Model comparison
Grok-3 mini vs Hy3
Hy3 is the stronger model overall, scoring 44.2 to 41.2 on the Noometry Index.
Last verified . 17 shared benchmarks.
TencentSummary
- They share 17 benchmarks with published results for both. Grok-3 mini scores higher in 3 categories and Hy3 in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Hy3 leads 26.1 to 13.6.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Grok-3 mini | Hy3 | |
|---|---|---|
| Provider | xAI | Tencent |
| Noometry Index | 41.2 | 44.2 |
| Released | 2025-04-09 | 2026-07-06 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.0825 |
| Output $ / M tokens | — | $0.33 |
| Results tracked | 35 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Grok-3 mini: 40.8 (#131), Hy3: 46.8 (#63)
| Benchmark | Grok-3 mini | Hy3 |
|---|---|---|
| LMArena Coding | 1379 | 1464 |
| Aider Polyglot | 49.3% | — |
| LMArena WebDev | — | 1508 |
| WeirdML | 42.6% | — |
Reasoning Hy3 leads
Grok-3 mini: 13.6 (#334), Hy3: 26.1 (#136)
| Benchmark | Grok-3 mini | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1375 | 1447 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| NYT Connections (extended) | — | 41.2% |
| ARC-AGI-1 | 16.5% | — |
| Epoch Capabilities Index | 140.35 | — |
Math Grok-3 mini leads
Grok-3 mini: 42.1 (#85), Hy3: 40.1 (#93)
| Benchmark | Grok-3 mini | Hy3 |
|---|---|---|
| LMArena Math | 1386 | 1475 |
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| Omni-MATH | 31.8% | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
Knowledge Grok-3 mini leads
Grok-3 mini: 46.4 (#81), Hy3: 40.8 (#114)
| Benchmark | Grok-3 mini | Hy3 |
|---|---|---|
| LMArena Expert | 1395 | 1460 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| GPQA (HELM) | 67.5% | — |
Multilingual Hy3 leads
Grok-3 mini: 48.1 (#145), Hy3: 53.5 (#65)
| Benchmark | Grok-3 mini | Hy3 |
|---|---|---|
| LMArena Non-English | 1352 | 1426 |
| LMArena Chinese | 1387 | 1493 |
| LMArena French | 1357 | 1461 |
| LMArena German | 1349 | 1439 |
| LMArena Japanese | 1342 | 1392 |
| LMArena Korean | 1335 | 1395 |
| LMArena Russian | 1353 | 1432 |
| LMArena Spanish | 1381 | 1456 |
Instruction Following Grok-3 mini leads
Grok-3 mini: 78.5 (#9), Hy3: 75.1 (#70)
| Benchmark | Grok-3 mini | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1357 | 1426 |
| IFEval | 95.1% | — |
Long Context Hy3 leads
Grok-3 mini: 41.0 (#147), Hy3: 44.1 (#75)
| Benchmark | Grok-3 mini | Hy3 |
|---|---|---|
| LMArena Longer Query | 1372 | 1442 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference Hy3 leads
Grok-3 mini: 52.5 (#169), Hy3: 62.2 (#81)
| Benchmark | Grok-3 mini | Hy3 |
|---|---|---|
| LMArena Text | 1370 | 1439 |
| LMArena Creative Writing | 1342 | 1402 |
| LMArena Multi-Turn | 1355 | 1436 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 65.1% | — |
Frequently asked questions
Is Grok-3 mini better than Hy3?
Hy3 is the stronger model overall, scoring 44.2 to 41.2 on the Noometry Index.
Is Grok-3 mini or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 40.8 in the Noometry coding category.
How many benchmarks do Grok-3 mini and Hy3 share?
17 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Hy3 has 19.