Model comparison
Grok 4.3 vs Hy4 preview
Hy4 preview is the stronger model overall, scoring 45.3 to 43.8 on the Noometry Index.
Last verified . 3 shared benchmarks.
TencentSummary
- They share 3 benchmarks with published results for both. Grok 4.3 scores higher in 1 category and Hy4 preview in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in coding, where Hy4 preview leads 51.6 to 41.6.
- The biggest single-benchmark swing is ProofBench: 11% for Grok 4.3 and 75% for Hy4 preview.
- Hy4 preview is cheaper at $0.75 / $2.25 per million input/output tokens, against $1.25 / $2.50 for Grok 4.3.
- Hy4 preview accepts more context: 1.05M tokens versus 1M.
- Hy4 preview has downloadable open weights; the other is API-only.
Side by side
| Grok 4.3 | Hy4 preview | |
|---|---|---|
| Provider | xAI | Tencent |
| Noometry Index | 43.8 | 45.3 |
| Released | 2026-04-17 | 2026-08-28 |
| Weights | Proprietary | Open |
| Context window | 1M | 1.05M |
| Max output | 30K | 64K |
| Input $ / M tokens | $1.25 | $0.75 |
| Output $ / M tokens | $2.50 | $2.25 |
| Results tracked | 40 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Grok 4.3: 41.6 (#121), Hy4 preview: 51.6 (#38)
| Benchmark | Grok 4.3 | Hy4 preview |
|---|---|---|
| LMArena WebDev | 1357 | 1632 |
| SciCode | 47.3% | — |
| WeirdML | 49.9% | — |
| LMArena Coding | 1415 | — |
| ALE-Bench | 944.17 | — |
Agentic & Tool Use Not comparable
Grok 4.3: 27.7 (#99), Hy4 preview: —
| Benchmark | Grok 4.3 | Hy4 preview |
|---|---|---|
| GDP.pdf | 8% | — |
| LMArena Search | 1165 | — |
| Vending-Bench 2 | 35.26 | — |
Reasoning Grok 4.3 leads
Grok 4.3: 35.9 (#68), Hy4 preview: 31.9 (#79)
| Benchmark | Grok 4.3 | Hy4 preview |
|---|---|---|
| NYT Connections (extended) | 55.2% | 68.2% |
| CritPt | 8% | — |
| Chess Puzzles | 25% | — |
| LMArena Hard Prompts | 1396 | — |
| DTBench | 90.7% | — |
| LMCA | 38.3% | — |
| Epoch Capabilities Index | 149.16 | — |
| ForecastBench | 60.3 | — |
Math Hy4 preview leads
Grok 4.3: 46.0 (#74), Hy4 preview: 55.7 (#42)
| Benchmark | Grok 4.3 | Hy4 preview |
|---|---|---|
| ProofBench | 11% | 75% |
| FrontierMath (Tiers 1-3) | 42.8% | — |
| FrontierMath Tier 4 | 14.6% | — |
| OTIS Mock AIME 2024-2025 | 93.3% | — |
| LMArena Math | 1388 | — |
Knowledge Not comparable
Grok 4.3: 52.5 (#62), Hy4 preview: —
| Benchmark | Grok 4.3 | Hy4 preview |
|---|---|---|
| GPQA Diamond | 88.8% | — |
| SimpleQA Verified | 33.2% | — |
| LMArena Expert | 1385 | — |
Multimodal Not comparable
Grok 4.3: 31.6 (#104), Hy4 preview: —
| Benchmark | Grok 4.3 | Hy4 preview |
|---|---|---|
| LMArena Vision | 1229 | — |
| Blueprint-Bench 2 | 0% | — |
Multilingual Not comparable
Grok 4.3: 50.5 (#120), Hy4 preview: —
| Benchmark | Grok 4.3 | Hy4 preview |
|---|---|---|
| LMArena Non-English | 1385 | — |
| LMArena Chinese | 1422 | — |
| LMArena French | 1412 | — |
| LMArena German | 1395 | — |
| LMArena Japanese | 1379 | — |
| LMArena Korean | 1356 | — |
| LMArena Russian | 1399 | — |
| LMArena Spanish | 1398 | — |
Instruction Following Not comparable
Grok 4.3: 72.1 (#140), Hy4 preview: —
| Benchmark | Grok 4.3 | Hy4 preview |
|---|---|---|
| LMArena Instruction Following | 1366 | — |
Long Context Not comparable
Grok 4.3: 42.5 (#123), Hy4 preview: —
| Benchmark | Grok 4.3 | Hy4 preview |
|---|---|---|
| LMArena Longer Query | 1393 | — |
Writing & Preference Not comparable
Grok 4.3: 58.5 (#118), Hy4 preview: —
| Benchmark | Grok 4.3 | Hy4 preview |
|---|---|---|
| LMArena Text | 1397 | — |
| LMArena Creative Writing | 1380 | — |
| EQ-Bench 4 | 1075 | — |
| LMArena Multi-Turn | 1406 | — |
Frequently asked questions
Is Grok 4.3 better than Hy4 preview?
Hy4 preview is the stronger model overall, scoring 45.3 to 43.8 on the Noometry Index.
Which is cheaper, Grok 4.3 or Hy4 preview?
Hy4 preview is cheaper. It lists at $0.75 per million input tokens and $2.25 per million output tokens; Grok 4.3 lists at $1.25 and $2.50.
Is Grok 4.3 or Hy4 preview better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 41.6 in the Noometry coding category.
Which has the bigger context window?
Hy4 preview does, with 1.05M tokens against 1M.
How many benchmarks do Grok 4.3 and Hy4 preview share?
3 benchmarks have published results for both models. Grok 4.3 has 40 scored results on Noometry and Hy4 preview has 3.