Model comparison
Grok 4.7 vs Granite 4.0 H Small
Grok 4.7 is the stronger model overall, scoring 46.6 to 35.9 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Grok 4.7 scores higher in 8 categories and Granite 4.0 H Small in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Grok 4.7 leads 70.1 to 44.0.
- Granite 4.0 H Small has downloadable open weights; the other is API-only.
Side by side
| Grok 4.7 | Granite 4.0 H Small | |
|---|---|---|
| Provider | xAI | IBM |
| Noometry Index | 46.6 | 35.9 |
| Released | 2026-09-21 | — |
| Weights | Proprietary | Open |
| Context window | 500K | — |
| Max output | 500K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $6 | — |
| Results tracked | 21 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.7 leads
Grok 4.7: 55.0 (#23), Granite 4.0 H Small: 35.8 (#207)
| Benchmark | Grok 4.7 | Granite 4.0 H Small |
|---|---|---|
| LMArena Coding | 1423 | 1247 |
| CursorBench | 46.3% | — |
| LMArena WebDev | 1636 | — |
| FrontierSWE | 29.5% | — |
| SciCode | 57.4% | — |
Reasoning Grok 4.7 leads
Grok 4.7: 40.1 (#49), Granite 4.0 H Small: 23.4 (#164)
| Benchmark | Grok 4.7 | Granite 4.0 H Small |
|---|---|---|
| LMArena Hard Prompts | 1409 | 1240 |
| NYT Connections (extended) | 76.8% | — |
| CritPt | 17.7% | — |
Math Grok 4.7 leads
Grok 4.7: 41.1 (#73), Granite 4.0 H Small: 29.3 (#219)
| Benchmark | Grok 4.7 | Granite 4.0 H Small |
|---|---|---|
| LMArena Math | 1393 | 1251 |
| ProofBench | 34% | — |
| Omni-MATH | — | 29.6% |
Knowledge Grok 4.7 leads
Grok 4.7: 38.7 (#130), Granite 4.0 H Small: 31.5 (#210)
| Benchmark | Grok 4.7 | Granite 4.0 H Small |
|---|---|---|
| LMArena Expert | 1413 | 1244 |
| MMLU-Pro | — | 56.9% |
| Vectara Hallucination Rate | — | 5.2% |
| GPQA (HELM) | — | 38.3% |
Multimodal Not comparable
Grok 4.7: 28.8 (#107), Granite 4.0 H Small: —
| Benchmark | Grok 4.7 | Granite 4.0 H Small |
|---|---|---|
| Furniture Assembly | 20.8% | — |
Multilingual Grok 4.7 leads
Grok 4.7: 51.2 (#108), Granite 4.0 H Small: 38.7 (#223)
| Benchmark | Grok 4.7 | Granite 4.0 H Small |
|---|---|---|
| LMArena Non-English | 1392 | 1216 |
| LMArena Chinese | 1476 | 1250 |
| LMArena Russian | 1396 | 1198 |
| LMArena Spanish | — | 1258 |
Instruction Following Grok 4.7 leads
Grok 4.7: 74.3 (#98), Granite 4.0 H Small: 68.9 (#178)
| Benchmark | Grok 4.7 | Granite 4.0 H Small |
|---|---|---|
| LMArena Instruction Following | 1406 | 1221 |
| IFEval | — | 89% |
Long Context Grok 4.7 leads
Grok 4.7: 43.2 (#97), Granite 4.0 H Small: 37.6 (#209)
| Benchmark | Grok 4.7 | Granite 4.0 H Small |
|---|---|---|
| LMArena Longer Query | 1416 | 1240 |
Writing & Preference Grok 4.7 leads
Grok 4.7: 70.1 (#23), Granite 4.0 H Small: 44.0 (#222)
| Benchmark | Grok 4.7 | Granite 4.0 H Small |
|---|---|---|
| LMArena Text | 1397 | 1241 |
| LMArena Creative Writing | 1391 | 1210 |
| LMArena Multi-Turn | 1389 | 1243 |
| EQ-Bench Creative Writing | 2007 | — |
| WildBench | — | 73.9% |
Frequently asked questions
Is Grok 4.7 better than Granite 4.0 H Small?
Grok 4.7 is the stronger model overall, scoring 46.6 to 35.9 on the Noometry Index.
Is Grok 4.7 or Granite 4.0 H Small better for coding?
Grok 4.7 scores higher on coding benchmarks: 55.0 versus 35.8 in the Noometry coding category.
How many benchmarks do Grok 4.7 and Granite 4.0 H Small share?
12 benchmarks have published results for both models. Grok 4.7 has 21 scored results on Noometry and Granite 4.0 H Small has 19.