Model comparison
Hy4 preview vs MiniMax-M2
Hy4 preview is the stronger model overall, scoring 45.3 to 37.4 on the Noometry Index. MiniMax-M2 costs 2.1× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
Tencent
MiniMaxSummary
- They share 2 benchmarks with published results for both. Hy4 preview scores higher in 3 categories and MiniMax-M2 in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Hy4 preview leads 55.7 to 37.3.
- The biggest single-benchmark swing is NYT Connections (extended): 68.2% for Hy4 preview and 14.8% for MiniMax-M2.
- MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.75 / $2.25 for Hy4 preview.
- Hy4 preview accepts more context: 1.05M tokens versus 205K.
Side by side
| Hy4 preview | MiniMax-M2 | |
|---|---|---|
| Provider | Tencent | MiniMax |
| Noometry Index | 45.3 | 37.4 |
| Released | 2026-08-28 | 2025-10-27 |
| Weights | Open | Open |
| Context window | 1.05M | 205K |
| Max output | 64K | 131K |
| Input $ / M tokens | $0.75 | $0.30 |
| Output $ / M tokens | $2.25 | $1.20 |
| Results tracked | 3 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Hy4 preview: 51.6 (#38), MiniMax-M2: 39.3 (#159)
| Benchmark | Hy4 preview | MiniMax-M2 |
|---|---|---|
| LMArena WebDev | 1632 | 1297 |
| SWE-bench Verified (bash only) | — | 61% |
| LMArena Coding | — | 1370 |
Agentic & Tool Use Not comparable
Hy4 preview: —, MiniMax-M2: 25.1 (#109)
| Benchmark | Hy4 preview | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Vending-Bench 2 | — | 160.6 |
Reasoning Hy4 preview leads
Hy4 preview: 31.9 (#79), MiniMax-M2: 19.4 (#258)
| Benchmark | Hy4 preview | MiniMax-M2 |
|---|---|---|
| NYT Connections (extended) | 68.2% | 14.8% |
| Kagi LLM Benchmark | — | 57.8% |
| LMArena Hard Prompts | — | 1357 |
Math Hy4 preview leads
Hy4 preview: 55.7 (#42), MiniMax-M2: 37.3 (#160)
| Benchmark | Hy4 preview | MiniMax-M2 |
|---|---|---|
| ProofBench | 75% | — |
| LMArena Math | — | 1352 |
Knowledge Not comparable
Hy4 preview: —, MiniMax-M2: 37.0 (#163)
| Benchmark | Hy4 preview | MiniMax-M2 |
|---|---|---|
| LMArena Expert | — | 1337 |
Multilingual Not comparable
Hy4 preview: —, MiniMax-M2: 45.3 (#171)
| Benchmark | Hy4 preview | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | — | 1313 |
| LMArena Chinese | — | 1366 |
| LMArena French | — | 1335 |
| LMArena German | — | 1355 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1326 |
Instruction Following Not comparable
Hy4 preview: —, MiniMax-M2: 70.2 (#166)
| Benchmark | Hy4 preview | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | — | 1328 |
Long Context Not comparable
Hy4 preview: —, MiniMax-M2: 40.5 (#153)
| Benchmark | Hy4 preview | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | — | 1331 |
Writing & Preference Not comparable
Hy4 preview: —, MiniMax-M2: 53.0 (#162)
| Benchmark | Hy4 preview | MiniMax-M2 |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1286 |
| LMArena Multi-Turn | — | 1361 |
Frequently asked questions
Is Hy4 preview better than MiniMax-M2?
Hy4 preview is the stronger model overall, scoring 45.3 to 37.4 on the Noometry Index. MiniMax-M2 costs 2.1× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.
Which is cheaper, Hy4 preview or MiniMax-M2?
MiniMax-M2 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Hy4 preview lists at $0.75 and $2.25.
Is Hy4 preview or MiniMax-M2 better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 39.3 in the Noometry coding category.
Which has the bigger context window?
Hy4 preview does, with 1.05M tokens against 205K.
How many benchmarks do Hy4 preview and MiniMax-M2 share?
2 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and MiniMax-M2 has 21.