Model comparison
GPT-6 Luna vs Hy3
GPT-6 Luna is the stronger model overall, scoring 45.1 to 43.6 on the Noometry Index.
Last verified . 15 shared benchmarks.
TencentSummary
- They share 15 benchmarks with published results for both. GPT-6 Luna scores higher in 2 categories and Hy3 in 6 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in coding, where GPT-6 Luna leads 54.7 to 46.6.
- The biggest single-benchmark swing is NYT Connections (extended): 68.7% for GPT-6 Luna and 41.2% for Hy3.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.13 / $0.53 for Hy3.
- GPT-6 Luna accepts more context: 1.05M tokens versus 262K.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Luna | Hy3 | |
|---|---|---|
| Provider | OpenAI | Tencent |
| Noometry Index | 45.1 | 43.6 |
| Released | 2026-09-22 | 2026-07-06 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 128K | 128K |
| Input $ / M tokens | $0.10 | $0.13 |
| Output $ / M tokens | $0.50 | $0.53 |
| Results tracked | 18 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Luna leads
GPT-6 Luna: 54.7 (#24), Hy3: 46.6 (#60)
| Benchmark | GPT-6 Luna | Hy3 |
|---|---|---|
| LMArena WebDev | 1583 | 1509 |
| LMArena Coding | 1448 | 1465 |
| DeepSWE | 66.6% | — |
| FrontierCode | 42.4% | — |
Reasoning GPT-6 Luna leads
GPT-6 Luna: 31.7 (#68), Hy3: 25.0 (#134)
| Benchmark | GPT-6 Luna | Hy3 |
|---|---|---|
| NYT Connections (extended) | 68.7% | 41.2% |
| LMArena Hard Prompts | 1415 | 1449 |
Math Hy3 leads
GPT-6 Luna: 35.6 (#140), Hy3: 37.4 (#98)
| Benchmark | GPT-6 Luna | Hy3 |
|---|---|---|
| LMArena Math | 1396 | 1475 |
Knowledge Too close to call
GPT-6 Luna: 40.1 (#110), Hy3: 40.2 (#108)
| Benchmark | GPT-6 Luna | Hy3 |
|---|---|---|
| LMArena Expert | 1458 | 1461 |
Multimodal Not comparable
GPT-6 Luna: 42.0 (#27), Hy3: —
| Benchmark | GPT-6 Luna | Hy3 |
|---|---|---|
| Furniture Assembly | 44.2% | — |
Multilingual Hy3 leads
GPT-6 Luna: 51.0 (#111), Hy3: 53.7 (#60)
| Benchmark | GPT-6 Luna | Hy3 |
|---|---|---|
| LMArena Non-English | 1390 | 1427 |
| LMArena Chinese | 1425 | 1496 |
| LMArena Russian | 1392 | 1435 |
| LMArena Spanish | 1416 | 1448 |
| LMArena French | — | 1461 |
| LMArena Korean | — | 1390 |
Instruction Following Too close to call
GPT-6 Luna: 74.7 (#85), Hy3: 75.3 (#68)
| Benchmark | GPT-6 Luna | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1414 | 1425 |
Long Context Too close to call
GPT-6 Luna: 43.3 (#95), Hy3: 44.1 (#70)
| Benchmark | GPT-6 Luna | Hy3 |
|---|---|---|
| LMArena Longer Query | 1417 | 1443 |
Writing & Preference Hy3 leads
GPT-6 Luna: 58.4 (#115), Hy3: 62.5 (#75)
| Benchmark | GPT-6 Luna | Hy3 |
|---|---|---|
| LMArena Text | 1392 | 1442 |
| LMArena Creative Writing | 1357 | 1399 |
| LMArena Multi-Turn | 1400 | 1436 |
Frequently asked questions
Is GPT-6 Luna better than Hy3?
GPT-6 Luna is the stronger model overall, scoring 45.1 to 43.6 on the Noometry Index.
Which is cheaper, GPT-6 Luna or Hy3?
GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Hy3 lists at $0.13 and $0.53.
Is GPT-6 Luna or Hy3 better for coding?
GPT-6 Luna scores higher on coding benchmarks: 54.7 versus 46.6 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Luna does, with 1.05M tokens against 262K.
How many benchmarks do GPT-6 Luna and Hy3 share?
15 benchmarks have published results for both models. GPT-6 Luna has 18 scored results on Noometry and Hy3 has 17.