Model comparison
Grok 3 vs Grok-3 mini
Grok-3 mini is the stronger model overall, scoring 41.0 to 39.6 on the Noometry Index.
Last verified . 35 shared benchmarks.
Summary
- They share 35 benchmarks with published results for both. Grok 3 scores higher in 4 categories and Grok-3 mini in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Grok 3 leads 52.5 to 48.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 55.6% for Grok 3 and 77.8% for Grok-3 mini.
Side by side
| Grok 3 | Grok-3 mini | |
|---|---|---|
| Provider | xAI | xAI |
| Noometry Index | 39.6 | 41.0 |
| Released | 2025-04-09 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 40 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 3 leads
Grok 3: 41.5 (#113), Grok-3 mini: 40.4 (#126)
| Benchmark | Grok 3 | Grok-3 mini |
|---|---|---|
| Aider Polyglot | 53.3% | 49.3% |
| WeirdML | 37.2% | 42.6% |
| LMArena Coding | 1432 | 1380 |
Agentic & Tool Use Not comparable
Grok 3: 30.2 (#69), Grok-3 mini: —
| Benchmark | Grok 3 | Grok-3 mini |
|---|---|---|
| BALROG | 29.5% | — |
Reasoning Too close to call
Grok 3: 13.8 (#322), Grok-3 mini: 13.8 (#323)
| Benchmark | Grok 3 | Grok-3 mini |
|---|---|---|
| ARC-AGI-2 | 0% | 0.4% |
| Kagi LLM Benchmark | 61.3% | 61.3% |
| ARC-AGI-1 | 5.5% | 16.5% |
| LMArena Hard Prompts | 1433 | 1374 |
| Epoch Capabilities Index | 138.34 | 140.35 |
| SimpleBench | 36.1% | — |
Math Grok-3 mini leads
Grok 3: 36.2 (#122), Grok-3 mini: 40.3 (#78)
| Benchmark | Grok 3 | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 55.6% | 77.8% |
| Omni-MATH | 46.4% | 31.8% |
| LMArena Math | 1390 | 1386 |
| MATH Level 5 | 88.7% | 90.9% |
| FrontierMath (Feb 2025 set) | 3.8% | 5.9% |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Too close to call
Grok 3: 46.0 (#76), Grok-3 mini: 46.3 (#75)
| Benchmark | Grok 3 | Grok-3 mini |
|---|---|---|
| GPQA Diamond | 75.8% | 76.3% |
| MMLU-Pro | 78.8% | 79.9% |
| Confabulations | 14.2% | 10.8% |
| GPQA (HELM) | 65% | 67.5% |
| LMArena Expert | 1420 | 1395 |
| Vectara Hallucination Rate | 5.8% | — |
Multilingual Grok 3 leads
Grok 3: 52.5 (#81), Grok-3 mini: 48.3 (#141)
| Benchmark | Grok 3 | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1411 | 1352 |
| LMArena Chinese | 1448 | 1387 |
| LMArena French | 1460 | 1357 |
| LMArena German | 1431 | 1350 |
| LMArena Japanese | 1389 | 1343 |
| LMArena Korean | 1374 | 1336 |
| LMArena Russian | 1416 | 1352 |
| LMArena Spanish | 1417 | 1379 |
Instruction Following Grok-3 mini leads
Grok 3: 75.2 (#69), Grok-3 mini: 78.7 (#8)
| Benchmark | Grok 3 | Grok-3 mini |
|---|---|---|
| IFEval | 88.4% | 95.1% |
| LMArena Instruction Following | 1409 | 1356 |
Long Context Grok-3 mini leads
Grok 3: 38.7 (#187), Grok-3 mini: 41.0 (#142)
| Benchmark | Grok 3 | Grok-3 mini |
|---|---|---|
| Fiction.LiveBench | 58.3% | 66.7% |
| LMArena Longer Query | 1439 | 1372 |
Writing & Preference Grok 3 leads
Grok 3: 56.0 (#136), Grok-3 mini: 52.7 (#163)
| Benchmark | Grok 3 | Grok-3 mini |
|---|---|---|
| LMArena Text | 1426 | 1370 |
| LMArena Creative Writing | 1414 | 1342 |
| Short-Story Creative Writing | 76.4% | 73.5% |
| WildBench | 84.9% | 65.1% |
| LMArena Multi-Turn | 1424 | 1355 |
| EQ-Bench Creative Writing | 1186 | — |
Frequently asked questions
Is Grok 3 better than Grok-3 mini?
Grok-3 mini is the stronger model overall, scoring 41.0 to 39.6 on the Noometry Index.
Is Grok 3 or Grok-3 mini better for coding?
Grok 3 scores higher on coding benchmarks: 41.5 versus 40.4 in the Noometry coding category.
How many benchmarks do Grok 3 and Grok-3 mini share?
35 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Grok-3 mini has 35.