Model comparison
GPT-4 vs Grok 4.1
Grok 4.1 is the stronger model overall, scoring 41.5 to 29.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Grok 4.1 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4.1 leads 38.9 to 10.8.
Side by side
| GPT-4 | Grok 4.1 | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 29.1 | 41.5 |
| Released | 2023-03-14 | 2025-11-17 |
| Weights | Proprietary | Proprietary |
| Context window | 8K | — |
| Max output | 8K | — |
| Input $ / M tokens | $30 | — |
| Output $ / M tokens | $60 | — |
| Results tracked | 38 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.1 leads
GPT-4: 31.6 (#283), Grok 4.1: 33.7 (#253)
| Benchmark | GPT-4 | Grok 4.1 |
|---|---|---|
| LMArena Coding | 1254 | 1445 |
| LMArena WebDev | — | 1214 |
| WeirdML | 12.4% | — |
| BigCodeBench Instruct | 46% | — |
| BigCodeBench Complete | 57.2% | — |
| HumanEval+ | 79.3% | — |
Agentic & Tool Use Not comparable
GPT-4: —, Grok 4.1: 34.1 (#49)
| Benchmark | GPT-4 | Grok 4.1 |
|---|---|---|
| Cybench | — | 39% |
| METR Time Horizons | 36.1% | — |
Reasoning Grok 4.1 leads
GPT-4: 17.8 (#289), Grok 4.1: 29.5 (#91)
| Benchmark | GPT-4 | Grok 4.1 |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1435 |
| Chess Puzzles | 4% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 62.7% | — |
| LMCA | 17.1% | — |
| BIG-Bench Hard | 75.1% | — |
| Epoch Capabilities Index | 125.89 | — |
| ForecastBench | 57.8 | — |
| HellaSwag | 95.3% | — |
| WinoGrande | 87.5% | — |
Math Grok 4.1 leads
GPT-4: 10.8 (#309), Grok 4.1: 38.9 (#120)
| Benchmark | GPT-4 | Grok 4.1 |
|---|---|---|
| LMArena Math | 1269 | 1422 |
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| MATH Level 5 | 23% | — |
| GSM8K | 92% | — |
Knowledge Grok 4.1 leads
GPT-4: 18.4 (#282), Grok 4.1: 39.5 (#133)
| Benchmark | GPT-4 | Grok 4.1 |
|---|---|---|
| LMArena Expert | 1211 | 1417 |
| GPQA Diamond | 35.7% | — |
| MMLU | 86.4% | — |
| TriviaQA | 84.8% | — |
Multilingual Grok 4.1 leads
GPT-4: 40.6 (#215), Grok 4.1: 53.4 (#68)
| Benchmark | GPT-4 | Grok 4.1 |
|---|---|---|
| LMArena Non-English | 1246 | 1425 |
| LMArena Chinese | 1242 | 1465 |
| LMArena French | 1283 | 1448 |
| LMArena German | 1251 | 1446 |
| LMArena Japanese | 1209 | 1397 |
| LMArena Korean | 1184 | 1407 |
| LMArena Russian | 1251 | 1434 |
| LMArena Spanish | 1261 | 1438 |
Instruction Following Grok 4.1 leads
GPT-4: 65.3 (#222), Grok 4.1: 73.8 (#111)
| Benchmark | GPT-4 | Grok 4.1 |
|---|---|---|
| LMArena Instruction Following | 1241 | 1400 |
Long Context Grok 4.1 leads
GPT-4: 37.7 (#212), Grok 4.1: 43.2 (#100)
| Benchmark | GPT-4 | Grok 4.1 |
|---|---|---|
| LMArena Longer Query | 1244 | 1416 |
Writing & Preference Grok 4.1 leads
GPT-4: 34.9 (#268), Grok 4.1: 62.4 (#75)
| Benchmark | GPT-4 | Grok 4.1 |
|---|---|---|
| LMArena Text | 1263 | 1437 |
| LMArena Creative Writing | 1244 | 1411 |
| LMArena Multi-Turn | 1257 | 1437 |
| EQ-Bench Creative Writing | 752 | — |
Frequently asked questions
Is GPT-4 better than Grok 4.1?
Grok 4.1 is the stronger model overall, scoring 41.5 to 29.1 on the Noometry Index.
Is GPT-4 or Grok 4.1 better for coding?
Grok 4.1 scores higher on coding benchmarks: 33.7 versus 31.6 in the Noometry coding category.
How many benchmarks do GPT-4 and Grok 4.1 share?
17 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Grok 4.1 has 19.