Model comparison
Hy4 preview vs MiniMax-M2.7
Hy4 preview is the stronger model overall, scoring 44.6 to 37.4 on the Noometry Index. MiniMax-M2.7 costs 2.4× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.
Last verified . 3 shared benchmarks.
Tencent
MiniMaxSummary
- They share 3 benchmarks with published results for both. Hy4 preview scores higher in 3 categories and MiniMax-M2.7 in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Hy4 preview leads 54.5 to 24.9.
- The biggest single-benchmark swing is ProofBench: 75% for Hy4 preview and 3% for MiniMax-M2.7.
- MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.83 / $2.50 for Hy4 preview.
- Hy4 preview accepts more context: 1.05M tokens versus 205K.
Side by side
| Hy4 preview | MiniMax-M2.7 | |
|---|---|---|
| Provider | Tencent | MiniMax |
| Noometry Index | 44.6 | 37.4 |
| Released | 2026-08-28 | 2026-03-18 |
| Weights | Open | Open |
| Context window | 1.05M | 205K |
| Max output | 64K | 131K |
| Input $ / M tokens | $0.83 | $0.30 |
| Output $ / M tokens | $2.50 | $1.20 |
| Results tracked | 3 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Hy4 preview: 51.4 (#36), MiniMax-M2.7: 41.4 (#115)
| Benchmark | Hy4 preview | MiniMax-M2.7 |
|---|---|---|
| LMArena WebDev | 1633 | 1397 |
| SciCode | — | 47% |
| WeirdML | — | 37% |
| LMArena Coding | — | 1454 |
| ALE-Bench | — | 599.25 |
Agentic & Tool Use Not comparable
Hy4 preview: —, MiniMax-M2.7: 24.9 (#103)
| Benchmark | Hy4 preview | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | — | 45.1% |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |
Reasoning Hy4 preview leads
Hy4 preview: 30.6 (#75), MiniMax-M2.7: 19.0 (#248)
| Benchmark | Hy4 preview | MiniMax-M2.7 |
|---|---|---|
| NYT Connections (extended) | 68.2% | 24.7% |
| CritPt | — | 0.6% |
| Thematic Generalization | — | 39.3% |
| LMArena Hard Prompts | — | 1422 |
| Epoch Capabilities Index | — | 145.84 |
Math Hy4 preview leads
Hy4 preview: 54.5 (#37), MiniMax-M2.7: 24.9 (#254)
| Benchmark | Hy4 preview | MiniMax-M2.7 |
|---|---|---|
| ProofBench | 75% | 3% |
| LMArena Math | — | 1420 |
Knowledge Not comparable
Hy4 preview: —, MiniMax-M2.7: 37.1 (#151)
| Benchmark | Hy4 preview | MiniMax-M2.7 |
|---|---|---|
| Vectara Hallucination Rate | — | 12.9% |
| LMArena Expert | — | 1443 |
Multilingual Not comparable
Hy4 preview: —, MiniMax-M2.7: 50.5 (#120)
| Benchmark | Hy4 preview | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | — | 1382 |
| LMArena Chinese | — | 1439 |
| LMArena French | — | 1422 |
| LMArena German | — | 1398 |
| LMArena Japanese | — | 1261 |
| LMArena Korean | — | 1313 |
| LMArena Russian | — | 1383 |
| LMArena Spanish | — | 1403 |
Instruction Following Not comparable
Hy4 preview: —, MiniMax-M2.7: 74.2 (#101)
| Benchmark | Hy4 preview | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | — | 1404 |
Long Context Not comparable
Hy4 preview: —, MiniMax-M2.7: 43.3 (#94)
| Benchmark | Hy4 preview | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | — | 1419 |
Writing & Preference Not comparable
Hy4 preview: —, MiniMax-M2.7: 59.1 (#107)
| Benchmark | Hy4 preview | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | — | 1404 |
| LMArena Creative Writing | — | 1354 |
| LMArena Multi-Turn | — | 1413 |
Frequently asked questions
Is Hy4 preview better than MiniMax-M2.7?
Hy4 preview is the stronger model overall, scoring 44.6 to 37.4 on the Noometry Index. MiniMax-M2.7 costs 2.4× 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-M2.7?
MiniMax-M2.7 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Hy4 preview lists at $0.83 and $2.50.
Is Hy4 preview or MiniMax-M2.7 better for coding?
Hy4 preview scores higher on coding benchmarks: 51.4 versus 41.4 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-M2.7 share?
3 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and MiniMax-M2.7 has 30.