Model comparison
Claude Sonnet 4.5 vs Hy3
Claude Sonnet 4.5 and Hy3 score almost the same on the Noometry Index (44.1 vs 44.2), so choose on price, context window or the category you care about most.
Last verified . 19 shared benchmarks.
TencentSummary
- They share 19 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 5 categories and Hy3 in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Hy3 leads 40.1 to 32.3.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
- Hy3 accepts more context: 262K tokens versus 200K.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4.5 | Hy3 | |
|---|---|---|
| Provider | Anthropic | Tencent |
| Noometry Index | 44.1 | 44.2 |
| Released | 2025-09-29 | 2026-07-06 |
| Weights | Proprietary | Open |
| Context window | 200K | 262K |
| Max output | 64K | 128K |
| Input $ / M tokens | $3 | $0.0825 |
| Output $ / M tokens | $15 | $0.33 |
| Results tracked | 73 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude Sonnet 4.5: 47.3 (#61), Hy3: 46.8 (#63)
| Benchmark | Claude Sonnet 4.5 | Hy3 |
|---|---|---|
| LMArena WebDev | 1393 | 1508 |
| LMArena Coding | 1489 | 1464 |
| SWE-bench Verified | 71.3% | — |
| SWE-bench Verified (bash only) | 71.4% | — |
| SWE-bench Multilingual | 67% | — |
| SciCode | 44.7% | — |
| GSO | 14.7% | — |
| WeirdML | 47.7% | — |
| ALE-Bench | 796.15 | — |
| AlgoTune | 1.52 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4.5: 38.3 (#32), Hy3: —
| Benchmark | Claude Sonnet 4.5 | Hy3 |
|---|---|---|
| Terminal-Bench | 46.5% | — |
| Berkeley Function Calling Leaderboard | 73.2% | — |
| GDPval | 42.5% | — |
| Remote Labor Index | 2.1% | — |
| τ²-bench Airline | 72% | — |
| τ²-bench Banking | 25.3% | — |
| τ²-bench Retail | 72.4% | — |
| τ²-bench Telecom | 84.9% | — |
| Cybench | 60% | — |
| DeepResearch Bench | 52.6% | — |
| OSWorld | 62.9% | — |
| LMArena Search | 1159 | — |
| METR Time Horizons | 67.4% | — |
| Vending-Bench 2 | 3,839 | — |
Reasoning Too close to call
Claude Sonnet 4.5: 26.9 (#125), Hy3: 26.1 (#136)
| Benchmark | Claude Sonnet 4.5 | Hy3 |
|---|---|---|
| NYT Connections (extended) | 37.3% | 41.2% |
| LMArena Hard Prompts | 1462 | 1447 |
| ARC-AGI-2 | 13.6% | — |
| SimpleBench | 54.3% | — |
| Kagi LLM Benchmark | 57.9% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 12% | — |
| EnigmaEval | 6% | — |
| EBR-Bench | 2.4% | — |
| Mystery Game Puzzles | 17% | — |
| DTBench | 83.2% | — |
| LMCA | 38.8% | — |
| Epoch Capabilities Index | 146.84 | — |
| ForecastBench | 61.9 | — |
Math Hy3 leads
Claude Sonnet 4.5: 32.3 (#216), Hy3: 40.1 (#93)
| Benchmark | Claude Sonnet 4.5 | Hy3 |
|---|---|---|
| LMArena Math | 1449 | 1475 |
| FrontierMath (Tiers 1-3) | 23.9% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| ProofBench | 19% | — |
| Omni-MATH | 55.3% | — |
| MATH Level 5 | 97.7% | — |
| FrontierMath (Feb 2025 set) | 15.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 48.4 (#76), Hy3: 40.8 (#114)
| Benchmark | Claude Sonnet 4.5 | Hy3 |
|---|---|---|
| LMArena Expert | 1482 | 1460 |
| GPQA Diamond | 82.3% | — |
| Humanity's Last Exam | 13.7% | — |
| SimpleQA Verified | 30.7% | — |
| MMLU-Pro | 86.9% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 68.6% | — |
Multimodal Not comparable
Claude Sonnet 4.5: 34.8 (#89), Hy3: —
| Benchmark | Claude Sonnet 4.5 | Hy3 |
|---|---|---|
| VPCT | 39.8% | — |
| LMArena Document | 1450 | — |
Multilingual Too close to call
Claude Sonnet 4.5: 53.4 (#69), Hy3: 53.5 (#65)
| Benchmark | Claude Sonnet 4.5 | Hy3 |
|---|---|---|
| LMArena Non-English | 1425 | 1426 |
| LMArena Chinese | 1459 | 1493 |
| LMArena French | 1458 | 1461 |
| LMArena German | 1427 | 1439 |
| LMArena Japanese | 1390 | 1392 |
| LMArena Korean | 1403 | 1395 |
| LMArena Russian | 1437 | 1432 |
| LMArena Spanish | 1457 | 1456 |
Instruction Following Too close to call
Claude Sonnet 4.5: 75.0 (#78), Hy3: 75.1 (#70)
| Benchmark | Claude Sonnet 4.5 | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1459 | 1426 |
| IFEval | 85% | — |
Long Context Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 45.2 (#46), Hy3: 44.1 (#75)
| Benchmark | Claude Sonnet 4.5 | Hy3 |
|---|---|---|
| LMArena Longer Query | 1476 | 1442 |
Writing & Preference Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 66.5 (#34), Hy3: 62.2 (#81)
| Benchmark | Claude Sonnet 4.5 | Hy3 |
|---|---|---|
| LMArena Text | 1439 | 1439 |
| LMArena Creative Writing | 1442 | 1402 |
| LMArena Multi-Turn | 1465 | 1436 |
| EQ-Bench Creative Writing | 1678 | — |
| WildBench | 85.4% | — |
Frequently asked questions
Is Claude Sonnet 4.5 better than Hy3?
Claude Sonnet 4.5 and Hy3 score almost the same on the Noometry Index (44.1 vs 44.2), so choose on price, context window or the category you care about most.
Which is cheaper, Claude Sonnet 4.5 or Hy3?
Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.
Is Claude Sonnet 4.5 or Hy3 better for coding?
They score almost the same on coding (47.3 vs 46.8); test both on your own repository before choosing.
Which has the bigger context window?
Hy3 does, with 262K tokens against 200K.
How many benchmarks do Claude Sonnet 4.5 and Hy3 share?
19 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Hy3 has 19.