Model comparison
Hy4 preview vs o3
o3 is the stronger model overall, scoring 47.5 to 45.3 on the Noometry Index. Hy4 preview costs 3.1× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
TencentSummary
- The widest gap is in math, where Hy4 preview leads 55.7 to 50.2.
- Hy4 preview is cheaper at $0.75 / $2.25 per million input/output tokens, against $2 / $8 for o3.
- Hy4 preview accepts more context: 1.05M tokens versus 200K.
- Hy4 preview has downloadable open weights; the other is API-only.
Side by side
| Hy4 preview | o3 | |
|---|---|---|
| Provider | Tencent | OpenAI |
| Noometry Index | 45.3 | 47.5 |
| Released | 2026-08-28 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | 1.05M | 200K |
| Max output | 64K | 100K |
| Input $ / M tokens | $0.75 | $2 |
| Output $ / M tokens | $2.25 | $8 |
| Results tracked | 3 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Hy4 preview: 51.6 (#38), o3: 46.8 (#64)
| Benchmark | Hy4 preview | o3 |
|---|---|---|
| SWE-bench Verified | — | 62.3% |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| LMArena WebDev | 1632 | — |
| GSO | — | 8.8% |
| WeirdML | — | 52.4% |
| LMArena Coding | — | 1408 |
| CadEval | — | 74% |
| ALE-Bench | — | 933.55 |
Agentic & Tool Use Not comparable
Hy4 preview: —, o3: 34.5 (#44)
| Benchmark | Hy4 preview | o3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 30.8% |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |
Reasoning Too close to call
Hy4 preview: 31.9 (#79), o3: 32.0 (#78)
| Benchmark | Hy4 preview | o3 |
|---|---|---|
| ARC-AGI-2 | — | 6.5% |
| SimpleBench | — | 53.1% |
| Kagi LLM Benchmark | — | 67.6% |
| NYT Connections (extended) | 68.2% | — |
| ARC-AGI-1 | — | 60.8% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 38% |
| EnigmaEval | — | 13.1% |
| LMArena Hard Prompts | — | 1402 |
| Mystery Game Puzzles | — | 29% |
| DTBench | — | 84.8% |
| LMCA | — | 39.7% |
| Epoch Capabilities Index | — | 146.86 |
| ForecastBench | — | 62.5 |
Math Hy4 preview leads
Hy4 preview: 55.7 (#42), o3: 50.2 (#58)
| Benchmark | Hy4 preview | o3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 33.3% |
| OTIS Mock AIME 2024-2025 | — | 84.4% |
| ProofBench | 75% | — |
| Omni-MATH | — | 71.4% |
| LMArena Math | — | 1426 |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 18.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Not comparable
Hy4 preview: —, o3: 54.6 (#52)
| Benchmark | Hy4 preview | o3 |
|---|---|---|
| GPQA Diamond | — | 81.8% |
| Humanity's Last Exam | — | 20.3% |
| SimpleQA Verified | — | 49.4% |
| MMLU-Pro | — | 85.9% |
| Confabulations | — | 14.4% |
| GPQA (HELM) | — | 75.3% |
| LMArena Expert | — | 1402 |
Multimodal Not comparable
Hy4 preview: —, o3: 41.4 (#36)
| Benchmark | Hy4 preview | o3 |
|---|---|---|
| LMArena Vision | — | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |
Multilingual Not comparable
Hy4 preview: —, o3: 51.7 (#105)
| Benchmark | Hy4 preview | o3 |
|---|---|---|
| LMArena Non-English | — | 1401 |
| LMArena Chinese | — | 1437 |
| LMArena French | — | 1430 |
| LMArena German | — | 1420 |
| LMArena Japanese | — | 1403 |
| LMArena Korean | — | 1370 |
| LMArena Russian | — | 1406 |
| LMArena Spanish | — | 1395 |
Instruction Following Not comparable
Hy4 preview: —, o3: 72.8 (#127)
| Benchmark | Hy4 preview | o3 |
|---|---|---|
| IFEval | — | 86.9% |
| LMArena Instruction Following | — | 1368 |
Long Context Not comparable
Hy4 preview: —, o3: 53.3 (#6)
| Benchmark | Hy4 preview | o3 |
|---|---|---|
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |
| LMArena Longer Query | — | 1372 |
Writing & Preference Not comparable
Hy4 preview: —, o3: 63.5 (#64)
| Benchmark | Hy4 preview | o3 |
|---|---|---|
| LMArena Text | — | 1410 |
| LMArena Creative Writing | — | 1359 |
| Short-Story Creative Writing | — | 83.9% |
| EQ-Bench Creative Writing | — | 1676 |
| WildBench | — | 86.1% |
| LMArena Multi-Turn | — | 1405 |
Frequently asked questions
Is Hy4 preview better than o3?
o3 is the stronger model overall, scoring 47.5 to 45.3 on the Noometry Index. Hy4 preview costs 3.1× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Which is cheaper, Hy4 preview or o3?
Hy4 preview is cheaper. It lists at $0.75 per million input tokens and $2.25 per million output tokens; o3 lists at $2 and $8.
Is Hy4 preview or o3 better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 46.8 in the Noometry coding category.
Which has the bigger context window?
Hy4 preview does, with 1.05M tokens against 200K.
How many benchmarks do Hy4 preview and o3 share?
0 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and o3 has 63.