Model comparison
Hy4 preview vs Llama 4 Scout
Hy4 preview is the stronger model overall, scoring 45.3 to 27.7 on the Noometry Index. Llama 4 Scout costs 8.3× 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.
Tencent
MetaSummary
- The widest gap is in math, where Hy4 preview leads 55.7 to 19.6.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.83 / $2.50 for Hy4 preview.
- Hy4 preview accepts more context: 1.05M tokens versus 128K.
Side by side
| Hy4 preview | Llama 4 Scout | |
|---|---|---|
| Provider | Tencent | Meta |
| Noometry Index | 45.3 | 27.7 |
| Released | 2026-08-28 | 2025-04-05 |
| Weights | Open | Open |
| Context window | 1.05M | 128K |
| Max output | 64K | 4K |
| Input $ / M tokens | $0.83 | $0.10 |
| Output $ / M tokens | $2.50 | $0.30 |
| Results tracked | 3 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Hy4 preview: 51.6 (#38), Llama 4 Scout: 20.2 (#339)
| Benchmark | Hy4 preview | Llama 4 Scout |
|---|---|---|
| SWE-bench Verified (bash only) | — | 9.1% |
| LMArena WebDev | 1632 | — |
| SciCode | — | 17% |
| LMArena Coding | — | 1286 |
| BigCodeBench Complete | — | 43.1% |
Agentic & Tool Use Not comparable
Hy4 preview: —, Llama 4 Scout: 24.6 (#119)
| Benchmark | Hy4 preview | Llama 4 Scout |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.1% |
Reasoning Hy4 preview leads
Hy4 preview: 31.9 (#79), Llama 4 Scout: 9.1 (#345)
| Benchmark | Hy4 preview | Llama 4 Scout |
|---|---|---|
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 36.9% |
| NYT Connections (extended) | 68.2% | — |
| ARC-AGI-1 | — | 0.5% |
| CritPt | — | 0% |
| LMArena Hard Prompts | — | 1266 |
| DTBench | — | 57.9% |
| LMCA | — | 12% |
| Epoch Capabilities Index | — | 129.64 |
| ForecastBench | — | 57.5 |
Math Hy4 preview leads
Hy4 preview: 55.7 (#42), Llama 4 Scout: 19.6 (#286)
| Benchmark | Hy4 preview | Llama 4 Scout |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 7.8% |
| ProofBench | 75% | — |
| Omni-MATH | — | 37.3% |
| LMArena Math | — | 1287 |
| MATH Level 5 | — | 62.3% |
| FrontierMath (Feb 2025 set) | — | 0% |
Knowledge Not comparable
Hy4 preview: —, Llama 4 Scout: 31.9 (#217)
| Benchmark | Hy4 preview | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | — | 51.8% |
| MMLU-Pro | — | 74.2% |
| Vectara Hallucination Rate | — | 7.7% |
| GPQA (HELM) | — | 50.7% |
| LMArena Expert | — | 1235 |
Multimodal Not comparable
Hy4 preview: —, Llama 4 Scout: 32.2 (#102)
| Benchmark | Hy4 preview | Llama 4 Scout |
|---|---|---|
| LMArena Vision | — | 1118 |
| SpatialViz-Bench | — | 34.2% |
Multilingual Not comparable
Hy4 preview: —, Llama 4 Scout: 41.0 (#212)
| Benchmark | Hy4 preview | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | — | 1252 |
| LMArena Chinese | — | 1255 |
| LMArena French | — | 1282 |
| LMArena German | — | 1272 |
| LMArena Japanese | — | 1206 |
| LMArena Korean | — | 1207 |
| LMArena Russian | — | 1263 |
| LMArena Spanish | — | 1278 |
Instruction Following Not comparable
Hy4 preview: —, Llama 4 Scout: 65.8 (#217)
| Benchmark | Hy4 preview | Llama 4 Scout |
|---|---|---|
| IFEval | — | 81.8% |
| LMArena Instruction Following | — | 1248 |
Long Context Not comparable
Hy4 preview: —, Llama 4 Scout: 27.5 (#294)
| Benchmark | Hy4 preview | Llama 4 Scout |
|---|---|---|
| Fiction.LiveBench | — | 36% |
| LMArena Longer Query | — | 1265 |
Writing & Preference Not comparable
Hy4 preview: —, Llama 4 Scout: 37.0 (#261)
| Benchmark | Hy4 preview | Llama 4 Scout |
|---|---|---|
| LMArena Text | — | 1279 |
| LMArena Creative Writing | — | 1249 |
| EQ-Bench Creative Writing | — | 783 |
| WildBench | — | 78% |
| LMArena Multi-Turn | — | 1280 |
Frequently asked questions
Is Hy4 preview better than Llama 4 Scout?
Hy4 preview is the stronger model overall, scoring 45.3 to 27.7 on the Noometry Index. Llama 4 Scout costs 8.3× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.
Which is cheaper, Hy4 preview or Llama 4 Scout?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Hy4 preview lists at $0.83 and $2.50.
Is Hy4 preview or Llama 4 Scout better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Hy4 preview does, with 1.05M tokens against 128K.
How many benchmarks do Hy4 preview and Llama 4 Scout share?
0 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Llama 4 Scout has 43.