Model comparison
MiniMax-M2.1 vs Nemotron 3 Ultra
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 38.9 on the Noometry Index. MiniMax-M2.1 costs 1.8× less per token, which makes it the better buy when Nemotron 3 Ultra's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
MiniMax
NVIDIASummary
- They share 16 benchmarks with published results for both. MiniMax-M2.1 scores higher in 3 categories and Nemotron 3 Ultra in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Nemotron 3 Ultra leads 31.0 to 16.6.
- MiniMax-M2.1 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.50 / $2.20 for Nemotron 3 Ultra.
- Nemotron 3 Ultra accepts more context: 262K tokens versus 205K.
Side by side
| MiniMax-M2.1 | Nemotron 3 Ultra | |
|---|---|---|
| Provider | MiniMax | NVIDIA |
| Noometry Index | 38.9 | 42.5 |
| Released | 2025-12-23 | 2026-06-04 |
| Weights | Open | Open |
| Context window | 205K | 262K |
| Max output | 131K | 128K |
| Input $ / M tokens | $0.30 | $0.50 |
| Output $ / M tokens | $1.20 | $2.20 |
| Results tracked | 22 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.1 leads
MiniMax-M2.1: 40.4 (#143), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | MiniMax-M2.1 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Coding | 1421 | 1468 |
| FrontierCode | — | 13.6% |
| LMArena WebDev | 1384 | — |
| SciCode | — | 40.3% |
| WeirdML | — | 43.5% |
| ALE-Bench | 623.83 | — |
Agentic & Tool Use MiniMax-M2.1 leads
MiniMax-M2.1: 27.9 (#98), Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | MiniMax-M2.1 | Nemotron 3 Ultra |
|---|---|---|
| Terminal-Bench | 36.6% | — |
| APEX-Agents | — | 22.7% |
Reasoning Nemotron 3 Ultra leads
MiniMax-M2.1: 16.6 (#302), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | MiniMax-M2.1 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Hard Prompts | 1411 | 1452 |
| NYT Connections (extended) | 11.2% | — |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
| Epoch Capabilities Index | — | 146.17 |
Math MiniMax-M2.1 leads
MiniMax-M2.1: 38.3 (#138), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | MiniMax-M2.1 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Math | 1397 | 1457 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 2% |
Knowledge Nemotron 3 Ultra leads
MiniMax-M2.1: 38.3 (#147), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | MiniMax-M2.1 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Expert | 1431 | 1472 |
| GPQA Diamond | — | 85.4% |
| Vectara Hallucination Rate | 11.8% | — |
Multilingual Nemotron 3 Ultra leads
MiniMax-M2.1: 50.0 (#128), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | MiniMax-M2.1 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1378 | 1427 |
| LMArena Chinese | 1430 | 1497 |
| LMArena French | 1404 | 1472 |
| LMArena German | 1381 | 1471 |
| LMArena Korean | 1298 | 1386 |
| LMArena Russian | 1387 | 1417 |
| LMArena Spanish | 1397 | 1454 |
| LMArena Japanese | 1287 | — |
Instruction Following Too close to call
MiniMax-M2.1: 73.8 (#112), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | MiniMax-M2.1 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1400 | 1418 |
Long Context Too close to call
MiniMax-M2.1: 43.2 (#101), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | MiniMax-M2.1 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1416 | 1437 |
Writing & Preference Nemotron 3 Ultra leads
MiniMax-M2.1: 58.3 (#120), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | MiniMax-M2.1 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1392 | 1445 |
| LMArena Creative Writing | 1361 | 1398 |
| LMArena Multi-Turn | 1396 | 1411 |
| EQ-Bench Creative Writing | — | 1692 |
Frequently asked questions
Is MiniMax-M2.1 better than Nemotron 3 Ultra?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 38.9 on the Noometry Index. MiniMax-M2.1 costs 1.8× less per token, which makes it the better buy when Nemotron 3 Ultra's lead doesn't matter for your workload.
Which is cheaper, MiniMax-M2.1 or Nemotron 3 Ultra?
MiniMax-M2.1 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Nemotron 3 Ultra lists at $0.50 and $2.20.
Is MiniMax-M2.1 or Nemotron 3 Ultra better for coding?
MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 38.1 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Ultra does, with 262K tokens against 205K.
How many benchmarks do MiniMax-M2.1 and Nemotron 3 Ultra share?
16 benchmarks have published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and Nemotron 3 Ultra has 30.