Model comparison
GPT-5.4 nano vs Hy4 preview
Hy4 preview is the stronger model overall, scoring 44.6 to 41.9 on the Noometry Index. GPT-5.4 nano costs 2.7× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.
Last verified . 1 shared benchmarks.
TencentSummary
- They share 1 benchmark with published results for both. GPT-5.4 nano scores higher in 0 categories and Hy4 preview in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Hy4 preview leads 54.5 to 40.7.
- The biggest single-benchmark swing is ProofBench: 5% for GPT-5.4 nano and 75% for Hy4 preview.
- GPT-5.4 nano is cheaper at $0.20 / $1.25 per million input/output tokens, against $0.83 / $2.50 for Hy4 preview.
- Hy4 preview accepts more context: 1.05M tokens versus 400K.
- Hy4 preview has downloadable open weights; the other is API-only.
Side by side
| GPT-5.4 nano | Hy4 preview | |
|---|---|---|
| Provider | OpenAI | Tencent |
| Noometry Index | 41.9 | 44.6 |
| Released | 2026-03-17 | 2026-08-28 |
| Weights | Proprietary | Open |
| Context window | 400K | 1.05M |
| Max output | 128K | 64K |
| Input $ / M tokens | $0.20 | $0.83 |
| Output $ / M tokens | $1.25 | $2.50 |
| Results tracked | 40 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
GPT-5.4 nano: 43.1 (#82), Hy4 preview: 51.4 (#36)
| Benchmark | GPT-5.4 nano | Hy4 preview |
|---|---|---|
| LMArena WebDev | — | 1633 |
| SciCode | 46.9% | — |
| WeirdML | 49.2% | — |
| LMArena Coding | 1404 | — |
| ALE-Bench | 1,005 | — |
Reasoning Hy4 preview leads
GPT-5.4 nano: 23.8 (#159), Hy4 preview: 30.6 (#75)
| Benchmark | GPT-5.4 nano | Hy4 preview |
|---|---|---|
| ARC-AGI-2 | 5.7% | — |
| Kagi LLM Benchmark | 39.7% | — |
| NYT Connections (extended) | — | 68.2% |
| ARC-AGI-1 | 51.5% | — |
| CritPt | 9.3% | — |
| Chess Puzzles | 30% | — |
| LMArena Hard Prompts | 1380 | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 80.3% | — |
| LMCA | 36.9% | — |
| Epoch Capabilities Index | 145.78 | — |
| ForecastBench | 57.3 | — |
Math Hy4 preview leads
GPT-5.4 nano: 40.7 (#76), Hy4 preview: 54.5 (#37)
| Benchmark | GPT-5.4 nano | Hy4 preview |
|---|---|---|
| ProofBench | 5% | 75% |
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 87.8% | — |
| LMArena Math | 1406 | — |
| FrontierMath (Feb 2025 set) | 25.9% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge Not comparable
GPT-5.4 nano: 41.8 (#94), Hy4 preview: —
| Benchmark | GPT-5.4 nano | Hy4 preview |
|---|---|---|
| GPQA Diamond | 78.5% | — |
| SimpleQA Verified | 11.7% | — |
| Vectara Hallucination Rate | 3.1% | — |
| LMArena Expert | 1397 | — |
Multimodal Not comparable
GPT-5.4 nano: 36.0 (#73), Hy4 preview: —
| Benchmark | GPT-5.4 nano | Hy4 preview |
|---|---|---|
| LMArena Vision | 1196 | — |
Multilingual Not comparable
GPT-5.4 nano: 48.8 (#136), Hy4 preview: —
| Benchmark | GPT-5.4 nano | Hy4 preview |
|---|---|---|
| LMArena Non-English | 1359 | — |
| LMArena Chinese | 1391 | — |
| LMArena French | 1396 | — |
| LMArena German | 1368 | — |
| LMArena Japanese | 1342 | — |
| LMArena Korean | 1321 | — |
| LMArena Russian | 1363 | — |
| LMArena Spanish | 1368 | — |
Instruction Following Not comparable
GPT-5.4 nano: 72.1 (#139), Hy4 preview: —
| Benchmark | GPT-5.4 nano | Hy4 preview |
|---|---|---|
| LMArena Instruction Following | 1362 | — |
Long Context Not comparable
GPT-5.4 nano: 41.6 (#131), Hy4 preview: —
| Benchmark | GPT-5.4 nano | Hy4 preview |
|---|---|---|
| LMArena Longer Query | 1365 | — |
Writing & Preference Not comparable
GPT-5.4 nano: 55.9 (#137), Hy4 preview: —
| Benchmark | GPT-5.4 nano | Hy4 preview |
|---|---|---|
| LMArena Text | 1372 | — |
| LMArena Creative Writing | 1313 | — |
| LMArena Multi-Turn | 1382 | — |
Frequently asked questions
Is GPT-5.4 nano better than Hy4 preview?
Hy4 preview is the stronger model overall, scoring 44.6 to 41.9 on the Noometry Index. GPT-5.4 nano costs 2.7× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.
Which is cheaper, GPT-5.4 nano or Hy4 preview?
GPT-5.4 nano is cheaper. It lists at $0.20 per million input tokens and $1.25 per million output tokens; Hy4 preview lists at $0.83 and $2.50.
Is GPT-5.4 nano or Hy4 preview better for coding?
Hy4 preview scores higher on coding benchmarks: 51.4 versus 43.1 in the Noometry coding category.
Which has the bigger context window?
Hy4 preview does, with 1.05M tokens against 400K.
How many benchmarks do GPT-5.4 nano and Hy4 preview share?
1 benchmark has published results for both models. GPT-5.4 nano has 40 scored results on Noometry and Hy4 preview has 3.