Model comparison
GPT-5.2 Pro vs Hy3
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 44.2 on the Noometry Index. Hy3 costs 400× less per token, which makes it the better buy when GPT-5.2 Pro's lead doesn't matter for your workload.
Last verified . 1 shared benchmarks.
TencentSummary
- They share 1 benchmark with published results for both. GPT-5.2 Pro scores higher in 2 categories and Hy3 in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.2 Pro leads 51.5 to 26.1.
- The biggest single-benchmark swing is NYT Connections (extended): 79.3% for GPT-5.2 Pro and 41.2% for Hy3.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $21 / $168 for GPT-5.2 Pro.
- GPT-5.2 Pro accepts more context: 400K tokens versus 262K.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| GPT-5.2 Pro | Hy3 | |
|---|---|---|
| Provider | OpenAI | Tencent |
| Noometry Index | 52.3 | 44.2 |
| Released | 2025-12-11 | 2026-07-06 |
| Weights | Proprietary | Open |
| Context window | 400K | 262K |
| Max output | 128K | 128K |
| Input $ / M tokens | $21 | $0.0825 |
| Output $ / M tokens | $168 | $0.33 |
| Results tracked | 8 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-5.2 Pro: —, Hy3: 46.8 (#63)
| Benchmark | GPT-5.2 Pro | Hy3 |
|---|---|---|
| LMArena WebDev | — | 1508 |
| LMArena Coding | — | 1464 |
Reasoning GPT-5.2 Pro leads
GPT-5.2 Pro: 51.5 (#33), Hy3: 26.1 (#136)
| Benchmark | GPT-5.2 Pro | Hy3 |
|---|---|---|
| NYT Connections (extended) | 79.3% | 41.2% |
| ARC-AGI-2 | 54.2% | — |
| SimpleBench | 57.4% | — |
| ARC-AGI-1 | 90.5% | — |
| LMArena Hard Prompts | — | 1447 |
| Epoch Capabilities Index | 155.4 | — |
Math GPT-5.2 Pro leads
GPT-5.2 Pro: 65.3 (#29), Hy3: 40.1 (#93)
| Benchmark | GPT-5.2 Pro | Hy3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 74% | — |
| FrontierMath Tier 4 | 46% | — |
| LMArena Math | — | 1475 |
| FrontierMath Tier 4 (v1) | 31.3% | — |
Knowledge Not comparable
GPT-5.2 Pro: —, Hy3: 40.8 (#114)
| Benchmark | GPT-5.2 Pro | Hy3 |
|---|---|---|
| LMArena Expert | — | 1460 |
Multilingual Not comparable
GPT-5.2 Pro: —, Hy3: 53.5 (#65)
| Benchmark | GPT-5.2 Pro | Hy3 |
|---|---|---|
| LMArena Non-English | — | 1426 |
| LMArena Chinese | — | 1493 |
| LMArena French | — | 1461 |
| LMArena German | — | 1439 |
| LMArena Japanese | — | 1392 |
| LMArena Korean | — | 1395 |
| LMArena Russian | — | 1432 |
| LMArena Spanish | — | 1456 |
Instruction Following Not comparable
GPT-5.2 Pro: —, Hy3: 75.1 (#70)
| Benchmark | GPT-5.2 Pro | Hy3 |
|---|---|---|
| LMArena Instruction Following | — | 1426 |
Long Context Not comparable
GPT-5.2 Pro: —, Hy3: 44.1 (#75)
| Benchmark | GPT-5.2 Pro | Hy3 |
|---|---|---|
| LMArena Longer Query | — | 1442 |
Writing & Preference Not comparable
GPT-5.2 Pro: —, Hy3: 62.2 (#81)
| Benchmark | GPT-5.2 Pro | Hy3 |
|---|---|---|
| LMArena Text | — | 1439 |
| LMArena Creative Writing | — | 1402 |
| LMArena Multi-Turn | — | 1436 |
Frequently asked questions
Is GPT-5.2 Pro better than Hy3?
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 44.2 on the Noometry Index. Hy3 costs 400× less per token, which makes it the better buy when GPT-5.2 Pro's lead doesn't matter for your workload.
Which is cheaper, GPT-5.2 Pro or Hy3?
Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; GPT-5.2 Pro lists at $21 and $168.
Which has the bigger context window?
GPT-5.2 Pro does, with 400K tokens against 262K.
How many benchmarks do GPT-5.2 Pro and Hy3 share?
1 benchmark has published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and Hy3 has 19.