428 | 1253 |
| LMArena Spanish | 1432 | 1345 |
Instruction Following MiniMax-M3 leads
MiniMax-M3: 75.5 (#62), Nemotron 3.5 Lightning: 69.6 (#170)
| Benchmark | MiniMax-M3 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Instruction Following | 1433 | 1318 |
Long Context MiniMax-M3 leads
MiniMax-M3: 44.2 (#72), Nemotron 3.5 Lightning: 39.9 (#165)
| Benchmark | MiniMax-M3 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Longer Query | 1445 | 1314 |
Writing & Preference MiniMax-M3 leads
MiniMax-M3: 62.1 (#83), Nemotron 3.5 Lightning: 48.5 (#201)
| Benchmark | MiniMax-M3 | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Text | 1433 | 1327 |
| LMArena Creative Writing | 1404 | 1254 |
| LMArena Multi-Turn | 1442 | 1328 |
| EQ-Bench Creative Writing | — | 1280 |
| EQ-Bench 4 | 1150 | — |
Frequently asked questions
Is MiniMax-M3 better than Nemotron 3.5 Lightning?
MiniMax-M3 is the stronger model overall, scoring 43.8 to 40.0 on the Noometry Index. Nemotron 3.5 Lightning costs 6.0× less per token, which makes it the better buy when MiniMax-M3's lead doesn't matter for your workload.
Which is cheaper, MiniMax-M3 or Nemotron 3.5 Lightning?
Nemotron 3.5 Lightning is cheaper. It lists at $0.05 per million input tokens and $0.20 per million output tokens; MiniMax-M3 lists at $0.30 and $1.20.
Is MiniMax-M3 or Nemotron 3.5 Lightning better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 40.4 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M3 does, with 1M tokens against 262K.
How many benchmarks do MiniMax-M3 and Nemotron 3.5 Lightning share?
17 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Nemotron 3.5 Lightning has 18.