Model comparison
MiniMax M1 vs Sonar
MiniMax M1 is the stronger model overall, scoring 40.3 to 38.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
MiniMax
PerplexitySummary
- The widest gap is in reasoning, where MiniMax M1 leads 26.9 to 21.1.
- Both cost about the same: $0.55 input and $2.20 output per million tokens.
- MiniMax M1 accepts more context: 1M tokens versus 128K.
- MiniMax M1 has downloadable open weights; the other is API-only.
Side by side
| MiniMax M1 | Sonar | |
|---|---|---|
| Provider | MiniMax | Perplexity |
| Noometry Index | 40.3 | 38.5 |
| Released | 2025-06-13 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | 1M | 128K |
| Max output | 40K | 4K |
| Input $ / M tokens | $0.55 | $1 |
| Output $ / M tokens | $2.20 | $1 |
| Results tracked | 18 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax M1 leads
MiniMax M1: 39.9 (#153), Sonar: 35.7 (#221)
| Benchmark | MiniMax M1 | Sonar |
|---|---|---|
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1359 | — |
Reasoning MiniMax M1 leads
MiniMax M1: 26.9 (#126), Sonar: 21.1 (#227)
| Benchmark | MiniMax M1 | Sonar |
|---|---|---|
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1339 | — |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |
Math MiniMax M1 leads
MiniMax M1: 37.5 (#151), Sonar: 33.7 (#200)
| Benchmark | MiniMax M1 | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
| LMArena Math | 1361 | — |
Knowledge Not comparable
MiniMax M1: 36.4 (#170), Sonar: —
| Benchmark | MiniMax M1 | Sonar |
|---|---|---|
| LMArena Expert | 1317 | — |
Multilingual Not comparable
MiniMax M1: 45.8 (#163), Sonar: —
| Benchmark | MiniMax M1 | Sonar |
|---|---|---|
| LMArena Non-English | 1319 | — |
| LMArena Chinese | 1360 | — |
| LMArena French | 1370 | — |
| LMArena German | 1350 | — |
| LMArena Japanese | 1217 | — |
| LMArena Korean | 1266 | — |
| LMArena Russian | 1329 | — |
| LMArena Spanish | 1353 | — |
Instruction Following Sonar leads
MiniMax M1: 69.3 (#174), Sonar: 71.4 (#150)
| Benchmark | MiniMax M1 | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1312 | — |
Long Context Not comparable
MiniMax M1: 41.4 (#141), Sonar: —
| Benchmark | MiniMax M1 | Sonar |
|---|---|---|
| Fiction.LiveBench | 69.4% | — |
| LMArena Longer Query | 1326 | — |
Writing & Preference Too close to call
MiniMax M1: 53.1 (#161), Sonar: 52.6 (#167)
| Benchmark | MiniMax M1 | Sonar |
|---|---|---|
| LMArena Text | 1343 | — |
| LMArena Creative Writing | 1298 | — |
| LMArena Multi-Turn | 1335 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is MiniMax M1 better than Sonar?
MiniMax M1 is the stronger model overall, scoring 40.3 to 38.5 on the Noometry Index.
Which is cheaper, MiniMax M1 or Sonar?
MiniMax M1 is cheaper. It lists at $0.55 per million input tokens and $2.20 per million output tokens; Sonar lists at $1 and $1.
Is MiniMax M1 or Sonar better for coding?
MiniMax M1 scores higher on coding benchmarks: 39.9 versus 35.7 in the Noometry coding category.
Which has the bigger context window?
MiniMax M1 does, with 1M tokens against 128K.
How many benchmarks do MiniMax M1 and Sonar share?
0 benchmarks have published results for both models. MiniMax M1 has 18 scored results on Noometry and Sonar has 7.