Model comparison
GPT-4.1 vs Grok-2 (Dec 2024)
GPT-4.1 is the stronger model overall, scoring 35.7 to 33.4 on the Noometry Index.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. GPT-4.1 scores higher in 7 categories and Grok-2 (Dec 2024) in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4.1 leads 57.8 to 48.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 38.3% for GPT-4.1 and 11.5% for Grok-2 (Dec 2024).
Side by side
| GPT-4.1 | Grok-2 (Dec 2024) | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 35.7 | 33.4 |
| Released | 2025-04-14 | 2024-08-13 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 33K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $8 | — |
| Results tracked | 52 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.1 leads
GPT-4.1: 34.2 (#228), Grok-2 (Dec 2024): 32.9 (#254)
| Benchmark | GPT-4.1 | Grok-2 (Dec 2024) |
|---|---|---|
| WeirdML | 39% | 22.2% |
| LMArena Coding | 1391 | 1288 |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| LiveBench Coding | — | 46.4% |
| CadEval | 42% | — |
| ALE-Bench | 558.1 | — |
Agentic & Tool Use Not comparable
GPT-4.1: 34.4 (#40), Grok-2 (Dec 2024): —
| Benchmark | GPT-4.1 | Grok-2 (Dec 2024) |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | — |
Reasoning Grok-2 (Dec 2024) leads
GPT-4.1: 11.7 (#334), Grok-2 (Dec 2024): 16.4 (#294)
| Benchmark | GPT-4.1 | Grok-2 (Dec 2024) |
|---|---|---|
| SimpleBench | 27% | 22.7% |
| LMArena Hard Prompts | 1384 | 1272 |
| DTBench | 68.3% | 65.2% |
| Epoch Capabilities Index | 136.79 | 130.48 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 52.3% | — |
| ARC-AGI-1 | 5.5% | — |
| Chess Puzzles | 6% | — |
| EnigmaEval | 2.2% | — |
| LiveBench Reasoning | — | 54.8% |
| LiveBench Data Analysis | — | 54.5% |
| LMCA | 25.6% | — |
| ForecastBench | 61.5 | — |
| LiveBench | — | 54.3% |
Math GPT-4.1 leads
GPT-4.1: 21.4 (#269), Grok-2 (Dec 2024): 19.6 (#278)
| Benchmark | GPT-4.1 | Grok-2 (Dec 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 38.3% | 11.5% |
| LMArena Math | 1369 | 1283 |
| MATH Level 5 | 83% | 63.5% |
| FrontierMath (Feb 2025 set) | 5.5% | 0.7% |
| FrontierMath (Tiers 1-3) | 6% | — |
| Omni-MATH | 47.1% | — |
| LiveBench Math | — | 54.9% |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GPT-4.1 leads
GPT-4.1: 37.0 (#152), Grok-2 (Dec 2024): 29.8 (#225)
| Benchmark | GPT-4.1 | Grok-2 (Dec 2024) |
|---|---|---|
| GPQA Diamond | 66.9% | 53.8% |
| LMArena Expert | 1364 | 1254 |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | 31.1% | — |
| MMLU-Pro | 81.1% | — |
| Confabulations | — | 20.1% |
| Vectara Hallucination Rate | 5.6% | — |
| GPQA (HELM) | 65.9% | — |
Multimodal Not comparable
GPT-4.1: 37.5 (#66), Grok-2 (Dec 2024): —
| Benchmark | GPT-4.1 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Vision | 1210 | — |
| GeoBench | 72% | — |
Multilingual GPT-4.1 leads
GPT-4.1: 49.6 (#128), Grok-2 (Dec 2024): 43.3 (#183)
| Benchmark | GPT-4.1 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Non-English | 1370 | 1282 |
| LMArena Chinese | 1382 | 1289 |
| LMArena French | 1383 | 1317 |
| LMArena German | 1380 | 1287 |
| LMArena Japanese | 1320 | 1244 |
| LMArena Korean | 1339 | 1237 |
| LMArena Russian | 1377 | 1286 |
| LMArena Spanish | 1375 | 1281 |
Instruction Following GPT-4.1 leads
GPT-4.1: 71.5 (#148), Grok-2 (Dec 2024): 67.1 (#197)
| Benchmark | GPT-4.1 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Instruction Following | 1367 | 1270 |
| LiveBench Instruction Following | — | 69.6% |
| IFEval | 83.8% | — |
Long Context GPT-4.1 leads
GPT-4.1: 40.0 (#158), Grok-2 (Dec 2024): 38.7 (#186)
| Benchmark | GPT-4.1 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Longer Query | 1385 | 1276 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference GPT-4.1 leads
GPT-4.1: 57.8 (#120), Grok-2 (Dec 2024): 48.8 (#192)
| Benchmark | GPT-4.1 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Text | 1383 | 1305 |
| LMArena Creative Writing | 1363 | 1284 |
| LMArena Multi-Turn | 1398 | 1290 |
| Short-Story Creative Writing | — | 63.6% |
| EQ-Bench Creative Writing | 1420 | — |
| WildBench | 85.4% | — |
| LiveBench Language | — | 45.6% |
Frequently asked questions
Is GPT-4.1 better than Grok-2 (Dec 2024)?
GPT-4.1 is the stronger model overall, scoring 35.7 to 33.4 on the Noometry Index.
Is GPT-4.1 or Grok-2 (Dec 2024) better for coding?
GPT-4.1 scores higher on coding benchmarks: 34.2 versus 32.9 in the Noometry coding category.
How many benchmarks do GPT-4.1 and Grok-2 (Dec 2024) share?
25 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Grok-2 (Dec 2024) has 34.