Model comparison
Granite 3.1 2b Instruct vs Grok-3 mini
Grok-3 mini is the stronger model overall, scoring 41.2 to 33.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Granite 3.1 2b Instruct scores higher in 1 category and Grok-3 mini in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Grok-3 mini leads 78.5 to 57.7.
- Granite 3.1 2b Instruct has downloadable open weights; the other is API-only.
Side by side
| Granite 3.1 2b Instruct | Grok-3 mini | |
|---|---|---|
| Provider | IBM | xAI |
| Noometry Index | 33.2 | 41.2 |
| Released | — | 2025-04-09 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 12 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-3 mini leads
Granite 3.1 2b Instruct: 33.4 (#257), Grok-3 mini: 40.8 (#131)
| Benchmark | Granite 3.1 2b Instruct | Grok-3 mini |
|---|---|---|
| LMArena Coding | 1149 | 1379 |
| Aider Polyglot | — | 49.3% |
| WeirdML | — | 42.6% |
Reasoning Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 22.0 (#209), Grok-3 mini: 13.6 (#334)
| Benchmark | Granite 3.1 2b Instruct | Grok-3 mini |
|---|---|---|
| LMArena Hard Prompts | 1138 | 1375 |
| ARC-AGI-2 | — | 0.4% |
| Kagi LLM Benchmark | — | 61.3% |
| ARC-AGI-1 | — | 16.5% |
| Epoch Capabilities Index | — | 140.35 |
Math Grok-3 mini leads
Granite 3.1 2b Instruct: 33.1 (#206), Grok-3 mini: 42.1 (#85)
| Benchmark | Granite 3.1 2b Instruct | Grok-3 mini |
|---|---|---|
| LMArena Math | 1159 | 1386 |
| 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
Granite 3.1 2b Instruct: 30.8 (#224), Grok-3 mini: 46.4 (#81)
| Benchmark | Granite 3.1 2b Instruct | Grok-3 mini |
|---|---|---|
| LMArena Expert | 1131 | 1395 |
| GPQA Diamond | — | 76.3% |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| GPQA (HELM) | — | 67.5% |
Multilingual Grok-3 mini leads
Granite 3.1 2b Instruct: 29.1 (#269), Grok-3 mini: 48.1 (#145)
| Benchmark | Granite 3.1 2b Instruct | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1068 | 1352 |
| LMArena Chinese | 1139 | 1387 |
| LMArena Russian | 1063 | 1353 |
| LMArena French | — | 1357 |
| LMArena German | — | 1349 |
| LMArena Japanese | — | 1342 |
| LMArena Korean | — | 1335 |
| LMArena Spanish | — | 1381 |
Instruction Following Grok-3 mini leads
Granite 3.1 2b Instruct: 57.7 (#264), Grok-3 mini: 78.5 (#9)
| Benchmark | Granite 3.1 2b Instruct | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1116 | 1357 |
| IFEval | — | 95.1% |
Long Context Grok-3 mini leads
Granite 3.1 2b Instruct: 35.0 (#244), Grok-3 mini: 41.0 (#147)
| Benchmark | Granite 3.1 2b Instruct | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1155 | 1372 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Grok-3 mini leads
Granite 3.1 2b Instruct: 34.1 (#274), Grok-3 mini: 52.5 (#169)
| Benchmark | Granite 3.1 2b Instruct | Grok-3 mini |
|---|---|---|
| LMArena Text | 1127 | 1370 |
| LMArena Creative Writing | 1116 | 1342 |
| LMArena Multi-Turn | 1099 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| WildBench | — | 65.1% |
Frequently asked questions
Is Granite 3.1 2b Instruct better than Grok-3 mini?
Grok-3 mini is the stronger model overall, scoring 41.2 to 33.2 on the Noometry Index.
Is Granite 3.1 2b Instruct or Grok-3 mini better for coding?
Grok-3 mini scores higher on coding benchmarks: 40.8 versus 33.4 in the Noometry coding category.
How many benchmarks do Granite 3.1 2b Instruct and Grok-3 mini share?
12 benchmarks have published results for both models. Granite 3.1 2b Instruct has 12 scored results on Noometry and Grok-3 mini has 35.