Model comparison
Hy3 vs Mercury 2
Hy3 is the stronger model overall, scoring 44.2 to 39.1 on the Noometry Index.
Last verified . 12 shared benchmarks.
TencentSummary
- They share 12 benchmarks with published results for both. Hy3 scores higher in 7 categories and Mercury 2 in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Hy3 leads 46.8 to 33.5.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $0.25 / $0.75 for Mercury 2.
- Hy3 accepts more context: 262K tokens versus 128K.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Hy3 | Mercury 2 | |
|---|---|---|
| Provider | Tencent | Inception |
| Noometry Index | 44.2 | 39.1 |
| Released | 2026-07-06 | 2026-02-20 |
| Weights | Open | Proprietary |
| Context window | 262K | 128K |
| Max output | 128K | 50K |
| Input $ / M tokens | $0.0825 | $0.25 |
| Output $ / M tokens | $0.33 | $0.75 |
| Results tracked | 19 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Mercury 2: 33.5 (#255)
| Benchmark | Hy3 | Mercury 2 |
|---|---|---|
| LMArena WebDev | 1508 | 1171 |
| LMArena Coding | 1464 | 1391 |
| SciCode | — | 38.7% |
| WeirdML | — | 43.2% |
| ALE-Bench | — | 785.58 |
Reasoning Hy3 leads
Hy3: 26.1 (#136), Mercury 2: 23.8 (#170)
| Benchmark | Hy3 | Mercury 2 |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1362 |
| NYT Connections (extended) | 41.2% | — |
| CritPt | — | 0.8% |
Math Not comparable
Hy3: 40.1 (#93), Mercury 2: —
| Benchmark | Hy3 | Mercury 2 |
|---|---|---|
| LMArena Math | 1475 | — |
Knowledge Hy3 leads
Hy3: 40.8 (#114), Mercury 2: 36.2 (#172)
| Benchmark | Hy3 | Mercury 2 |
|---|---|---|
| LMArena Expert | 1460 | 1358 |
| Vectara Hallucination Rate | — | 12.3% |
Multilingual Hy3 leads
Hy3: 53.5 (#65), Mercury 2: 46.6 (#157)
| Benchmark | Hy3 | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1426 | 1331 |
| LMArena Chinese | 1493 | 1417 |
| LMArena Russian | 1432 | 1304 |
| LMArena French | 1461 | — |
| LMArena German | 1439 | — |
| LMArena Japanese | 1392 | — |
| LMArena Korean | 1395 | — |
| LMArena Spanish | 1456 | — |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), Mercury 2: 70.2 (#165)
| Benchmark | Hy3 | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1426 | 1329 |
Long Context Hy3 leads
Hy3: 44.1 (#75), Mercury 2: 40.5 (#154)
| Benchmark | Hy3 | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1442 | 1330 |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), Mercury 2: 53.8 (#155)
| Benchmark | Hy3 | Mercury 2 |
|---|---|---|
| LMArena Text | 1439 | 1355 |
| LMArena Creative Writing | 1402 | 1289 |
| LMArena Multi-Turn | 1436 | 1358 |
Frequently asked questions
Is Hy3 better than Mercury 2?
Hy3 is the stronger model overall, scoring 44.2 to 39.1 on the Noometry Index.
Which is cheaper, Hy3 or Mercury 2?
Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; Mercury 2 lists at $0.25 and $0.75.
Is Hy3 or Mercury 2 better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Hy3 does, with 262K tokens against 128K.
How many benchmarks do Hy3 and Mercury 2 share?
12 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Mercury 2 has 17.