Model comparison
Grok-2 (Dec 2024) vs o3-mini
o3-mini is the stronger model overall, scoring 36.7 to 33.7 on the Noometry Index.
Last verified . 34 shared benchmarks.
Summary
- They share 34 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 2 categories and o3-mini in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3-mini leads 38.3 to 29.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 11.5% for Grok-2 (Dec 2024) and 76.9% for o3-mini.
Side by side
| Grok-2 (Dec 2024) | o3-mini | |
|---|---|---|
| Provider | xAI | OpenAI |
| Noometry Index | 33.7 | 36.7 |
| Released | 2024-08-13 | 2024-12-20 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $1.10 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 34 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
Grok-2 (Dec 2024): 33.3 (#258), o3-mini: 40.8 (#132)
| Benchmark | Grok-2 (Dec 2024) | o3-mini |
|---|---|---|
| WeirdML | 22.2% | 43.7% |
| LiveBench Coding | 46.4% | 82.7% |
| LMArena Coding | 1287 | 1378 |
| Aider Polyglot | — | 60.4% |
| SciCode | — | 39.8% |
| GSO | — | 1.3% |
| CadEval | — | 54% |
Agentic & Tool Use Not comparable
Grok-2 (Dec 2024): —, o3-mini: 29.6 (#84)
| Benchmark | Grok-2 (Dec 2024) | o3-mini |
|---|---|---|
| Cybench | — | 22.5% |
Reasoning Too close to call
Grok-2 (Dec 2024): 16.9 (#299), o3-mini: 16.3 (#305)
| Benchmark | Grok-2 (Dec 2024) | o3-mini |
|---|---|---|
| SimpleBench | 22.7% | 22.8% |
| LiveBench Reasoning | 54.8% | 89.6% |
| LMArena Hard Prompts | 1272 | 1366 |
| DTBench | 65.2% | 68.8% |
| LiveBench Data Analysis | 54.5% | 70.6% |
| Epoch Capabilities Index | 130.48 | 140.34 |
| LiveBench | 54.3% | 75.9% |
| ARC-AGI-2 | — | 3% |
| ARC-AGI-1 | — | 34.5% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 17% |
| Mystery Game Puzzles | — | 7% |
| LMCA | — | 19% |
| ForecastBench | — | 59.6 |
Math o3-mini leads
Grok-2 (Dec 2024): 20.8 (#284), o3-mini: 28.1 (#244)
| Benchmark | Grok-2 (Dec 2024) | o3-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 11.5% | 76.9% |
| LiveBench Math | 54.9% | 77.3% |
| LMArena Math | 1283 | 1396 |
| MATH Level 5 | 63.5% | 96.5% |
| FrontierMath (Feb 2025 set) | 0.7% | 12.4% |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge o3-mini leads
Grok-2 (Dec 2024): 29.8 (#233), o3-mini: 38.3 (#146)
| Benchmark | Grok-2 (Dec 2024) | o3-mini |
|---|---|---|
| GPQA Diamond | 53.8% | 77% |
| Confabulations | 20.1% | 17.9% |
| LMArena Expert | 1254 | 1364 |
| SimpleQA Verified | — | 15.3% |
Multilingual o3-mini leads
Grok-2 (Dec 2024): 43.1 (#188), o3-mini: 45.7 (#164)
| Benchmark | Grok-2 (Dec 2024) | o3-mini |
|---|---|---|
| LMArena Non-English | 1282 | 1319 |
| LMArena Chinese | 1289 | 1379 |
| LMArena French | 1318 | 1334 |
| LMArena German | 1287 | 1303 |
| LMArena Japanese | 1244 | 1286 |
| LMArena Korean | 1237 | 1314 |
| LMArena Russian | 1286 | 1304 |
| LMArena Spanish | 1281 | 1321 |
Instruction Following o3-mini leads
Grok-2 (Dec 2024): 66.9 (#202), o3-mini: 75.1 (#72)
| Benchmark | Grok-2 (Dec 2024) | o3-mini |
|---|---|---|
| LiveBench Instruction Following | 69.6% | 84.4% |
| LMArena Instruction Following | 1270 | 1337 |
Long Context Grok-2 (Dec 2024) leads
Grok-2 (Dec 2024): 38.8 (#190), o3-mini: 33.8 (#256)
| Benchmark | Grok-2 (Dec 2024) | o3-mini |
|---|---|---|
| LMArena Longer Query | 1276 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference o3-mini leads
Grok-2 (Dec 2024): 48.6 (#198), o3-mini: 50.3 (#182)
| Benchmark | Grok-2 (Dec 2024) | o3-mini |
|---|---|---|
| LMArena Text | 1305 | 1337 |
| LMArena Creative Writing | 1284 | 1286 |
| Short-Story Creative Writing | 63.6% | 61.7% |
| LMArena Multi-Turn | 1290 | 1320 |
| LiveBench Language | 45.6% | 50.7% |
Frequently asked questions
Is Grok-2 (Dec 2024) better than o3-mini?
o3-mini is the stronger model overall, scoring 36.7 to 33.7 on the Noometry Index.
Is Grok-2 (Dec 2024) or o3-mini better for coding?
o3-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 o3-mini share?
34 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and o3-mini has 51.