Model comparison
GPT-4.1 vs Grok 4.20 (Non-Reasoning)
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 35.9 on the Noometry Index.
Last verified . 33 shared benchmarks.
Summary
- They share 33 benchmarks with published results for both. GPT-4.1 scores higher in 2 categories and Grok 4.20 (Non-Reasoning) in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 11.7.
- The biggest single-benchmark swing is ARC-AGI-1: 5.5% for GPT-4.1 and 89.5% for Grok 4.20 (Non-Reasoning).
- Grok 4.20 (Non-Reasoning) is cheaper at $1.25 / $2.50 per million input/output tokens, against $2 / $8 for GPT-4.1.
- GPT-4.1 accepts more context: 1.05M tokens versus 1M.
Side by side
| GPT-4.1 | Grok 4.20 (Non-Reasoning) | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 35.9 | 48.6 |
| Released | 2025-04-14 | 2026-02-17 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1M |
| Max output | 33K | 30K |
| Input $ / M tokens | $2 | $1.25 |
| Output $ / M tokens | $8 | $2.50 |
| Results tracked | 52 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.20 (Non-Reasoning) leads
GPT-4.1: 34.4 (#238), Grok 4.20 (Non-Reasoning): 42.1 (#112)
| Benchmark | GPT-4.1 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| WeirdML | 39% | 52.3% |
| LMArena Coding | 1391 | 1459 |
| ALE-Bench | 558.1 | 1,150 |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| LMArena WebDev | — | 1375 |
| CadEval | 42% | — |
Agentic & Tool Use Too close to call
GPT-4.1: 34.7 (#43), Grok 4.20 (Non-Reasoning): 34.4 (#46)
| Benchmark | GPT-4.1 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | — | 57.3% |
| Berkeley Function Calling Leaderboard | 54% | — |
| τ²-bench Banking | — | 18% |
| LMArena Search | — | 1189 |
| Vending-Bench 2 | — | 4,663 |
Reasoning Grok 4.20 (Non-Reasoning) leads
GPT-4.1: 11.7 (#339), Grok 4.20 (Non-Reasoning): 52.3 (#32)
| Benchmark | GPT-4.1 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| ARC-AGI-2 | 0.4% | 65.1% |
| Kagi LLM Benchmark | 52.3% | 75% |
| ARC-AGI-1 | 5.5% | 89.5% |
| Chess Puzzles | 6% | 24% |
| LMArena Hard Prompts | 1384 | 1451 |
| DTBench | 68.3% | 90.1% |
| LMCA | 25.6% | 38.7% |
| Epoch Capabilities Index | 136.78 | 151.98 |
| ForecastBench | 61.5 | 61.4 |
| SimpleBench | 27% | — |
| NYT Connections (extended) | — | 85.4% |
| EnigmaEval | 2.2% | — |
| Thematic Generalization | — | 63.8% |
Math Grok 4.20 (Non-Reasoning) leads
GPT-4.1: 22.3 (#280), Grok 4.20 (Non-Reasoning): 48.2 (#65)
| Benchmark | GPT-4.1 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| FrontierMath (Tiers 1-3) | 6% | 44.9% |
| OTIS Mock AIME 2024-2025 | 38.3% | 92.2% |
| LMArena Math | 1370 | 1455 |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 14% |
| Omni-MATH | 47.1% | — |
| MATH Level 5 | 83% | — |
| FrontierMath (Feb 2025 set) | 5.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Grok 4.20 (Non-Reasoning) leads
GPT-4.1: 37.1 (#160), Grok 4.20 (Non-Reasoning): 52.8 (#60)
| Benchmark | GPT-4.1 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| GPQA Diamond | 66.9% | 89.3% |
| SimpleQA Verified | 31.1% | 30.2% |
| LMArena Expert | 1364 | 1439 |
| Humanity's Last Exam | 5.4% | — |
| MMLU-Pro | 81.1% | — |
| Vectara Hallucination Rate | 5.6% | — |
| GPQA (HELM) | 65.9% | — |
Multimodal GPT-4.1 leads
GPT-4.1: 38.2 (#67), Grok 4.20 (Non-Reasoning): 33.3 (#98)
| Benchmark | GPT-4.1 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | 1211 | 1263 |
| GeoBench | 72% | — |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1416 |
Multilingual Grok 4.20 (Non-Reasoning) leads
GPT-4.1: 49.4 (#133), Grok 4.20 (Non-Reasoning): 54.5 (#40)
| Benchmark | GPT-4.1 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1370 | 1441 |
| LMArena Chinese | 1382 | 1481 |
| LMArena French | 1382 | 1476 |
| LMArena German | 1381 | 1465 |
| LMArena Japanese | 1319 | 1449 |
| LMArena Korean | 1339 | 1417 |
| LMArena Russian | 1377 | 1458 |
| LMArena Spanish | 1376 | 1443 |
Instruction Following Grok 4.20 (Non-Reasoning) leads
GPT-4.1: 71.3 (#153), Grok 4.20 (Non-Reasoning): 74.8 (#83)
| Benchmark | GPT-4.1 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1367 | 1420 |
| IFEval | 83.8% | — |
Long Context Grok 4.20 (Non-Reasoning) leads
GPT-4.1: 40.0 (#163), Grok 4.20 (Non-Reasoning): 45.5 (#34)
| Benchmark | GPT-4.1 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1385 | 1437 |
| Fiction.LiveBench | 63.9% | — |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
GPT-4.1: 57.6 (#125), Grok 4.20 (Non-Reasoning): 65.7 (#44)
| Benchmark | GPT-4.1 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1383 | 1451 |
| LMArena Creative Writing | 1363 | 1438 |
| EQ-Bench Creative Writing | 1420 | 1574 |
| LMArena Multi-Turn | 1398 | 1456 |
| WildBench | 85.4% | — |
Frequently asked questions
Is GPT-4.1 better than Grok 4.20 (Non-Reasoning)?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 35.9 on the Noometry Index.
Which is cheaper, GPT-4.1 or Grok 4.20 (Non-Reasoning)?
Grok 4.20 (Non-Reasoning) is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; GPT-4.1 lists at $2 and $8.
Is GPT-4.1 or Grok 4.20 (Non-Reasoning) better for coding?
Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 does, with 1.05M tokens against 1M.
How many benchmarks do GPT-4.1 and Grok 4.20 (Non-Reasoning) share?
33 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.