Model comparison
Grok 3 vs o1-mini
Grok 3 is the stronger model overall, scoring 39.9 to 34.0 on the Noometry Index.
Last verified . 29 shared benchmarks.
Summary
- They share 29 benchmarks with published results for both. Grok 3 scores higher in 8 categories and o1-mini in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 3 leads 46.2 to 34.9.
- The biggest single-benchmark swing is Aider Polyglot: 53.3% for Grok 3 and 32.9% for o1-mini.
Side by side
| Grok 3 | o1-mini | |
|---|---|---|
| Provider | xAI | OpenAI |
| Noometry Index | 39.9 | 34.0 |
| Released | 2025-04-09 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 40 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 3 leads
Grok 3: 41.9 (#115), o1-mini: 35.5 (#224)
| Benchmark | Grok 3 | o1-mini |
|---|---|---|
| Aider Polyglot | 53.3% | 32.9% |
| WeirdML | 37.2% | 36.3% |
| LMArena Coding | 1432 | 1362 |
| LiveBench Coding | — | 48% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use Grok 3 leads
Grok 3: 30.5 (#76), o1-mini: 24.6 (#118)
Reasoning Grok 3 leads
Grok 3: 13.7 (#333), o1-mini: 8.8 (#346)
| Benchmark | Grok 3 | o1-mini |
|---|---|---|
| ARC-AGI-2 | 0% | 0.8% |
| SimpleBench | 36.1% | 18.1% |
| ARC-AGI-1 | 5.5% | 14% |
| LMArena Hard Prompts | 1434 | 1333 |
| Epoch Capabilities Index | 138.33 | 135.82 |
| Kagi LLM Benchmark | 61.3% | — |
| LiveBench Reasoning | — | 72.3% |
| LiveBench Data Analysis | — | 57.9% |
| LiveBench | — | 57.8% |
Math Grok 3 leads
Grok 3: 38.0 (#145), o1-mini: 35.4 (#186)
| Benchmark | Grok 3 | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 55.6% | 46.9% |
| LMArena Math | 1391 | 1358 |
| MATH Level 5 | 88.7% | 89.2% |
| FrontierMath (Feb 2025 set) | 3.8% | 1.7% |
| Omni-MATH | 46.4% | — |
| LiveBench Math | — | 62% |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Grok 3 leads
Grok 3: 46.2 (#82), o1-mini: 34.9 (#192)
| Benchmark | Grok 3 | o1-mini |
|---|---|---|
| GPQA Diamond | 75.8% | 62.4% |
| Confabulations | 14.2% | 18.6% |
| LMArena Expert | 1421 | 1316 |
| MMLU-Pro | 78.8% | — |
| Vectara Hallucination Rate | 5.8% | — |
| GPQA (HELM) | 65% | — |
Multilingual Grok 3 leads
Grok 3: 52.3 (#87), o1-mini: 43.6 (#182)
| Benchmark | Grok 3 | o1-mini |
|---|---|---|
| LMArena Non-English | 1410 | 1289 |
| LMArena Chinese | 1448 | 1314 |
| LMArena French | 1460 | 1293 |
| LMArena German | 1431 | 1278 |
| LMArena Japanese | 1387 | 1245 |
| LMArena Korean | 1373 | 1223 |
| LMArena Russian | 1416 | 1283 |
| LMArena Spanish | 1417 | 1303 |
Instruction Following Grok 3 leads
Grok 3: 75.0 (#73), o1-mini: 66.7 (#206)
| Benchmark | Grok 3 | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1409 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
| IFEval | 88.4% | — |
Long Context o1-mini leads
Grok 3: 38.7 (#192), o1-mini: 40.1 (#161)
| Benchmark | Grok 3 | o1-mini |
|---|---|---|
| LMArena Longer Query | 1439 | 1320 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference Grok 3 leads
Grok 3: 55.8 (#141), o1-mini: 48.4 (#202)
| Benchmark | Grok 3 | o1-mini |
|---|---|---|
| LMArena Text | 1426 | 1317 |
| LMArena Creative Writing | 1414 | 1244 |
| Short-Story Creative Writing | 76.4% | 64.9% |
| LMArena Multi-Turn | 1425 | 1314 |
| EQ-Bench Creative Writing | 1186 | — |
| WildBench | 84.9% | — |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is Grok 3 better than o1-mini?
Grok 3 is the stronger model overall, scoring 39.9 to 34.0 on the Noometry Index.
Is Grok 3 or o1-mini better for coding?
Grok 3 scores higher on coding benchmarks: 41.9 versus 35.5 in the Noometry coding category.
How many benchmarks do Grok 3 and o1-mini share?
29 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and o1-mini has 39.