Model comparison
gpt-oss-20b vs Hy4 preview
Hy4 preview is the stronger model overall, scoring 45.3 to 32.5 on the Noometry Index. gpt-oss-20b costs 35× less per token, which makes it the better buy when Hy4 preview'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 39.4.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.83 / $2.50 for Hy4 preview.
- Hy4 preview accepts more context: 1.05M tokens versus 131K.
Side by side
| gpt-oss-20b | Hy4 preview | |
|---|---|---|
| Provider | OpenAI | Tencent |
| Noometry Index | 32.5 | 45.3 |
| Released | 2025-08-05 | 2026-08-28 |
| Weights | Open | Open |
| Context window | 131K | 1.05M |
| Max output | 16K | 64K |
| Input $ / M tokens | $0.018 | $0.83 |
| Output $ / M tokens | $0.09 | $2.50 |
| Results tracked | 34 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
gpt-oss-20b: 37.6 (#192), Hy4 preview: 51.6 (#38)
| Benchmark | gpt-oss-20b | Hy4 preview |
|---|---|---|
| LMArena WebDev | — | 1632 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| LMArena Coding | 1306 | — |
| ALE-Bench | 566.05 | — |
Agentic & Tool Use Not comparable
gpt-oss-20b: 9.3 (#154), Hy4 preview: —
| Benchmark | gpt-oss-20b | Hy4 preview |
|---|---|---|
| Terminal-Bench | 3.4% | — |
Reasoning Hy4 preview leads
gpt-oss-20b: 19.3 (#261), Hy4 preview: 31.9 (#79)
| Benchmark | gpt-oss-20b | Hy4 preview |
|---|---|---|
| Kagi LLM Benchmark | 53.2% | — |
| NYT Connections (extended) | — | 68.2% |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| LMArena Hard Prompts | 1274 | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |
| Epoch Capabilities Index | 137.82 | — |
Math Hy4 preview leads
gpt-oss-20b: 39.4 (#103), Hy4 preview: 55.7 (#42)
| Benchmark | gpt-oss-20b | Hy4 preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| ProofBench | — | 75% |
| Omni-MATH | 56.5% | — |
| LMArena Math | 1317 | — |
Knowledge Not comparable
gpt-oss-20b: 34.6 (#195), Hy4 preview: —
| Benchmark | gpt-oss-20b | Hy4 preview |
|---|---|---|
| GPQA Diamond | 60.8% | — |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
| LMArena Expert | 1258 | — |
Multilingual Not comparable
gpt-oss-20b: 42.2 (#197), Hy4 preview: —
| Benchmark | gpt-oss-20b | Hy4 preview |
|---|---|---|
| LMArena Non-English | 1268 | — |
| LMArena Chinese | 1314 | — |
| LMArena German | 1255 | — |
| LMArena Japanese | 1244 | — |
| LMArena Korean | 1236 | — |
| LMArena Russian | 1278 | — |
| LMArena Spanish | 1267 | — |
Instruction Following Not comparable
gpt-oss-20b: 61.8 (#240), Hy4 preview: —
| Benchmark | gpt-oss-20b | Hy4 preview |
|---|---|---|
| IFEval | 73.2% | — |
| LMArena Instruction Following | 1236 | — |
Long Context Not comparable
gpt-oss-20b: 37.9 (#209), Hy4 preview: —
| Benchmark | gpt-oss-20b | Hy4 preview |
|---|---|---|
| LMArena Longer Query | 1250 | — |
Writing & Preference Not comparable
gpt-oss-20b: 35.5 (#265), Hy4 preview: —
| Benchmark | gpt-oss-20b | Hy4 preview |
|---|---|---|
| LMArena Text | 1287 | — |
| LMArena Creative Writing | 1201 | — |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
| LMArena Multi-Turn | 1268 | — |
Frequently asked questions
Is gpt-oss-20b better than Hy4 preview?
Hy4 preview is the stronger model overall, scoring 45.3 to 32.5 on the Noometry Index. gpt-oss-20b costs 35× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-20b or Hy4 preview?
gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Hy4 preview lists at $0.83 and $2.50.
Is gpt-oss-20b or Hy4 preview better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 37.6 in the Noometry coding category.
Which has the bigger context window?
Hy4 preview does, with 1.05M tokens against 131K.
How many benchmarks do gpt-oss-20b and Hy4 preview share?
0 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Hy4 preview has 3.