Model comparison
Hy3 vs MiniMax-M2.1
Hy3 is the stronger model overall, scoring 43.6 to 38.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Tencent
MiniMaxSummary
- They share 17 benchmarks with published results for both. Hy3 scores higher in 8 categories and MiniMax-M2.1 in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Hy3 leads 25.0 to 15.8.
- The biggest single-benchmark swing is NYT Connections (extended): 41.2% for Hy3 and 11.2% for MiniMax-M2.1.
- Hy3 is cheaper at $0.13 / $0.53 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.1.
- Hy3 accepts more context: 262K tokens versus 205K.
Side by side
| Hy3 | MiniMax-M2.1 | |
|---|---|---|
| Provider | Tencent | MiniMax |
| Noometry Index | 43.6 | 38.4 |
| Released | 2026-07-06 | 2025-12-23 |
| Weights | Open | Open |
| Context window | 262K | 205K |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.13 | $0.30 |
| Output $ / M tokens | $0.53 | $1.20 |
| Results tracked | 17 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.6 (#60), MiniMax-M2.1: 40.1 (#132)
| Benchmark | Hy3 | MiniMax-M2.1 |
|---|---|---|
| LMArena WebDev | 1509 | 1384 |
| LMArena Coding | 1465 | 1421 |
| ALE-Bench | — | 623.83 |
Agentic & Tool Use Not comparable
Hy3: —, MiniMax-M2.1: 27.7 (#91)
| Benchmark | Hy3 | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |
Reasoning Hy3 leads
Hy3: 25.0 (#134), MiniMax-M2.1: 15.8 (#301)
| Benchmark | Hy3 | MiniMax-M2.1 |
|---|---|---|
| NYT Connections (extended) | 41.2% | 11.2% |
| LMArena Hard Prompts | 1449 | 1410 |
Math Hy3 leads
Hy3: 37.4 (#98), MiniMax-M2.1: 35.6 (#142)
| Benchmark | Hy3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1475 | 1396 |
Knowledge Hy3 leads
Hy3: 40.2 (#108), MiniMax-M2.1: 37.7 (#143)
| Benchmark | Hy3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Expert | 1461 | 1432 |
| Vectara Hallucination Rate | — | 11.8% |
Multilingual Hy3 leads
Hy3: 53.7 (#60), MiniMax-M2.1: 50.2 (#123)
| Benchmark | Hy3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1427 | 1378 |
| LMArena Chinese | 1496 | 1430 |
| LMArena French | 1461 | 1405 |
| LMArena Korean | 1390 | 1297 |
| LMArena Russian | 1435 | 1386 |
| LMArena Spanish | 1448 | 1396 |
| LMArena German | — | 1380 |
| LMArena Japanese | — | 1287 |
Instruction Following Hy3 leads
Hy3: 75.3 (#68), MiniMax-M2.1: 74.0 (#108)
| Benchmark | Hy3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1425 | 1399 |
Long Context Too close to call
Hy3: 44.1 (#70), MiniMax-M2.1: 43.2 (#98)
| Benchmark | Hy3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1443 | 1416 |
Writing & Preference Hy3 leads
Hy3: 62.5 (#75), MiniMax-M2.1: 58.5 (#114)
| Benchmark | Hy3 | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1442 | 1392 |
| LMArena Creative Writing | 1399 | 1362 |
| LMArena Multi-Turn | 1436 | 1396 |
Frequently asked questions
Is Hy3 better than MiniMax-M2.1?
Hy3 is the stronger model overall, scoring 43.6 to 38.4 on the Noometry Index.
Which is cheaper, Hy3 or MiniMax-M2.1?
Hy3 is cheaper. It lists at $0.13 per million input tokens and $0.53 per million output tokens; MiniMax-M2.1 lists at $0.30 and $1.20.
Is Hy3 or MiniMax-M2.1 better for coding?
Hy3 scores higher on coding benchmarks: 46.6 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
Hy3 does, with 262K tokens against 205K.
How many benchmarks do Hy3 and MiniMax-M2.1 share?
17 benchmarks have published results for both models. Hy3 has 17 scored results on Noometry and MiniMax-M2.1 has 22.