Model comparison
Grok 4 vs o1
Grok 4 is the stronger model overall, scoring 48.1 to 40.9 on the Noometry Index.
Last verified . 33 shared benchmarks.
Summary
- They share 33 benchmarks with published results for both. Grok 4 scores higher in 9 categories and o1 in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in long context, where Grok 4 leads 63.1 to 50.3.
- The biggest single-benchmark swing is ARC-AGI-1: 66.7% for Grok 4 and 30.7% for o1.
Side by side
| Grok 4 | o1 | |
|---|---|---|
| Provider | xAI | OpenAI |
| Noometry Index | 48.1 | 40.9 |
| Released | 2025-07-09 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $15 |
| Output $ / M tokens | — | $60 |
| Results tracked | 48 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4 leads
Grok 4: 50.3 (#46), o1: 46.1 (#70)
| Benchmark | Grok 4 | o1 |
|---|---|---|
| Aider Polyglot | 79.6% | 61.7% |
| WeirdML | 45.7% | 47.6% |
| LMArena Coding | 1408 | 1367 |
| LiveBench Coding | — | 69.7% |
| CadEval | — | 56% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use Grok 4 leads
Grok 4: 32.3 (#68), o1: 24.6 (#117)
| Benchmark | Grok 4 | o1 |
|---|---|---|
| Cybench | 43% | 10% |
| METR Time Horizons | 66.6% | 51.1% |
| Terminal-Bench | 27.2% | — |
| Berkeley Function Calling Leaderboard | 63% | — |
| GDPval | 21.1% | — |
| DeepResearch Bench | 47.3% | — |
| BALROG | 43.6% | — |
| LMArena Search | 1142 | — |
Reasoning Grok 4 leads
Grok 4: 36.7 (#65), o1: 27.9 (#111)
| Benchmark | Grok 4 | o1 |
|---|---|---|
| SimpleBench | 60.5% | 41.7% |
| ARC-AGI-1 | 66.7% | 30.7% |
| Chess Puzzles | 28% | 15% |
| LMArena Hard Prompts | 1409 | 1371 |
| Epoch Capabilities Index | 146.44 | 141.91 |
| ARC-AGI-2 | 16% | — |
| Kagi LLM Benchmark | 73.6% | — |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| DTBench | — | 74.7% |
| LiveBench Data Analysis | — | 65.5% |
| LMCA | — | 22.3% |
| ForecastBench | 60.9 | — |
| LiveBench | — | 75.7% |
Math Grok 4 leads
Grok 4: 48.4 (#64), o1: 36.1 (#175)
| Benchmark | Grok 4 | o1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 84% | 73.3% |
| LMArena Math | 1422 | 1388 |
| FrontierMath (Feb 2025 set) | 19.7% | 9.3% |
| FrontierMath (Tiers 1-3) | — | 14.7% |
| Omni-MATH | 60.3% | — |
| LiveBench Math | — | 80.3% |
| MATH Level 5 | — | 94.7% |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Grok 4 leads
Grok 4: 53.8 (#55), o1: 41.5 (#110)
| Benchmark | Grok 4 | o1 |
|---|---|---|
| GPQA Diamond | 87% | 76.8% |
| Confabulations | 12.4% | 11.7% |
| LMArena Expert | 1415 | 1361 |
| Humanity's Last Exam | — | 8% |
| SimpleQA Verified | — | 41.1% |
| MMLU-Pro | 85.1% | — |
| GPQA (HELM) | 72.7% | — |
Multimodal Too close to call
Grok 4: 33.7 (#94), o1: 34.2 (#93)
| Benchmark | Grok 4 | o1 |
|---|---|---|
| LMArena Vision | 1210 | 1168 |
| GeoBench | 45% | 80% |
| VPCT | — | 37% |
| SpatialViz-Bench | — | 41.4% |
Multilingual Grok 4 leads
Grok 4: 51.8 (#103), o1: 48.6 (#142)
| Benchmark | Grok 4 | o1 |
|---|---|---|
| LMArena Non-English | 1403 | 1358 |
| LMArena Chinese | 1427 | 1394 |
| LMArena French | 1418 | 1344 |
| LMArena German | 1429 | 1337 |
| LMArena Japanese | 1394 | 1346 |
| LMArena Korean | 1377 | 1396 |
| LMArena Russian | 1410 | 1356 |
| LMArena Spanish | 1420 | 1345 |
Instruction Following Grok 4 leads
Grok 4: 79.2 (#5), o1: 74.8 (#86)
| Benchmark | Grok 4 | o1 |
|---|---|---|
| LMArena Instruction Following | 1387 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
| IFEval | 94.9% | — |
Long Context Grok 4 leads
Grok 4: 63.1 (#4), o1: 50.3 (#9)
| Benchmark | Grok 4 | o1 |
|---|---|---|
| Fiction.LiveBench | 94.4% | 83.3% |
| LMArena Longer Query | 1409 | 1378 |
Writing & Preference Grok 4 leads
Grok 4: 58.5 (#116), o1: 55.6 (#144)
| Benchmark | Grok 4 | o1 |
|---|---|---|
| LMArena Text | 1411 | 1366 |
| LMArena Creative Writing | 1397 | 1348 |
| Short-Story Creative Writing | 76.9% | 70.2% |
| LMArena Multi-Turn | 1416 | 1369 |
| WildBench | 79.7% | — |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is Grok 4 better than o1?
Grok 4 is the stronger model overall, scoring 48.1 to 40.9 on the Noometry Index.
Is Grok 4 or o1 better for coding?
Grok 4 scores higher on coding benchmarks: 50.3 versus 46.1 in the Noometry coding category.
How many benchmarks do Grok 4 and o1 share?
33 benchmarks have published results for both models. Grok 4 has 48 scored results on Noometry and o1 has 52.