Model comparison
Hy3 vs Mercury
Hy3 is the stronger model overall, scoring 43.6 to 37.3 on the Noometry Index.
Last verified . 8 shared benchmarks.
TencentSummary
- They share 8 benchmarks with published results for both. Hy3 scores higher in 6 categories and Mercury in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hy3 leads 62.5 to 46.2.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Hy3 | Mercury | |
|---|---|---|
| Provider | Tencent | Inception |
| Noometry Index | 43.6 | 37.3 |
| Released | 2026-07-06 | — |
| Weights | Open | Proprietary |
| Context window | 262K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.13 | — |
| Output $ / M tokens | $0.53 | — |
| Results tracked | 17 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.6 (#60), Mercury: 38.1 (#164)
| Benchmark | Hy3 | Mercury |
|---|---|---|
| LMArena Coding | 1465 | 1323 |
| LMArena WebDev | 1509 | — |
Reasoning Hy3 leads
Hy3: 25.0 (#134), Mercury: 16.8 (#288)
| Benchmark | Hy3 | Mercury |
|---|---|---|
| LMArena Hard Prompts | 1449 | 1284 |
| Kagi LLM Benchmark | — | 21.6% |
| NYT Connections (extended) | 41.2% | — |
Math Not comparable
Hy3: 37.4 (#98), Mercury: —
| Benchmark | Hy3 | Mercury |
|---|---|---|
| LMArena Math | 1475 | — |
Knowledge Not comparable
Hy3: 40.2 (#108), Mercury: —
| Benchmark | Hy3 | Mercury |
|---|---|---|
| LMArena Expert | 1461 | — |
Multilingual Hy3 leads
Hy3: 53.7 (#60), Mercury: 41.7 (#201)
| Benchmark | Hy3 | Mercury |
|---|---|---|
| LMArena Non-English | 1427 | 1259 |
| LMArena Chinese | 1496 | — |
| LMArena French | 1461 | — |
| LMArena Korean | 1390 | — |
| LMArena Russian | 1435 | — |
| LMArena Spanish | 1448 | — |
Instruction Following Hy3 leads
Hy3: 75.3 (#68), Mercury: 65.3 (#220)
| Benchmark | Hy3 | Mercury |
|---|---|---|
| LMArena Instruction Following | 1425 | 1238 |
Long Context Hy3 leads
Hy3: 44.1 (#70), Mercury: 38.3 (#193)
| Benchmark | Hy3 | Mercury |
|---|---|---|
| LMArena Longer Query | 1443 | 1264 |
Writing & Preference Hy3 leads
Hy3: 62.5 (#75), Mercury: 46.2 (#216)
| Benchmark | Hy3 | Mercury |
|---|---|---|
| LMArena Text | 1442 | 1282 |
| LMArena Creative Writing | 1399 | 1186 |
| LMArena Multi-Turn | 1436 | 1283 |
Frequently asked questions
Is Hy3 better than Mercury?
Hy3 is the stronger model overall, scoring 43.6 to 37.3 on the Noometry Index.
Is Hy3 or Mercury better for coding?
Hy3 scores higher on coding benchmarks: 46.6 versus 38.1 in the Noometry coding category.
How many benchmarks do Hy3 and Mercury share?
8 benchmarks have published results for both models. Hy3 has 17 scored results on Noometry and Mercury has 9.