Model comparison
GPT-5 Pro vs Hy3
GPT-5 Pro is the stronger model overall, scoring 46.2 to 43.6 on the Noometry Index. Hy3 costs 179× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
TencentSummary
- The widest gap is in knowledge, where GPT-5 Pro leads 56.2 to 40.2.
- Hy3 is cheaper at $0.13 / $0.53 per million input/output tokens, against $15 / $120 for GPT-5 Pro.
- GPT-5 Pro accepts more context: 400K tokens versus 262K.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Pro | Hy3 | |
|---|---|---|
| Provider | OpenAI | Tencent |
| Noometry Index | 46.2 | 43.6 |
| Released | 2025-10-06 | 2026-07-06 |
| Weights | Proprietary | Open |
| Context window | 400K | 262K |
| Max output | 272K | 128K |
| Input $ / M tokens | $15 | $0.13 |
| Output $ / M tokens | $120 | $0.53 |
| Results tracked | 12 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
GPT-5 Pro: 43.4 (#77), Hy3: 46.6 (#60)
| Benchmark | GPT-5 Pro | Hy3 |
|---|---|---|
| LMArena WebDev | — | 1509 |
| WeirdML | 60.4% | — |
| LMArena Coding | — | 1465 |
| AlgoTune | 1.31 | — |
Reasoning GPT-5 Pro leads
GPT-5 Pro: 39.2 (#52), Hy3: 25.0 (#134)
| Benchmark | GPT-5 Pro | Hy3 |
|---|---|---|
| ARC-AGI-2 | 18.3% | — |
| SimpleBench | 61.6% | — |
| Kagi LLM Benchmark | 76.8% | — |
| NYT Connections (extended) | — | 41.2% |
| ARC-AGI-1 | 70.2% | — |
| EnigmaEval | 18.8% | — |
| LMArena Hard Prompts | — | 1449 |
| Epoch Capabilities Index | 150.26 | — |
Math GPT-5 Pro leads
GPT-5 Pro: 48.0 (#53), Hy3: 37.4 (#98)
| Benchmark | GPT-5 Pro | Hy3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 55.8% | — |
| FrontierMath Tier 4 | 19.5% | — |
| LMArena Math | — | 1475 |
| FrontierMath Tier 4 (v1) | 14.6% | — |
Knowledge GPT-5 Pro leads
GPT-5 Pro: 56.2 (#39), Hy3: 40.2 (#108)
| Benchmark | GPT-5 Pro | Hy3 |
|---|---|---|
| Humanity's Last Exam | 31.6% | — |
| LMArena Expert | — | 1461 |
Multilingual Not comparable
GPT-5 Pro: —, Hy3: 53.7 (#60)
| Benchmark | GPT-5 Pro | Hy3 |
|---|---|---|
| LMArena Non-English | — | 1427 |
| LMArena Chinese | — | 1496 |
| LMArena French | — | 1461 |
| LMArena Korean | — | 1390 |
| LMArena Russian | — | 1435 |
| LMArena Spanish | — | 1448 |
Instruction Following Not comparable
GPT-5 Pro: —, Hy3: 75.3 (#68)
| Benchmark | GPT-5 Pro | Hy3 |
|---|---|---|
| LMArena Instruction Following | — | 1425 |
Long Context Not comparable
GPT-5 Pro: —, Hy3: 44.1 (#70)
| Benchmark | GPT-5 Pro | Hy3 |
|---|---|---|
| LMArena Longer Query | — | 1443 |
Writing & Preference Not comparable
GPT-5 Pro: —, Hy3: 62.5 (#75)
| Benchmark | GPT-5 Pro | Hy3 |
|---|---|---|
| LMArena Text | — | 1442 |
| LMArena Creative Writing | — | 1399 |
| LMArena Multi-Turn | — | 1436 |
Frequently asked questions
Is GPT-5 Pro better than Hy3?
GPT-5 Pro is the stronger model overall, scoring 46.2 to 43.6 on the Noometry Index. Hy3 costs 179× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.
Which is cheaper, GPT-5 Pro or Hy3?
Hy3 is cheaper. It lists at $0.13 per million input tokens and $0.53 per million output tokens; GPT-5 Pro lists at $15 and $120.
Is GPT-5 Pro or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.6 versus 43.4 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Pro does, with 400K tokens against 262K.
How many benchmarks do GPT-5 Pro and Hy3 share?
0 benchmarks have published results for both models. GPT-5 Pro has 12 scored results on Noometry and Hy3 has 17.