Model comparison
MiniMax-M3 vs Sonar
MiniMax-M3 is the stronger model overall, scoring 43.5 to 37.8 on the Noometry Index.
Last verified . 0 shared benchmarks.
MiniMax
PerplexitySummary
- The widest gap is in writing & preference, where MiniMax-M3 leads 62.3 to 52.6.
- MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1 / $1 for Sonar.
- MiniMax-M3 accepts more context: 1M tokens versus 128K.
- MiniMax-M3 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M3 | Sonar | |
|---|---|---|
| Provider | MiniMax | Perplexity |
| Noometry Index | 43.5 | 37.8 |
| Released | 2026-06-01 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | 1M | 128K |
| Max output | 512K | 4K |
| Input $ / M tokens | $0.30 | $1 |
| Output $ / M tokens | $1.20 | $1 |
| Results tracked | 41 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M3 leads
MiniMax-M3: 41.5 (#111), Sonar: 35.1 (#217)
| Benchmark | MiniMax-M3 | Sonar |
|---|---|---|
| FrontierCode | 14.7% | — |
| LMArena WebDev | 1482 | — |
| SciCode | 47.1% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1470 | — |
| ALE-Bench | 640.02 | — |
Agentic & Tool Use Not comparable
MiniMax-M3: 22.5 (#121), Sonar: —
| Benchmark | MiniMax-M3 | Sonar |
|---|---|---|
| APEX-Agents | 37.7% | — |
| OSWorld 2.0 | 4.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 2,158 | — |
Reasoning MiniMax-M3 leads
MiniMax-M3: 29.3 (#83), Sonar: 20.3 (#221)
| Benchmark | MiniMax-M3 | Sonar |
|---|---|---|
| SimpleBench | 45.8% | — |
| NYT Connections (extended) | 65.1% | — |
| CritPt | 3.7% | — |
| Chess Puzzles | 14% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1447 | — |
| Mystery Game Puzzles | 8% | — |
| DTBench | 78.9% | — |
| LiveBench Data Analysis | — | 37.9% |
| LMCA | 33.7% | — |
| Surface Evolver Bench | 55% | — |
| Epoch Capabilities Index | 147 | — |
| ForecastBench | 61.4 | — |
| LiveBench | — | 46.9% |
Math MiniMax-M3 leads
MiniMax-M3: 39.1 (#83), Sonar: 31.3 (#197)
| Benchmark | MiniMax-M3 | Sonar |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | 18% | — |
| LiveBench Math | — | 41.6% |
| LMArena Math | 1432 | — |
Knowledge Not comparable
MiniMax-M3: 58.4 (#32), Sonar: —
| Benchmark | MiniMax-M3 | Sonar |
|---|---|---|
| GPQA Diamond | 90.9% | — |
| LMArena Expert | 1462 | — |
Multimodal Not comparable
MiniMax-M3: 39.5 (#45), Sonar: —
| Benchmark | MiniMax-M3 | Sonar |
|---|---|---|
| LMArena Vision | 1254 | — |
| LMArena Document | 1435 | — |
Multilingual Not comparable
MiniMax-M3: 53.2 (#70), Sonar: —
| Benchmark | MiniMax-M3 | Sonar |
|---|---|---|
| LMArena Non-English | 1420 | — |
| LMArena Chinese | 1465 | — |
| LMArena French | 1445 | — |
| LMArena German | 1424 | — |
| LMArena Japanese | 1381 | — |
| LMArena Korean | 1372 | — |
| LMArena Russian | 1430 | — |
| LMArena Spanish | 1431 | — |
Instruction Following MiniMax-M3 leads
MiniMax-M3: 75.7 (#56), Sonar: 71.5 (#146)
| Benchmark | MiniMax-M3 | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1433 | — |
Long Context Not comparable
MiniMax-M3: 44.2 (#68), Sonar: —
| Benchmark | MiniMax-M3 | Sonar |
|---|---|---|
| LMArena Longer Query | 1445 | — |
Writing & Preference MiniMax-M3 leads
MiniMax-M3: 62.3 (#79), Sonar: 52.6 (#166)
| Benchmark | MiniMax-M3 | Sonar |
|---|---|---|
| LMArena Text | 1433 | — |
| LMArena Creative Writing | 1405 | — |
| EQ-Bench 4 | 1150 | — |
| LMArena Multi-Turn | 1441 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is MiniMax-M3 better than Sonar?
MiniMax-M3 is the stronger model overall, scoring 43.5 to 37.8 on the Noometry Index.
Which is cheaper, MiniMax-M3 or Sonar?
MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Sonar lists at $1 and $1.
Is MiniMax-M3 or Sonar better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.5 versus 35.1 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M3 does, with 1M tokens against 128K.
How many benchmarks do MiniMax-M3 and Sonar share?
0 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Sonar has 7.