Model comparison
Granite 4.2 30b vs Grok 4
Grok 4 is the stronger model overall, scoring 47.8 to 41.4 on the Noometry Index.
Last verified . 11 shared benchmarks.
Summary
- They share 11 benchmarks with published results for both. Granite 4.2 30b scores higher in 0 categories and Grok 4 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where Grok 4 leads 63.1 to 41.4.
- Granite 4.2 30b has downloadable open weights; the other is API-only.
Side by side
| Granite 4.2 30b | Grok 4 | |
|---|---|---|
| Provider | IBM | xAI |
| Noometry Index | 41.4 | 47.8 |
| Released | — | 2025-07-09 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 11 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4 leads
Granite 4.2 30b: 40.4 (#127), Grok 4: 49.9 (#44)
| Benchmark | Granite 4.2 30b | Grok 4 |
|---|---|---|
| LMArena Coding | 1394 | 1408 |
| Aider Polyglot | — | 79.6% |
| WeirdML | — | 45.7% |
Agentic & Tool Use Not comparable
Granite 4.2 30b: —, Grok 4: 32.1 (#62)
| Benchmark | Granite 4.2 30b | Grok 4 |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 21.1% |
| Cybench | — | 43% |
| DeepResearch Bench | — | 47.3% |
| BALROG | — | 43.6% |
| LMArena Search | — | 1142 |
| METR Time Horizons | — | 66.6% |
Reasoning Grok 4 leads
Granite 4.2 30b: 26.7 (#114), Grok 4: 36.9 (#59)
| Benchmark | Granite 4.2 30b | Grok 4 |
|---|---|---|
| LMArena Hard Prompts | 1375 | 1409 |
| ARC-AGI-2 | — | 16% |
| SimpleBench | — | 60.5% |
| Kagi LLM Benchmark | — | 73.6% |
| ARC-AGI-1 | — | 66.7% |
| Chess Puzzles | — | 28% |
| Epoch Capabilities Index | — | 146.46 |
| ForecastBench | — | 60.9 |
Math Not comparable
Granite 4.2 30b: —, Grok 4: 46.5 (#58)
| Benchmark | Granite 4.2 30b | Grok 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 84% |
| Omni-MATH | — | 60.3% |
| LMArena Math | — | 1422 |
| FrontierMath (Feb 2025 set) | — | 19.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Grok 4 leads
Granite 4.2 30b: 38.5 (#134), Grok 4: 53.7 (#50)
| Benchmark | Granite 4.2 30b | Grok 4 |
|---|---|---|
| LMArena Expert | 1405 | 1417 |
| GPQA Diamond | — | 87% |
| MMLU-Pro | — | 85.1% |
| Confabulations | — | 12.4% |
| GPQA (HELM) | — | 72.7% |
Multimodal Not comparable
Granite 4.2 30b: —, Grok 4: 33.1 (#89)
| Benchmark | Granite 4.2 30b | Grok 4 |
|---|---|---|
| LMArena Vision | — | 1211 |
| GeoBench | — | 45% |
Multilingual Grok 4 leads
Granite 4.2 30b: 47.4 (#146), Grok 4: 52.0 (#98)
| Benchmark | Granite 4.2 30b | Grok 4 |
|---|---|---|
| LMArena Non-English | 1340 | 1403 |
| LMArena Chinese | 1415 | 1428 |
| LMArena Russian | 1342 | 1409 |
| LMArena French | — | 1418 |
| LMArena German | — | 1429 |
| LMArena Japanese | — | 1396 |
| LMArena Korean | — | 1376 |
| LMArena Spanish | — | 1419 |
Instruction Following Grok 4 leads
Granite 4.2 30b: 71.3 (#150), Grok 4: 79.4 (#4)
| Benchmark | Granite 4.2 30b | Grok 4 |
|---|---|---|
| LMArena Instruction Following | 1346 | 1387 |
| IFEval | — | 94.9% |
Long Context Grok 4 leads
Granite 4.2 30b: 41.4 (#135), Grok 4: 63.1 (#4)
| Benchmark | Granite 4.2 30b | Grok 4 |
|---|---|---|
| LMArena Longer Query | 1359 | 1409 |
| Fiction.LiveBench | — | 94.4% |
Writing & Preference Grok 4 leads
Granite 4.2 30b: 54.3 (#147), Grok 4: 58.7 (#111)
| Benchmark | Granite 4.2 30b | Grok 4 |
|---|---|---|
| LMArena Text | 1363 | 1412 |
| LMArena Creative Writing | 1294 | 1397 |
| LMArena Multi-Turn | 1340 | 1416 |
| Short-Story Creative Writing | — | 76.9% |
| WildBench | — | 79.7% |
Frequently asked questions
Is Granite 4.2 30b better than Grok 4?
Grok 4 is the stronger model overall, scoring 47.8 to 41.4 on the Noometry Index.
Is Granite 4.2 30b or Grok 4 better for coding?
Grok 4 scores higher on coding benchmarks: 49.9 versus 40.4 in the Noometry coding category.
How many benchmarks do Granite 4.2 30b and Grok 4 share?
11 benchmarks have published results for both models. Granite 4.2 30b has 11 scored results on Noometry and Grok 4 has 48.