Model comparison
MiniMax-M3 vs Nova 2 Lite
MiniMax-M3 is the stronger model overall, scoring 43.8 to 39.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
MiniMaxSummary
- They share 17 benchmarks with published results for both. MiniMax-M3 scores higher in 8 categories and Nova 2 Lite in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 43.0.
- MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.30 / $2.50 for Nova 2 Lite.
- MiniMax-M3 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M3 | Nova 2 Lite | |
|---|---|---|
| Provider | MiniMax | Amazon |
| Noometry Index | 43.8 | 39.7 |
| Released | 2026-06-01 | 2025-12-01 |
| Weights | Open | Proprietary |
| Context window | 1M | 1M |
| Max output | 512K | 64K |
| Input $ / M tokens | $0.30 | $0.30 |
| Output $ / M tokens | $1.20 | $2.50 |
| Results tracked | 41 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M3 leads
MiniMax-M3: 41.8 (#118), Nova 2 Lite: 40.7 (#134)
| Benchmark | MiniMax-M3 | Nova 2 Lite |
|---|---|---|
| LMArena Coding | 1469 | 1385 |
| FrontierCode | 14.7% | — |
| LMArena WebDev | 1482 | — |
| SciCode | 47.1% | — |
| ALE-Bench | 640.02 | — |
Agentic & Tool Use Nova 2 Lite leads
MiniMax-M3: 22.6 (#130), Nova 2 Lite: 24.1 (#121)
| Benchmark | MiniMax-M3 | Nova 2 Lite |
|---|---|---|
| APEX-Agents | 37.7% | — |
| Berkeley Function Calling Leaderboard | — | 27.1% |
| OSWorld 2.0 | 4.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 2,158 | — |
Reasoning MiniMax-M3 leads
MiniMax-M3: 30.1 (#87), Nova 2 Lite: 27.5 (#118)
| Benchmark | MiniMax-M3 | Nova 2 Lite |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1364 |
| 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), Nova 2 Lite: 37.5 (#156)
| Benchmark | MiniMax-M3 | Nova 2 Lite |
|---|---|---|
| LMArena Math | 1429 | 1359 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | 18% | — |
Knowledge MiniMax-M3 leads
MiniMax-M3: 58.4 (#35), Nova 2 Lite: 43.0 (#94)
| Benchmark | MiniMax-M3 | Nova 2 Lite |
|---|---|---|
| LMArena Expert | 1461 | 1358 |
| GPQA Diamond | 90.9% | — |
| Vectara Hallucination Rate | — | 5.1% |
Multimodal Not comparable
MiniMax-M3: 40.2 (#51), Nova 2 Lite: —
| Benchmark | MiniMax-M3 | Nova 2 Lite |
|---|---|---|
| LMArena Vision | 1253 | — |
| LMArena Document | 1435 | — |
Multilingual MiniMax-M3 leads
MiniMax-M3: 53.0 (#75), Nova 2 Lite: 47.1 (#153)
| Benchmark | MiniMax-M3 | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | 1420 | 1337 |
| LMArena Chinese | 1463 | 1364 |
| LMArena French | 1447 | 1381 |
| LMArena German | 1426 | 1343 |
| LMArena Japanese | 1381 | 1271 |
| LMArena Korean | 1372 | 1284 |
| LMArena Russian | 1428 | 1343 |
| LMArena Spanish | 1432 | 1373 |
Instruction Following MiniMax-M3 leads
MiniMax-M3: 75.5 (#62), Nova 2 Lite: 70.5 (#161)
| Benchmark | MiniMax-M3 | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | 1433 | 1335 |
Long Context MiniMax-M3 leads
MiniMax-M3: 44.2 (#72), Nova 2 Lite: 40.6 (#150)
| Benchmark | MiniMax-M3 | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | 1445 | 1335 |
Writing & Preference MiniMax-M3 leads
MiniMax-M3: 62.1 (#83), Nova 2 Lite: 53.9 (#154)
| Benchmark | MiniMax-M3 | Nova 2 Lite |
|---|---|---|
| LMArena Text | 1433 | 1362 |
| LMArena Creative Writing | 1404 | 1291 |
| LMArena Multi-Turn | 1442 | 1338 |
| EQ-Bench 4 | 1150 | — |
Frequently asked questions
Is MiniMax-M3 better than Nova 2 Lite?
MiniMax-M3 is the stronger model overall, scoring 43.8 to 39.7 on the Noometry Index.
Which is cheaper, MiniMax-M3 or Nova 2 Lite?
MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Nova 2 Lite lists at $0.30 and $2.50.
Is MiniMax-M3 or Nova 2 Lite better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 40.7 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do MiniMax-M3 and Nova 2 Lite share?
17 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Nova 2 Lite has 19.