Model comparison
Claude Opus 4.5 vs Hy3
Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 44.2 on the Noometry Index. Hy3 costs 69× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
TencentSummary
- They share 19 benchmarks with published results for both. Claude Opus 4.5 scores higher in 7 categories and Hy3 in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 4.5 leads 42.6 to 26.1.
- The biggest single-benchmark swing is NYT Connections (extended): 52.5% for Claude Opus 4.5 and 41.2% for Hy3.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $5 / $25 for Claude Opus 4.5.
- Hy3 accepts more context: 262K tokens versus 200K.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4.5 | Hy3 | |
|---|---|---|
| Provider | Anthropic | Tencent |
| Noometry Index | 50.5 | 44.2 |
| Released | 2025-11-01 | 2026-07-06 |
| Weights | Proprietary | Open |
| Context window | 200K | 262K |
| Max output | 64K | 128K |
| Input $ / M tokens | $5 | $0.0825 |
| Output $ / M tokens | $25 | $0.33 |
| Results tracked | 69 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.5 leads
Claude Opus 4.5: 54.8 (#27), Hy3: 46.8 (#63)
| Benchmark | Claude Opus 4.5 | Hy3 |
|---|---|---|
| LMArena WebDev | 1494 | 1508 |
| LMArena Coding | 1504 | 1464 |
| SWE-bench Verified | 76.7% | — |
| SWE-bench Verified (bash only) | 76.8% | — |
| SWE-bench Multilingual | 70.7% | — |
| GSO | 26.5% | — |
| WeirdML | 63.7% | — |
| ALE-Bench | 1,025 | — |
| AlgoTune | 1.77 | — |
Agentic & Tool Use Not comparable
Claude Opus 4.5: 47.3 (#12), Hy3: —
| Benchmark | Claude Opus 4.5 | Hy3 |
|---|---|---|
| Terminal-Bench | 63.1% | — |
| Berkeley Function Calling Leaderboard | 77.5% | — |
| GDPval | 45.5% | — |
| Remote Labor Index | 3.8% | — |
| τ²-bench Airline | 84% | — |
| τ²-bench Banking | 24.7% | — |
| τ²-bench Retail | 79.6% | — |
| τ²-bench Telecom | 92.3% | — |
| Cybench | 82% | — |
| DeepResearch Bench | 54.8% | — |
| OSWorld | 66.3% | — |
| BALROG | 43.5% | — |
| LMArena Search | 1180 | — |
| METR Time Horizons | 75% | — |
| Vending-Bench 2 | 4,967 | — |
Reasoning Claude Opus 4.5 leads
Claude Opus 4.5: 42.6 (#51), Hy3: 26.1 (#136)
| Benchmark | Claude Opus 4.5 | Hy3 |
|---|---|---|
| NYT Connections (extended) | 52.5% | 41.2% |
| LMArena Hard Prompts | 1476 | 1447 |
| ARC-AGI-2 | 37.6% | — |
| SimpleBench | 62% | — |
| Kagi LLM Benchmark | 80.2% | — |
| ARC-AGI-1 | 80% | — |
| Chess Puzzles | 12% | — |
| EnigmaEval | 11.9% | — |
| EBR-Bench | 14.3% | — |
| Mystery Game Puzzles | 22% | — |
| DTBench | 89.9% | — |
| LMCA | 44.5% | — |
| Epoch Capabilities Index | 150.09 | — |
| ForecastBench | 60.7 | — |
Math Hy3 leads
Claude Opus 4.5: 38.6 (#132), Hy3: 40.1 (#93)
| Benchmark | Claude Opus 4.5 | Hy3 |
|---|---|---|
| LMArena Math | 1463 | 1475 |
| FrontierMath (Tiers 1-3) | 34.4% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 86.1% | — |
| ProofBench | 36% | — |
| FrontierMath (Feb 2025 set) | 20.7% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Opus 4.5 leads
Claude Opus 4.5: 56.5 (#44), Hy3: 40.8 (#114)
| Benchmark | Claude Opus 4.5 | Hy3 |
|---|---|---|
| LMArena Expert | 1487 | 1460 |
| GPQA Diamond | 86% | — |
| Humanity's Last Exam | 25.2% | — |
| SimpleQA Verified | 45.7% | — |
| Vectara Hallucination Rate | 10.9% | — |
Multimodal Not comparable
Claude Opus 4.5: 31.4 (#107), Hy3: —
| Benchmark | Claude Opus 4.5 | Hy3 |
|---|---|---|
| GeoBench | 75% | — |
| VPCT | 40% | — |
| Furniture Assembly | 28.3% | — |
| LMArena Document | 1462 | — |
Multilingual Too close to call
Claude Opus 4.5: 54.3 (#47), Hy3: 53.5 (#65)
| Benchmark | Claude Opus 4.5 | Hy3 |
|---|---|---|
| LMArena Non-English | 1438 | 1426 |
| LMArena Chinese | 1470 | 1493 |
| LMArena French | 1471 | 1461 |
| LMArena German | 1449 | 1439 |
| LMArena Japanese | 1416 | 1392 |
| LMArena Korean | 1424 | 1395 |
| LMArena Russian | 1447 | 1432 |
| LMArena Spanish | 1458 | 1456 |
Instruction Following Claude Opus 4.5 leads
Claude Opus 4.5: 77.5 (#19), Hy3: 75.1 (#70)
| Benchmark | Claude Opus 4.5 | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1478 | 1426 |
Long Context Claude Opus 4.5 leads
Claude Opus 4.5: 46.5 (#22), Hy3: 44.1 (#75)
| Benchmark | Claude Opus 4.5 | Hy3 |
|---|---|---|
| LMArena Longer Query | 1480 | 1442 |
| CL-bench | 21.1% | — |
Writing & Preference Claude Opus 4.5 leads
Claude Opus 4.5: 68.1 (#28), Hy3: 62.2 (#81)
| Benchmark | Claude Opus 4.5 | Hy3 |
|---|---|---|
| LMArena Text | 1451 | 1439 |
| LMArena Creative Writing | 1445 | 1402 |
| LMArena Multi-Turn | 1466 | 1436 |
| EQ-Bench Creative Writing | 1687 | — |
Frequently asked questions
Is Claude Opus 4.5 better than Hy3?
Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 44.2 on the Noometry Index. Hy3 costs 69× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 4.5 or Hy3?
Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; Claude Opus 4.5 lists at $5 and $25.
Is Claude Opus 4.5 or Hy3 better for coding?
Claude Opus 4.5 scores higher on coding benchmarks: 54.8 versus 46.8 in the Noometry coding category.
Which has the bigger context window?
Hy3 does, with 262K tokens against 200K.
How many benchmarks do Claude Opus 4.5 and Hy3 share?
19 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and Hy3 has 19.