Model comparison
Hy3 vs MiniMax-M2.5
Hy3 is the stronger model overall, scoring 43.6 to 38.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Tencent
MiniMaxSummary
- They share 17 benchmarks with published results for both. Hy3 scores higher in 7 categories and MiniMax-M2.5 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Hy3 leads 37.4 to 25.8.
- The biggest single-benchmark swing is NYT Connections (extended): 41.2% for Hy3 and 16.8% for MiniMax-M2.5.
- Hy3 is cheaper at $0.13 / $0.53 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.5.
- Hy3 accepts more context: 262K tokens versus 205K.
Side by side
| Hy3 | MiniMax-M2.5 | |
|---|---|---|
| Provider | Tencent | MiniMax |
| Noometry Index | 43.6 | 38.1 |
| Released | 2026-07-06 | 2026-02-12 |
| 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 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
Hy3: 46.6 (#60), MiniMax-M2.5: 47.9 (#53)
| Benchmark | Hy3 | MiniMax-M2.5 |
|---|---|---|
| LMArena WebDev | 1509 | 1386 |
| LMArena Coding | 1465 | 1380 |
| SWE-bench Verified (bash only) | — | 75.8% |
| SWE-bench Multilingual | — | 68.3% |
| ALE-Bench | — | 618.17 |
Agentic & Tool Use Not comparable
Hy3: —, MiniMax-M2.5: 30.2 (#70)
| Benchmark | Hy3 | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | — | 42.7% |
| Vending-Bench 2 | — | -23.16 |
Reasoning Hy3 leads
Hy3: 25.0 (#134), MiniMax-M2.5: 17.6 (#281)
| Benchmark | Hy3 | MiniMax-M2.5 |
|---|---|---|
| NYT Connections (extended) | 41.2% | 16.8% |
| LMArena Hard Prompts | 1449 | 1372 |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 55.2% |
| ARC-AGI-1 | — | 63.7% |
| Epoch Capabilities Index | — | 146.68 |
Math Hy3 leads
Hy3: 37.4 (#98), MiniMax-M2.5: 25.8 (#242)
| Benchmark | Hy3 | MiniMax-M2.5 |
|---|---|---|
| LMArena Math | 1475 | 1378 |
| ProofBench | — | 4% |
Knowledge Hy3 leads
Hy3: 40.2 (#108), MiniMax-M2.5: 38.6 (#132)
| Benchmark | Hy3 | MiniMax-M2.5 |
|---|---|---|
| LMArena Expert | 1461 | 1378 |
| Vectara Hallucination Rate | — | 9.1% |
Multilingual Hy3 leads
Hy3: 53.7 (#60), MiniMax-M2.5: 47.3 (#147)
| Benchmark | Hy3 | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1427 | 1338 |
| LMArena Chinese | 1496 | 1392 |
| LMArena French | 1461 | 1363 |
| LMArena Korean | 1390 | 1232 |
| LMArena Russian | 1435 | 1359 |
| LMArena Spanish | 1448 | 1354 |
| LMArena German | — | 1361 |
| LMArena Japanese | — | 1169 |
Instruction Following Hy3 leads
Hy3: 75.3 (#68), MiniMax-M2.5: 71.7 (#143)
| Benchmark | Hy3 | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1425 | 1353 |
Long Context Hy3 leads
Hy3: 44.1 (#70), MiniMax-M2.5: 37.4 (#211)
| Benchmark | Hy3 | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1443 | 1367 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |
Writing & Preference Hy3 leads
Hy3: 62.5 (#75), MiniMax-M2.5: 54.1 (#149)
| Benchmark | Hy3 | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1442 | 1359 |
| LMArena Creative Writing | 1399 | 1331 |
| LMArena Multi-Turn | 1436 | 1364 |
| EQ-Bench Creative Writing | — | 1361 |
Frequently asked questions
Is Hy3 better than MiniMax-M2.5?
Hy3 is the stronger model overall, scoring 43.6 to 38.1 on the Noometry Index.
Which is cheaper, Hy3 or MiniMax-M2.5?
Hy3 is cheaper. It lists at $0.13 per million input tokens and $0.53 per million output tokens; MiniMax-M2.5 lists at $0.30 and $1.20.
Is Hy3 or MiniMax-M2.5 better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 47.9 versus 46.6 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-M2.5 share?
17 benchmarks have published results for both models. Hy3 has 17 scored results on Noometry and MiniMax-M2.5 has 33.