Model comparison
Grok-3 mini vs o1-mini
Grok-3 mini is the stronger model overall, scoring 41.2 to 34.0 on the Noometry Index.
Last verified . 28 shared benchmarks.
Summary
- They share 28 benchmarks with published results for both. Grok-3 mini scores higher in 8 categories and o1-mini in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Grok-3 mini leads 78.5 to 66.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Grok-3 mini and 46.9% for o1-mini.
Side by side
| Grok-3 mini | o1-mini | |
|---|---|---|
| Provider | xAI | OpenAI |
| Noometry Index | 41.2 | 34.0 |
| Released | 2025-04-09 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-3 mini leads
Grok-3 mini: 40.8 (#131), o1-mini: 35.5 (#224)
| Benchmark | Grok-3 mini | o1-mini |
|---|---|---|
| Aider Polyglot | 49.3% | 32.9% |
| WeirdML | 42.6% | 36.3% |
| LMArena Coding | 1379 | 1362 |
| LiveBench Coding | — | 48% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use Not comparable
Grok-3 mini: —, o1-mini: 24.6 (#118)
| Benchmark | Grok-3 mini | o1-mini |
|---|---|---|
| Cybench | — | 10% |
Reasoning Grok-3 mini leads
Grok-3 mini: 13.6 (#334), o1-mini: 8.8 (#346)
| Benchmark | Grok-3 mini | o1-mini |
|---|---|---|
| ARC-AGI-2 | 0.4% | 0.8% |
| ARC-AGI-1 | 16.5% | 14% |
| LMArena Hard Prompts | 1375 | 1333 |
| Epoch Capabilities Index | 140.35 | 135.82 |
| SimpleBench | — | 18.1% |
| Kagi LLM Benchmark | 61.3% | — |
| LiveBench Reasoning | — | 72.3% |
| LiveBench Data Analysis | — | 57.9% |
| LiveBench | — | 57.8% |
Math Grok-3 mini leads
Grok-3 mini: 42.1 (#85), o1-mini: 35.4 (#186)
| Benchmark | Grok-3 mini | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 46.9% |
| LMArena Math | 1386 | 1358 |
| MATH Level 5 | 90.9% | 89.2% |
| FrontierMath (Feb 2025 set) | 5.9% | 1.7% |
| Omni-MATH | 31.8% | — |
| LiveBench Math | — | 62% |
Knowledge Grok-3 mini leads
Grok-3 mini: 46.4 (#81), o1-mini: 34.9 (#192)
| Benchmark | Grok-3 mini | o1-mini |
|---|---|---|
| GPQA Diamond | 76.3% | 62.4% |
| Confabulations | 10.8% | 18.6% |
| LMArena Expert | 1395 | 1316 |
| MMLU-Pro | 79.9% | — |
| GPQA (HELM) | 67.5% | — |
Multilingual Grok-3 mini leads
Grok-3 mini: 48.1 (#145), o1-mini: 43.6 (#182)
| Benchmark | Grok-3 mini | o1-mini |
|---|---|---|
| LMArena Non-English | 1352 | 1289 |
| LMArena Chinese | 1387 | 1314 |
| LMArena French | 1357 | 1293 |
| LMArena German | 1349 | 1278 |
| LMArena Japanese | 1342 | 1245 |
| LMArena Korean | 1335 | 1223 |
| LMArena Russian | 1353 | 1283 |
| LMArena Spanish | 1381 | 1303 |
Instruction Following Grok-3 mini leads
Grok-3 mini: 78.5 (#9), o1-mini: 66.7 (#206)
| Benchmark | Grok-3 mini | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1357 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
| IFEval | 95.1% | — |
Long Context Too close to call
Grok-3 mini: 41.0 (#147), o1-mini: 40.1 (#161)
| Benchmark | Grok-3 mini | o1-mini |
|---|---|---|
| LMArena Longer Query | 1372 | 1320 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference Grok-3 mini leads
Grok-3 mini: 52.5 (#169), o1-mini: 48.4 (#202)
| Benchmark | Grok-3 mini | o1-mini |
|---|---|---|
| LMArena Text | 1370 | 1317 |
| LMArena Creative Writing | 1342 | 1244 |
| Short-Story Creative Writing | 73.5% | 64.9% |
| LMArena Multi-Turn | 1355 | 1314 |
| WildBench | 65.1% | — |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is Grok-3 mini better than o1-mini?
Grok-3 mini is the stronger model overall, scoring 41.2 to 34.0 on the Noometry Index.
Is Grok-3 mini or o1-mini better for coding?
Grok-3 mini scores higher on coding benchmarks: 40.8 versus 35.5 in the Noometry coding category.
How many benchmarks do Grok-3 mini and o1-mini share?
28 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and o1-mini has 39.