Model comparison
Grok-3 mini vs o3-pro
o3-pro is the stronger model overall, scoring 42.9 to 41.2 on the Noometry Index.
Last verified . 9 shared benchmarks.
Summary
- They share 9 benchmarks with published results for both. Grok-3 mini scores higher in 1 category and o3-pro in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.2 to 41.0.
- The biggest single-benchmark swing is ARC-AGI-1: 16.5% for Grok-3 mini and 59.3% for o3-pro.
Side by side
| Grok-3 mini | o3-pro | |
|---|---|---|
| Provider | xAI | OpenAI |
| Noometry Index | 41.2 | 42.9 |
| Released | 2025-04-09 | 2025-06-10 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $20 |
| Output $ / M tokens | — | $80 |
| Results tracked | 35 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
Grok-3 mini: 40.8 (#131), o3-pro: 55.5 (#24)
| Benchmark | Grok-3 mini | o3-pro |
|---|---|---|
| Aider Polyglot | 49.3% | 84.9% |
| WeirdML | 42.6% | 58.2% |
| LMArena Coding | 1379 | — |
Reasoning o3-pro leads
Grok-3 mini: 13.6 (#334), o3-pro: 23.8 (#171)
| Benchmark | Grok-3 mini | o3-pro |
|---|---|---|
| ARC-AGI-2 | 0.4% | 4.9% |
| Kagi LLM Benchmark | 61.3% | 72.1% |
| ARC-AGI-1 | 16.5% | 59.3% |
| Epoch Capabilities Index | 140.35 | 147.42 |
| LMArena Hard Prompts | 1375 | — |
| DTBench | — | 86.9% |
| LMCA | — | 38.5% |
Math Not comparable
Grok-3 mini: 42.1 (#85), o3-pro: —
| Benchmark | Grok-3 mini | o3-pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| Omni-MATH | 31.8% | — |
| LMArena Math | 1386 | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
Knowledge Grok-3 mini leads
Grok-3 mini: 46.4 (#81), o3-pro: 29.5 (#238)
| Benchmark | Grok-3 mini | o3-pro |
|---|---|---|
| Confabulations | 10.8% | 14.2% |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.9% | — |
| Vectara Hallucination Rate | — | 23.3% |
| GPQA (HELM) | 67.5% | — |
| LMArena Expert | 1395 | — |
Multilingual Not comparable
Grok-3 mini: 48.1 (#145), o3-pro: —
| Benchmark | Grok-3 mini | o3-pro |
|---|---|---|
| LMArena Non-English | 1352 | — |
| LMArena Chinese | 1387 | — |
| LMArena French | 1357 | — |
| LMArena German | 1349 | — |
| LMArena Japanese | 1342 | — |
| LMArena Korean | 1335 | — |
| LMArena Russian | 1353 | — |
| LMArena Spanish | 1381 | — |
Instruction Following Not comparable
Grok-3 mini: 78.5 (#9), o3-pro: —
| Benchmark | Grok-3 mini | o3-pro |
|---|---|---|
| IFEval | 95.1% | — |
| LMArena Instruction Following | 1357 | — |
Long Context o3-pro leads
Grok-3 mini: 41.0 (#147), o3-pro: 72.2 (#1)
| Benchmark | Grok-3 mini | o3-pro |
|---|---|---|
| Fiction.LiveBench | 66.7% | 97.2% |
| LMArena Longer Query | 1372 | — |
Writing & Preference o3-pro leads
Grok-3 mini: 52.5 (#169), o3-pro: 57.1 (#133)
| Benchmark | Grok-3 mini | o3-pro |
|---|---|---|
| Short-Story Creative Writing | 73.5% | 84.4% |
| LMArena Text | 1370 | — |
| LMArena Creative Writing | 1342 | — |
| WildBench | 65.1% | — |
| LMArena Multi-Turn | 1355 | — |
Frequently asked questions
Is Grok-3 mini better than o3-pro?
o3-pro is the stronger model overall, scoring 42.9 to 41.2 on the Noometry Index.
Is Grok-3 mini or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 40.8 in the Noometry coding category.
How many benchmarks do Grok-3 mini and o3-pro share?
9 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and o3-pro has 12.