Model comparison
MiniMax-M2 vs Sonar
Sonar is the stronger model overall, scoring 38.5 to 37.4 on the Noometry Index. MiniMax-M2 costs 1.9× less per token, which makes it the better buy when Sonar's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
MiniMax
PerplexitySummary
- The widest gap is in math, where MiniMax-M2 leads 37.3 to 33.7.
- MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1 / $1 for Sonar.
- MiniMax-M2 accepts more context: 205K tokens versus 128K.
- MiniMax-M2 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M2 | Sonar | |
|---|---|---|
| Provider | MiniMax | Perplexity |
| Noometry Index | 37.4 | 38.5 |
| Released | 2025-10-27 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | 205K | 128K |
| Max output | 131K | 4K |
| Input $ / M tokens | $0.30 | $1 |
| Output $ / M tokens | $1.20 | $1 |
| Results tracked | 21 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
MiniMax-M2: 39.3 (#159), Sonar: 35.7 (#221)
| Benchmark | MiniMax-M2 | Sonar |
|---|---|---|
| SWE-bench Verified (bash only) | 61% | — |
| LMArena WebDev | 1297 | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1370 | — |
Agentic & Tool Use Not comparable
MiniMax-M2: 25.1 (#109), Sonar: —
| Benchmark | MiniMax-M2 | Sonar |
|---|---|---|
| Terminal-Bench | 30% | — |
| Vending-Bench 2 | 160.6 | — |
Reasoning Sonar leads
MiniMax-M2: 19.4 (#258), Sonar: 21.1 (#227)
| Benchmark | MiniMax-M2 | Sonar |
|---|---|---|
| Kagi LLM Benchmark | 57.8% | — |
| NYT Connections (extended) | 14.8% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1357 | — |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |
Math MiniMax-M2 leads
MiniMax-M2: 37.3 (#160), Sonar: 33.7 (#200)
| Benchmark | MiniMax-M2 | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
| LMArena Math | 1352 | — |
Knowledge Not comparable
MiniMax-M2: 37.0 (#163), Sonar: —
| Benchmark | MiniMax-M2 | Sonar |
|---|---|---|
| LMArena Expert | 1337 | — |
Multilingual Not comparable
MiniMax-M2: 45.3 (#171), Sonar: —
| Benchmark | MiniMax-M2 | Sonar |
|---|---|---|
| LMArena Non-English | 1313 | — |
| LMArena Chinese | 1366 | — |
| LMArena French | 1335 | — |
| LMArena German | 1355 | — |
| LMArena Russian | 1331 | — |
| LMArena Spanish | 1326 | — |
Instruction Following Sonar leads
MiniMax-M2: 70.2 (#166), Sonar: 71.4 (#150)
| Benchmark | MiniMax-M2 | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1328 | — |
Long Context Not comparable
MiniMax-M2: 40.5 (#153), Sonar: —
| Benchmark | MiniMax-M2 | Sonar |
|---|---|---|
| LMArena Longer Query | 1331 | — |
Writing & Preference Too close to call
MiniMax-M2: 53.0 (#162), Sonar: 52.6 (#167)
| Benchmark | MiniMax-M2 | Sonar |
|---|---|---|
| LMArena Text | 1340 | — |
| LMArena Creative Writing | 1286 | — |
| LMArena Multi-Turn | 1361 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is MiniMax-M2 better than Sonar?
Sonar is the stronger model overall, scoring 38.5 to 37.4 on the Noometry Index. MiniMax-M2 costs 1.9× less per token, which makes it the better buy when Sonar's lead doesn't matter for your workload.
Which is cheaper, MiniMax-M2 or Sonar?
MiniMax-M2 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-M2 or Sonar better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 35.7 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2 does, with 205K tokens against 128K.
How many benchmarks do MiniMax-M2 and Sonar share?
0 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Sonar has 7.