Model comparison
Granite 4.2 30b vs Grok-3 mini
Granite 4.2 30b and Grok-3 mini score almost the same on the Noometry Index (41.8 vs 41.2), so choose on price, context window or the category you care about most.
Last verified . 11 shared benchmarks.
Summary
- They share 11 benchmarks with published results for both. Granite 4.2 30b scores higher in 4 categories and Grok-3 mini in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Granite 4.2 30b leads 27.8 to 13.6.
- Granite 4.2 30b has downloadable open weights; the other is API-only.
Side by side
| Granite 4.2 30b | Grok-3 mini | |
|---|---|---|
| Provider | IBM | xAI |
| Noometry Index | 41.8 | 41.2 |
| Released | — | 2025-04-09 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 11 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Granite 4.2 30b: 41.0 (#126), Grok-3 mini: 40.8 (#131)
| Benchmark | Granite 4.2 30b | Grok-3 mini |
|---|---|---|
| LMArena Coding | 1396 | 1379 |
| Aider Polyglot | — | 49.3% |
| WeirdML | — | 42.6% |
Reasoning Granite 4.2 30b leads
Granite 4.2 30b: 27.8 (#112), Grok-3 mini: 13.6 (#334)
| Benchmark | Granite 4.2 30b | Grok-3 mini |
|---|---|---|
| LMArena Hard Prompts | 1374 | 1375 |
| ARC-AGI-2 | — | 0.4% |
| Kagi LLM Benchmark | — | 61.3% |
| ARC-AGI-1 | — | 16.5% |
| Epoch Capabilities Index | — | 140.35 |
Math Not comparable
Granite 4.2 30b: —, Grok-3 mini: 42.1 (#85)
| Benchmark | Granite 4.2 30b | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 77.8% |
| Omni-MATH | — | 31.8% |
| LMArena Math | — | 1386 |
| MATH Level 5 | — | 90.9% |
| FrontierMath (Feb 2025 set) | — | 5.9% |
Knowledge Grok-3 mini leads
Granite 4.2 30b: 39.1 (#138), Grok-3 mini: 46.4 (#81)
| Benchmark | Granite 4.2 30b | Grok-3 mini |
|---|---|---|
| LMArena Expert | 1406 | 1395 |
| GPQA Diamond | — | 76.3% |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| GPQA (HELM) | — | 67.5% |
Multilingual Too close to call
Granite 4.2 30b: 47.3 (#151), Grok-3 mini: 48.1 (#145)
| Benchmark | Granite 4.2 30b | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1340 | 1352 |
| LMArena Chinese | 1414 | 1387 |
| LMArena Russian | 1343 | 1353 |
| LMArena French | — | 1357 |
| LMArena German | — | 1349 |
| LMArena Japanese | — | 1342 |
| LMArena Korean | — | 1335 |
| LMArena Spanish | — | 1381 |
Instruction Following Grok-3 mini leads
Granite 4.2 30b: 71.2 (#155), Grok-3 mini: 78.5 (#9)
| Benchmark | Granite 4.2 30b | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1347 | 1357 |
| IFEval | — | 95.1% |
Long Context Too close to call
Granite 4.2 30b: 41.4 (#140), Grok-3 mini: 41.0 (#147)
| Benchmark | Granite 4.2 30b | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1359 | 1372 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Granite 4.2 30b leads
Granite 4.2 30b: 53.8 (#156), Grok-3 mini: 52.5 (#169)
| Benchmark | Granite 4.2 30b | Grok-3 mini |
|---|---|---|
| LMArena Text | 1361 | 1370 |
| LMArena Creative Writing | 1288 | 1342 |
| LMArena Multi-Turn | 1339 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| WildBench | — | 65.1% |
Frequently asked questions
Is Granite 4.2 30b better than Grok-3 mini?
Granite 4.2 30b and Grok-3 mini score almost the same on the Noometry Index (41.8 vs 41.2), so choose on price, context window or the category you care about most.
Is Granite 4.2 30b or Grok-3 mini better for coding?
They score almost the same on coding (41.0 vs 40.8); test both on your own repository before choosing.
How many benchmarks do Granite 4.2 30b and Grok-3 mini share?
11 benchmarks have published results for both models. Granite 4.2 30b has 11 scored results on Noometry and Grok-3 mini has 35.