Model comparison
Grok-2 (Dec 2024) vs o4-mini
o4-mini is the stronger model overall, scoring 41.6 to 33.4 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 0 categories and o4-mini in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where o4-mini leads 40.2 to 19.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 11.5% for Grok-2 (Dec 2024) and 81.7% for o4-mini.
Side by side
| Grok-2 (Dec 2024) | o4-mini | |
|---|---|---|
| Provider | xAI | OpenAI |
| Noometry Index | 33.4 | 41.6 |
| Released | 2024-08-13 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $1.10 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 34 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o4-mini leads
Grok-2 (Dec 2024): 32.9 (#254), o4-mini: 41.6 (#110)
| Benchmark | Grok-2 (Dec 2024) | o4-mini |
|---|---|---|
| WeirdML | 22.2% | 52.6% |
| LMArena Coding | 1288 | 1369 |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| GSO | — | 3.6% |
| LiveBench Coding | 46.4% | — |
| CadEval | — | 62% |
| ALE-Bench | — | 826.17 |
| AlgoTune | — | 1.72 |
Agentic & Tool Use Not comparable
Grok-2 (Dec 2024): —, o4-mini: 32.3 (#57)
| Benchmark | Grok-2 (Dec 2024) | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| METR Time Horizons | — | 63.9% |
Reasoning o4-mini leads
Grok-2 (Dec 2024): 16.4 (#294), o4-mini: 24.6 (#143)
| Benchmark | Grok-2 (Dec 2024) | o4-mini |
|---|---|---|
| SimpleBench | 22.7% | 38.7% |
| LMArena Hard Prompts | 1272 | 1351 |
| DTBench | 65.2% | 77.6% |
| Epoch Capabilities Index | 130.48 | 145.63 |
| ARC-AGI-2 | — | 6.1% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 58.7% |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 26% |
| EnigmaEval | — | 9.2% |
| LiveBench Reasoning | 54.8% | — |
| Mystery Game Puzzles | — | 5% |
| LiveBench Data Analysis | 54.5% | — |
| LMCA | — | 26.5% |
| ForecastBench | — | 61.8 |
| LiveBench | 54.3% | — |
Math o4-mini leads
Grok-2 (Dec 2024): 19.6 (#278), o4-mini: 40.2 (#79)
| Benchmark | Grok-2 (Dec 2024) | o4-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 11.5% | 81.7% |
| LMArena Math | 1283 | 1390 |
| MATH Level 5 | 63.5% | 97.8% |
| FrontierMath (Feb 2025 set) | 0.7% | 24.8% |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
| Omni-MATH | — | 72% |
| LiveBench Math | 54.9% | — |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge o4-mini leads
Grok-2 (Dec 2024): 29.8 (#225), o4-mini: 43.5 (#83)
| Benchmark | Grok-2 (Dec 2024) | o4-mini |
|---|---|---|
| GPQA Diamond | 53.8% | 79.6% |
| Confabulations | 20.1% | 15.8% |
| LMArena Expert | 1254 | 1344 |
| Humanity's Last Exam | — | 18.1% |
| SimpleQA Verified | — | 19.6% |
| MMLU-Pro | — | 82% |
| Vectara Hallucination Rate | — | 18.6% |
| GPQA (HELM) | — | 73.5% |
Multimodal Not comparable
Grok-2 (Dec 2024): —, o4-mini: 39.5 (#46)
| Benchmark | Grok-2 (Dec 2024) | o4-mini |
|---|---|---|
| LMArena Vision | — | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
Multilingual o4-mini leads
Grok-2 (Dec 2024): 43.3 (#183), o4-mini: 47.2 (#149)
| Benchmark | Grok-2 (Dec 2024) | o4-mini |
|---|---|---|
| LMArena Non-English | 1282 | 1336 |
| LMArena Chinese | 1289 | 1355 |
| LMArena French | 1317 | 1362 |
| LMArena German | 1287 | 1336 |
| LMArena Japanese | 1244 | 1308 |
| LMArena Korean | 1237 | 1313 |
| LMArena Russian | 1286 | 1334 |
| LMArena Spanish | 1281 | 1346 |
Instruction Following o4-mini leads
Grok-2 (Dec 2024): 67.1 (#197), o4-mini: 75.4 (#63)
| Benchmark | Grok-2 (Dec 2024) | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1270 | 1321 |
| LiveBench Instruction Following | 69.6% | — |
| IFEval | — | 92.8% |
Long Context o4-mini leads
Grok-2 (Dec 2024): 38.7 (#186), o4-mini: 45.5 (#31)
| Benchmark | Grok-2 (Dec 2024) | o4-mini |
|---|---|---|
| LMArena Longer Query | 1276 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference o4-mini leads
Grok-2 (Dec 2024): 48.8 (#192), o4-mini: 54.2 (#148)
| Benchmark | Grok-2 (Dec 2024) | o4-mini |
|---|---|---|
| LMArena Text | 1305 | 1353 |
| LMArena Creative Writing | 1284 | 1294 |
| Short-Story Creative Writing | 63.6% | 75% |
| LMArena Multi-Turn | 1290 | 1350 |
| WildBench | — | 85.4% |
| LiveBench Language | 45.6% | — |
Frequently asked questions
Is Grok-2 (Dec 2024) better than o4-mini?
o4-mini is the stronger model overall, scoring 41.6 to 33.4 on the Noometry Index.
Is Grok-2 (Dec 2024) or o4-mini better for coding?
o4-mini scores higher on coding benchmarks: 41.6 versus 32.9 in the Noometry coding category.
How many benchmarks do Grok-2 (Dec 2024) and o4-mini share?
27 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and o4-mini has 60.