Model comparison
GPT-4.5 vs Hy3
Hy3 is the stronger model overall, scoring 43.6 to 36.9 on the Noometry Index.
Last verified . 14 shared benchmarks.
TencentSummary
- They share 14 benchmarks with published results for both. GPT-4.5 scores higher in 0 categories and Hy3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Hy3 leads 25.0 to 14.1.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| GPT-4.5 | Hy3 | |
|---|---|---|
| Provider | OpenAI | Tencent |
| Noometry Index | 36.9 | 43.6 |
| Released | 2025-02-27 | 2026-07-06 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.13 |
| Output $ / M tokens | — | $0.53 |
| Results tracked | 42 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
GPT-4.5: 41.8 (#102), Hy3: 46.6 (#60)
| Benchmark | GPT-4.5 | Hy3 |
|---|---|---|
| LMArena Coding | 1397 | 1465 |
| Aider Polyglot | 44.9% | — |
| LMArena WebDev | — | 1509 |
| WeirdML | 39.4% | — |
| LiveBench Coding | 75.2% | — |
Agentic & Tool Use Not comparable
GPT-4.5: 27.6 (#92), Hy3: —
| Benchmark | GPT-4.5 | Hy3 |
|---|---|---|
| Cybench | 17.5% | — |
Reasoning Hy3 leads
GPT-4.5: 14.1 (#320), Hy3: 25.0 (#134)
| Benchmark | GPT-4.5 | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1404 | 1449 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 34.5% | — |
| NYT Connections (extended) | — | 41.2% |
| ARC-AGI-1 | 10.3% | — |
| EnigmaEval | 3.2% | — |
| LiveBench Reasoning | 71.1% | — |
| LiveBench Data Analysis | 64.3% | — |
| Epoch Capabilities Index | 136.74 | — |
| ForecastBench | 61.7 | — |
| LiveBench | 69% | — |
Math Hy3 leads
GPT-4.5: 31.0 (#200), Hy3: 37.4 (#98)
| Benchmark | GPT-4.5 | Hy3 |
|---|---|---|
| LMArena Math | 1412 | 1475 |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| LiveBench Math | 69.3% | — |
| MATH Level 5 | 78.6% | — |
Knowledge Hy3 leads
GPT-4.5: 32.4 (#205), Hy3: 40.2 (#108)
| Benchmark | GPT-4.5 | Hy3 |
|---|---|---|
| LMArena Expert | 1394 | 1461 |
| GPQA Diamond | 68.7% | — |
| Humanity's Last Exam | 5.4% | — |
| Confabulations | 13.6% | — |
Multimodal Not comparable
GPT-4.5: 37.0 (#68), Hy3: —
| Benchmark | GPT-4.5 | Hy3 |
|---|---|---|
| LMArena Vision | 1195 | — |
| VPCT | 45% | — |
Multilingual Hy3 leads
GPT-4.5: 52.7 (#78), Hy3: 53.7 (#60)
| Benchmark | GPT-4.5 | Hy3 |
|---|---|---|
| LMArena Non-English | 1413 | 1427 |
| LMArena Chinese | 1421 | 1496 |
| LMArena French | 1417 | 1461 |
| LMArena Korean | 1392 | 1390 |
| LMArena Russian | 1419 | 1435 |
| LMArena German | 1457 | — |
| LMArena Japanese | 1416 | — |
| LMArena Spanish | — | 1448 |
Instruction Following Hy3 leads
GPT-4.5: 72.8 (#129), Hy3: 75.3 (#68)
| Benchmark | GPT-4.5 | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1404 | 1425 |
| LiveBench Instruction Following | 72.3% | — |
Long Context Hy3 leads
GPT-4.5: 40.4 (#150), Hy3: 44.1 (#70)
| Benchmark | GPT-4.5 | Hy3 |
|---|---|---|
| LMArena Longer Query | 1406 | 1443 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference Hy3 leads
GPT-4.5: 57.1 (#129), Hy3: 62.5 (#75)
| Benchmark | GPT-4.5 | Hy3 |
|---|---|---|
| LMArena Text | 1417 | 1442 |
| LMArena Creative Writing | 1394 | 1399 |
| LMArena Multi-Turn | 1444 | 1436 |
| Short-Story Creative Writing | 75.6% | — |
| EQ-Bench Creative Writing | 1258 | — |
| LiveBench Language | 61.5% | — |
Frequently asked questions
Is GPT-4.5 better than Hy3?
Hy3 is the stronger model overall, scoring 43.6 to 36.9 on the Noometry Index.
Is GPT-4.5 or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.6 versus 41.8 in the Noometry coding category.
How many benchmarks do GPT-4.5 and Hy3 share?
14 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Hy3 has 17.