Model comparison
Grok-2 (Dec 2024) vs Grok-3 mini
Grok-3 mini is the stronger model overall, scoring 41.2 to 33.7 on the Noometry Index.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 1 category and Grok-3 mini in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok-3 mini leads 42.1 to 20.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 11.5% for Grok-2 (Dec 2024) and 77.8% for Grok-3 mini.
Side by side
| Grok-2 (Dec 2024) | Grok-3 mini | |
|---|---|---|
| Provider | xAI | xAI |
| Noometry Index | 33.7 | 41.2 |
| Released | 2024-08-13 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 34 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-3 mini leads
Grok-2 (Dec 2024): 33.3 (#258), Grok-3 mini: 40.8 (#131)
| Benchmark | Grok-2 (Dec 2024) | Grok-3 mini |
|---|---|---|
| WeirdML | 22.2% | 42.6% |
| LMArena Coding | 1287 | 1379 |
| Aider Polyglot | — | 49.3% |
| LiveBench Coding | 46.4% | — |
Reasoning Grok-2 (Dec 2024) leads
Grok-2 (Dec 2024): 16.9 (#299), Grok-3 mini: 13.6 (#334)
| Benchmark | Grok-2 (Dec 2024) | Grok-3 mini |
|---|---|---|
| LMArena Hard Prompts | 1272 | 1375 |
| Epoch Capabilities Index | 130.48 | 140.35 |
| ARC-AGI-2 | — | 0.4% |
| SimpleBench | 22.7% | — |
| Kagi LLM Benchmark | — | 61.3% |
| ARC-AGI-1 | — | 16.5% |
| LiveBench Reasoning | 54.8% | — |
| DTBench | 65.2% | — |
| LiveBench Data Analysis | 54.5% | — |
| LiveBench | 54.3% | — |
Math Grok-3 mini leads
Grok-2 (Dec 2024): 20.8 (#284), Grok-3 mini: 42.1 (#85)
| Benchmark | Grok-2 (Dec 2024) | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 11.5% | 77.8% |
| LMArena Math | 1283 | 1386 |
| MATH Level 5 | 63.5% | 90.9% |
| FrontierMath (Feb 2025 set) | 0.7% | 5.9% |
| Omni-MATH | — | 31.8% |
| LiveBench Math | 54.9% | — |
Knowledge Grok-3 mini leads
Grok-2 (Dec 2024): 29.8 (#233), Grok-3 mini: 46.4 (#81)
| Benchmark | Grok-2 (Dec 2024) | Grok-3 mini |
|---|---|---|
| GPQA Diamond | 53.8% | 76.3% |
| Confabulations | 20.1% | 10.8% |
| LMArena Expert | 1254 | 1395 |
| MMLU-Pro | — | 79.9% |
| GPQA (HELM) | — | 67.5% |
Multilingual Grok-3 mini leads
Grok-2 (Dec 2024): 43.1 (#188), Grok-3 mini: 48.1 (#145)
| Benchmark | Grok-2 (Dec 2024) | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1282 | 1352 |
| LMArena Chinese | 1289 | 1387 |
| LMArena French | 1318 | 1357 |
| LMArena German | 1287 | 1349 |
| LMArena Japanese | 1244 | 1342 |
| LMArena Korean | 1237 | 1335 |
| LMArena Russian | 1286 | 1353 |
| LMArena Spanish | 1281 | 1381 |
Instruction Following Grok-3 mini leads
Grok-2 (Dec 2024): 66.9 (#202), Grok-3 mini: 78.5 (#9)
| Benchmark | Grok-2 (Dec 2024) | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1270 | 1357 |
| LiveBench Instruction Following | 69.6% | — |
| IFEval | — | 95.1% |
Long Context Grok-3 mini leads
Grok-2 (Dec 2024): 38.8 (#190), Grok-3 mini: 41.0 (#147)
| Benchmark | Grok-2 (Dec 2024) | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1276 | 1372 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Grok-3 mini leads
Grok-2 (Dec 2024): 48.6 (#198), Grok-3 mini: 52.5 (#169)
| Benchmark | Grok-2 (Dec 2024) | Grok-3 mini |
|---|---|---|
| LMArena Text | 1305 | 1370 |
| LMArena Creative Writing | 1284 | 1342 |
| Short-Story Creative Writing | 63.6% | 73.5% |
| LMArena Multi-Turn | 1290 | 1355 |
| WildBench | — | 65.1% |
| LiveBench Language | 45.6% | — |
Frequently asked questions
Is Grok-2 (Dec 2024) better than Grok-3 mini?
Grok-3 mini is the stronger model overall, scoring 41.2 to 33.7 on the Noometry Index.
Is Grok-2 (Dec 2024) or Grok-3 mini better for coding?
Grok-3 mini scores higher on coding benchmarks: 40.8 versus 33.3 in the Noometry coding category.
How many benchmarks do Grok-2 (Dec 2024) and Grok-3 mini share?
25 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Grok-3 mini has 35.