Model comparison
MiniMax-M2 vs Nemotron 3 Ultra
Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 36.9 on the Noometry Index. MiniMax-M2 costs 2.0× less per token, which makes it the better buy when Nemotron 3 Ultra's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
MiniMax
NVIDIASummary
- They share 15 benchmarks with published results for both. MiniMax-M2 scores higher in 2 categories and Nemotron 3 Ultra in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 36.3.
- MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.60 / $2.40 for Nemotron 3 Ultra.
- Nemotron 3 Ultra accepts more context: 262K tokens versus 205K.
Side by side
| MiniMax-M2 | Nemotron 3 Ultra | |
|---|---|---|
| Provider | MiniMax | NVIDIA |
| Noometry Index | 36.9 | 44.7 |
| Released | 2025-10-27 | 2026-06-04 |
| Weights | Open | Open |
| Context window | 205K | 262K |
| Max output | 131K | 128K |
| Input $ / M tokens | $0.30 | $0.60 |
| Output $ / M tokens | $1.20 | $2.40 |
| Results tracked | 21 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
MiniMax-M2: 39.1 (#151), Nemotron 3 Ultra: 37.7 (#174)
| Benchmark | MiniMax-M2 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Coding | 1370 | 1468 |
| FrontierCode | — | 13.6% |
| SWE-bench Verified (bash only) | 61% | — |
| LMArena WebDev | 1297 | — |
| SciCode | — | 40.3% |
| WeirdML | — | 43.5% |
Agentic & Tool Use Not comparable
MiniMax-M2: 24.9 (#102), Nemotron 3 Ultra: —
| Benchmark | MiniMax-M2 | Nemotron 3 Ultra |
|---|---|---|
| Terminal-Bench | 30% | — |
| Vending-Bench 2 | 160.6 | — |
Reasoning Nemotron 3 Ultra leads
MiniMax-M2: 18.6 (#256), Nemotron 3 Ultra: 30.3 (#78)
| Benchmark | MiniMax-M2 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Hard Prompts | 1357 | 1452 |
| Kagi LLM Benchmark | 57.8% | — |
| NYT Connections (extended) | 14.8% | — |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
| Epoch Capabilities Index | — | 146.2 |
Math Too close to call
MiniMax-M2: 34.6 (#158), Nemotron 3 Ultra: 34.4 (#160)
| Benchmark | MiniMax-M2 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Math | 1350 | 1456 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 2% |
Knowledge Nemotron 3 Ultra leads
MiniMax-M2: 36.3 (#160), Nemotron 3 Ultra: 52.5 (#56)
| Benchmark | MiniMax-M2 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Expert | 1336 | 1472 |
| GPQA Diamond | — | 85.4% |
Multilingual Nemotron 3 Ultra leads
MiniMax-M2: 45.6 (#165), Nemotron 3 Ultra: 53.7 (#61)
| Benchmark | MiniMax-M2 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1314 | 1427 |
| LMArena Chinese | 1367 | 1498 |
| LMArena French | 1336 | 1475 |
| LMArena German | 1366 | 1471 |
| LMArena Russian | 1332 | 1415 |
| LMArena Spanish | 1326 | 1452 |
| LMArena Korean | — | 1387 |
Instruction Following Nemotron 3 Ultra leads
MiniMax-M2: 70.4 (#160), Nemotron 3 Ultra: 74.9 (#84)
| Benchmark | MiniMax-M2 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1329 | 1417 |
Long Context Nemotron 3 Ultra leads
MiniMax-M2: 40.5 (#148), Nemotron 3 Ultra: 43.9 (#77)
| Benchmark | MiniMax-M2 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1332 | 1437 |
Writing & Preference Nemotron 3 Ultra leads
MiniMax-M2: 53.3 (#157), Nemotron 3 Ultra: 66.3 (#35)
| Benchmark | MiniMax-M2 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1340 | 1444 |
| LMArena Creative Writing | 1288 | 1392 |
| LMArena Multi-Turn | 1362 | 1412 |
| EQ-Bench Creative Writing | — | 1692 |
Frequently asked questions
Is MiniMax-M2 better than Nemotron 3 Ultra?
Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 36.9 on the Noometry Index. MiniMax-M2 costs 2.0× 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 or Nemotron 3 Ultra?
MiniMax-M2 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Nemotron 3 Ultra lists at $0.60 and $2.40.
Is MiniMax-M2 or Nemotron 3 Ultra better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.1 versus 37.7 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 and Nemotron 3 Ultra share?
15 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Nemotron 3 Ultra has 29.