Model comparison
GPT-4.1 vs Grok 4.1
Grok 4.1 is the stronger model overall, scoring 41.5 to 35.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. GPT-4.1 scores higher in 2 categories and Grok 4.1 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.1 leads 29.5 to 11.7.
Side by side
| GPT-4.1 | Grok 4.1 | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 35.9 | 41.5 |
| Released | 2025-04-14 | 2025-11-17 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 33K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $8 | — |
| Results tracked | 52 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-4.1: 34.4 (#238), Grok 4.1: 33.7 (#253)
| Benchmark | GPT-4.1 | Grok 4.1 |
|---|---|---|
| LMArena Coding | 1391 | 1445 |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| LMArena WebDev | — | 1214 |
| WeirdML | 39% | — |
| CadEval | 42% | — |
| ALE-Bench | 558.1 | — |
Agentic & Tool Use Too close to call
GPT-4.1: 34.7 (#43), Grok 4.1: 34.1 (#49)
| Benchmark | GPT-4.1 | Grok 4.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | — |
| Cybench | — | 39% |
Reasoning Grok 4.1 leads
GPT-4.1: 11.7 (#339), Grok 4.1: 29.5 (#91)
| Benchmark | GPT-4.1 | Grok 4.1 |
|---|---|---|
| LMArena Hard Prompts | 1384 | 1435 |
| ARC-AGI-2 | 0.4% | — |
| SimpleBench | 27% | — |
| Kagi LLM Benchmark | 52.3% | — |
| ARC-AGI-1 | 5.5% | — |
| Chess Puzzles | 6% | — |
| EnigmaEval | 2.2% | — |
| DTBench | 68.3% | — |
| LMCA | 25.6% | — |
| Epoch Capabilities Index | 136.78 | — |
| ForecastBench | 61.5 | — |
Math Grok 4.1 leads
GPT-4.1: 22.3 (#280), Grok 4.1: 38.9 (#120)
| Benchmark | GPT-4.1 | Grok 4.1 |
|---|---|---|
| LMArena Math | 1370 | 1422 |
| FrontierMath (Tiers 1-3) | 6% | — |
| OTIS Mock AIME 2024-2025 | 38.3% | — |
| Omni-MATH | 47.1% | — |
| MATH Level 5 | 83% | — |
| FrontierMath (Feb 2025 set) | 5.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Grok 4.1 leads
GPT-4.1: 37.1 (#160), Grok 4.1: 39.5 (#133)
| Benchmark | GPT-4.1 | Grok 4.1 |
|---|---|---|
| LMArena Expert | 1364 | 1417 |
| GPQA Diamond | 66.9% | — |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | 31.1% | — |
| MMLU-Pro | 81.1% | — |
| Vectara Hallucination Rate | 5.6% | — |
| GPQA (HELM) | 65.9% | — |
Multimodal Not comparable
GPT-4.1: 38.2 (#67), Grok 4.1: —
| Benchmark | GPT-4.1 | Grok 4.1 |
|---|---|---|
| LMArena Vision | 1211 | — |
| GeoBench | 72% | — |
Multilingual Grok 4.1 leads
GPT-4.1: 49.4 (#133), Grok 4.1: 53.4 (#68)
| Benchmark | GPT-4.1 | Grok 4.1 |
|---|---|---|
| LMArena Non-English | 1370 | 1425 |
| LMArena Chinese | 1382 | 1465 |
| LMArena French | 1382 | 1448 |
| LMArena German | 1381 | 1446 |
| LMArena Japanese | 1319 | 1397 |
| LMArena Korean | 1339 | 1407 |
| LMArena Russian | 1377 | 1434 |
| LMArena Spanish | 1376 | 1438 |
Instruction Following Grok 4.1 leads
GPT-4.1: 71.3 (#153), Grok 4.1: 73.8 (#111)
| Benchmark | GPT-4.1 | Grok 4.1 |
|---|---|---|
| LMArena Instruction Following | 1367 | 1400 |
| IFEval | 83.8% | — |
Long Context Grok 4.1 leads
GPT-4.1: 40.0 (#163), Grok 4.1: 43.2 (#100)
| Benchmark | GPT-4.1 | Grok 4.1 |
|---|---|---|
| LMArena Longer Query | 1385 | 1416 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference Grok 4.1 leads
GPT-4.1: 57.6 (#125), Grok 4.1: 62.4 (#75)
| Benchmark | GPT-4.1 | Grok 4.1 |
|---|---|---|
| LMArena Text | 1383 | 1437 |
| LMArena Creative Writing | 1363 | 1411 |
| LMArena Multi-Turn | 1398 | 1437 |
| EQ-Bench Creative Writing | 1420 | — |
| WildBench | 85.4% | — |
Frequently asked questions
Is GPT-4.1 better than Grok 4.1?
Grok 4.1 is the stronger model overall, scoring 41.5 to 35.9 on the Noometry Index.
Is GPT-4.1 or Grok 4.1 better for coding?
They score almost the same on coding (34.4 vs 33.7); test both on your own repository before choosing.
How many benchmarks do GPT-4.1 and Grok 4.1 share?
17 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Grok 4.1 has 19.