Model comparison
GPT-4.5 vs Hy3
Hy3 is the stronger model overall, scoring 44.2 to 37.2 on the Noometry Index.
Last verified . 16 shared benchmarks.
TencentSummary
- They share 16 benchmarks with published results for both. GPT-4.5 scores higher in 0 categories and Hy3 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Hy3 leads 26.1 to 13.9.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| GPT-4.5 | Hy3 | |
|---|---|---|
| Provider | OpenAI | Tencent |
| Noometry Index | 37.2 | 44.2 |
| Released | 2025-02-27 | 2026-07-06 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.0825 |
| Output $ / M tokens | — | $0.33 |
| Results tracked | 42 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
GPT-4.5: 42.2 (#109), Hy3: 46.8 (#63)
| Benchmark | GPT-4.5 | Hy3 |
|---|---|---|
| LMArena Coding | 1396 | 1464 |
| Aider Polyglot | 44.9% | — |
| LMArena WebDev | — | 1508 |
| WeirdML | 39.4% | — |
| LiveBench Coding | 75.2% | — |
Agentic & Tool Use Not comparable
GPT-4.5: 27.9 (#97), Hy3: —
| Benchmark | GPT-4.5 | Hy3 |
|---|---|---|
| Cybench | 17.5% | — |
Reasoning Hy3 leads
GPT-4.5: 13.9 (#330), Hy3: 26.1 (#136)
| Benchmark | GPT-4.5 | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1403 | 1447 |
| 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: 32.6 (#211), Hy3: 40.1 (#93)
| 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: 32.5 (#211), Hy3: 40.8 (#114)
| Benchmark | GPT-4.5 | Hy3 |
|---|---|---|
| LMArena Expert | 1394 | 1460 |
| GPQA Diamond | 68.7% | — |
| Humanity's Last Exam | 5.4% | — |
| Confabulations | 13.6% | — |
Multimodal Not comparable
GPT-4.5: 37.6 (#71), Hy3: —
| Benchmark | GPT-4.5 | Hy3 |
|---|---|---|
| LMArena Vision | 1195 | — |
| VPCT | 45% | — |
Multilingual Too close to call
GPT-4.5: 52.5 (#83), Hy3: 53.5 (#65)
| Benchmark | GPT-4.5 | Hy3 |
|---|---|---|
| LMArena Non-English | 1413 | 1426 |
| LMArena Chinese | 1421 | 1493 |
| LMArena French | 1418 | 1461 |
| LMArena German | 1457 | 1439 |
| LMArena Japanese | 1416 | 1392 |
| LMArena Korean | 1392 | 1395 |
| LMArena Russian | 1419 | 1432 |
| LMArena Spanish | — | 1456 |
Instruction Following Hy3 leads
GPT-4.5: 72.6 (#134), Hy3: 75.1 (#70)
| Benchmark | GPT-4.5 | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1404 | 1426 |
| LiveBench Instruction Following | 72.3% | — |
Long Context Hy3 leads
GPT-4.5: 40.4 (#155), Hy3: 44.1 (#75)
| Benchmark | GPT-4.5 | Hy3 |
|---|---|---|
| LMArena Longer Query | 1406 | 1442 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference Hy3 leads
GPT-4.5: 56.9 (#134), Hy3: 62.2 (#81)
| Benchmark | GPT-4.5 | Hy3 |
|---|---|---|
| LMArena Text | 1417 | 1439 |
| LMArena Creative Writing | 1394 | 1402 |
| 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 44.2 to 37.2 on the Noometry Index.
Is GPT-4.5 or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 42.2 in the Noometry coding category.
How many benchmarks do GPT-4.5 and Hy3 share?
16 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Hy3 has 19.