Model comparison
Hy3 vs o1
Hy3 is the stronger model overall, scoring 44.2 to 40.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
TencentSummary
- They share 17 benchmarks with published results for both. Hy3 scores higher in 5 categories and o1 in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hy3 leads 62.2 to 55.6.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $15 / $60 for o1.
- Hy3 accepts more context: 262K tokens versus 200K.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Hy3 | o1 | |
|---|---|---|
| Provider | Tencent | OpenAI |
| Noometry Index | 44.2 | 40.9 |
| Released | 2026-07-06 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 262K | 200K |
| Max output | 128K | 100K |
| Input $ / M tokens | $0.0825 | $15 |
| Output $ / M tokens | $0.33 | $60 |
| Results tracked | 19 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Hy3: 46.8 (#63), o1: 46.1 (#70)
| Benchmark | Hy3 | o1 |
|---|---|---|
| LMArena Coding | 1464 | 1367 |
| Aider Polyglot | — | 61.7% |
| LMArena WebDev | 1508 | — |
| WeirdML | — | 47.6% |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use Not comparable
Hy3: —, o1: 24.6 (#117)
| Benchmark | Hy3 | o1 |
|---|---|---|
| Cybench | — | 10% |
| METR Time Horizons | — | 51.1% |
Reasoning o1 leads
Hy3: 26.1 (#136), o1: 27.9 (#111)
| Benchmark | Hy3 | o1 |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1371 |
| SimpleBench | — | 41.7% |
| NYT Connections (extended) | 41.2% | — |
| ARC-AGI-1 | — | 30.7% |
| Chess Puzzles | — | 15% |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| DTBench | — | 74.7% |
| LiveBench Data Analysis | — | 65.5% |
| LMCA | — | 22.3% |
| Epoch Capabilities Index | — | 141.91 |
| LiveBench | — | 75.7% |
Math Hy3 leads
Hy3: 40.1 (#93), o1: 36.1 (#175)
| Benchmark | Hy3 | o1 |
|---|---|---|
| LMArena Math | 1475 | 1388 |
| FrontierMath (Tiers 1-3) | — | 14.7% |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| LiveBench Math | — | 80.3% |
| MATH Level 5 | — | 94.7% |
| FrontierMath (Feb 2025 set) | — | 9.3% |
Knowledge Too close to call
Hy3: 40.8 (#114), o1: 41.5 (#110)
| Benchmark | Hy3 | o1 |
|---|---|---|
| LMArena Expert | 1460 | 1361 |
| GPQA Diamond | — | 76.8% |
| Humanity's Last Exam | — | 8% |
| SimpleQA Verified | — | 41.1% |
| Confabulations | — | 11.7% |
Multimodal Not comparable
Hy3: —, o1: 34.2 (#93)
| Benchmark | Hy3 | o1 |
|---|---|---|
| LMArena Vision | — | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| SpatialViz-Bench | — | 41.4% |
Multilingual Hy3 leads
Hy3: 53.5 (#65), o1: 48.6 (#142)
| Benchmark | Hy3 | o1 |
|---|---|---|
| LMArena Non-English | 1426 | 1358 |
| LMArena Chinese | 1493 | 1394 |
| LMArena French | 1461 | 1344 |
| LMArena German | 1439 | 1337 |
| LMArena Japanese | 1392 | 1346 |
| LMArena Korean | 1395 | 1396 |
| LMArena Russian | 1432 | 1356 |
| LMArena Spanish | 1456 | 1345 |
Instruction Following Too close to call
Hy3: 75.1 (#70), o1: 74.8 (#86)
| Benchmark | Hy3 | o1 |
|---|---|---|
| LMArena Instruction Following | 1426 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
Long Context o1 leads
Hy3: 44.1 (#75), o1: 50.3 (#9)
| Benchmark | Hy3 | o1 |
|---|---|---|
| LMArena Longer Query | 1442 | 1378 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), o1: 55.6 (#144)
| Benchmark | Hy3 | o1 |
|---|---|---|
| LMArena Text | 1439 | 1366 |
| LMArena Creative Writing | 1402 | 1348 |
| LMArena Multi-Turn | 1436 | 1369 |
| Short-Story Creative Writing | — | 70.2% |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is Hy3 better than o1?
Hy3 is the stronger model overall, scoring 44.2 to 40.9 on the Noometry Index.
Which is cheaper, Hy3 or o1?
Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; o1 lists at $15 and $60.
Is Hy3 or o1 better for coding?
They score almost the same on coding (46.8 vs 46.1); 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 Hy3 and o1 share?
17 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and o1 has 52.