Model comparison
Gemma 3 12B vs Grok 3
Grok 3 is the stronger model overall, scoring 39.9 to 32.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
GoogleSummary
- They share 17 benchmarks with published results for both. Gemma 3 12B scores higher in 2 categories and Grok 3 in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 3 leads 46.2 to 26.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 16.7% for Gemma 3 12B and 55.6% for Grok 3.
- Gemma 3 12B has downloadable open weights; the other is API-only.
Side by side
| Gemma 3 12B | Grok 3 | |
|---|---|---|
| Provider | xAI | |
| Noometry Index | 32.1 | 39.9 |
| Released | 2025-03-12 | 2025-04-09 |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 24 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 3 leads
Gemma 3 12B: 31.7 (#280), Grok 3: 41.9 (#115)
| Benchmark | Gemma 3 12B | Grok 3 |
|---|---|---|
| LMArena Coding | 1281 | 1432 |
| Aider Polyglot | — | 53.3% |
| SciCode | 17.4% | — |
| WeirdML | — | 37.2% |
Agentic & Tool Use Grok 3 leads
Gemma 3 12B: 25.5 (#108), Grok 3: 30.5 (#76)
| Benchmark | Gemma 3 12B | Grok 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
| BALROG | — | 29.5% |
Reasoning Gemma 3 12B leads
Gemma 3 12B: 15.7 (#313), Grok 3: 13.7 (#333)
| Benchmark | Gemma 3 12B | Grok 3 |
|---|---|---|
| LMArena Hard Prompts | 1309 | 1434 |
| Epoch Capabilities Index | 123.5 | 138.33 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 36.1% |
| Kagi LLM Benchmark | — | 61.3% |
| ARC-AGI-1 | — | 5.5% |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
Math Grok 3 leads
Gemma 3 12B: 22.3 (#279), Grok 3: 38.0 (#145)
| Benchmark | Gemma 3 12B | Grok 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.7% | 55.6% |
| LMArena Math | 1307 | 1391 |
| Omni-MATH | — | 46.4% |
| MATH Level 5 | — | 88.7% |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Grok 3 leads
Gemma 3 12B: 26.5 (#257), Grok 3: 46.2 (#82)
| Benchmark | Gemma 3 12B | Grok 3 |
|---|---|---|
| GPQA Diamond | 39.5% | 75.8% |
| Vectara Hallucination Rate | 4.4% | 5.8% |
| LMArena Expert | 1248 | 1421 |
| MMLU-Pro | — | 78.8% |
| Confabulations | — | 14.2% |
| GPQA (HELM) | — | 65% |
Multimodal Not comparable
Gemma 3 12B: —, Grok 3: —
| Benchmark | Gemma 3 12B | Grok 3 |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual Grok 3 leads
Gemma 3 12B: 45.7 (#165), Grok 3: 52.3 (#87)
| Benchmark | Gemma 3 12B | Grok 3 |
|---|---|---|
| LMArena Non-English | 1318 | 1410 |
| LMArena German | 1370 | 1431 |
| LMArena Russian | 1335 | 1416 |
| LMArena Chinese | — | 1448 |
| LMArena French | — | 1460 |
| LMArena Japanese | — | 1387 |
| LMArena Korean | — | 1373 |
| LMArena Spanish | — | 1417 |
Instruction Following Grok 3 leads
Gemma 3 12B: 68.6 (#186), Grok 3: 75.0 (#73)
| Benchmark | Gemma 3 12B | Grok 3 |
|---|---|---|
| LMArena Instruction Following | 1299 | 1409 |
| IFEval | — | 88.4% |
Long Context Gemma 3 12B leads
Gemma 3 12B: 40.0 (#162), Grok 3: 38.7 (#192)
| Benchmark | Gemma 3 12B | Grok 3 |
|---|---|---|
| LMArena Longer Query | 1317 | 1439 |
| Fiction.LiveBench | — | 58.3% |
Writing & Preference Grok 3 leads
Gemma 3 12B: 47.5 (#209), Grok 3: 55.8 (#141)
| Benchmark | Gemma 3 12B | Grok 3 |
|---|---|---|
| LMArena Text | 1334 | 1426 |
| LMArena Creative Writing | 1331 | 1414 |
| EQ-Bench Creative Writing | 1126 | 1186 |
| LMArena Multi-Turn | 1334 | 1425 |
| Short-Story Creative Writing | — | 76.4% |
| WildBench | — | 84.9% |
Frequently asked questions
Is Gemma 3 12B better than Grok 3?
Grok 3 is the stronger model overall, scoring 39.9 to 32.1 on the Noometry Index.
Is Gemma 3 12B or Grok 3 better for coding?
Grok 3 scores higher on coding benchmarks: 41.9 versus 31.7 in the Noometry coding category.
How many benchmarks do Gemma 3 12B and Grok 3 share?
17 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Grok 3 has 40.