Model comparison
GPT-4.1 vs Grok 4.1 Fast
Grok 4.1 Fast is the stronger model overall, scoring 40.9 to 35.7 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 4 categories and Grok 4.1 Fast in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.1 Fast leads 42.3 to 11.7.
- The biggest single-benchmark swing is SimpleBench: 27% for GPT-4.1 and 56% for Grok 4.1 Fast.
- Grok 4.1 Fast is cheaper at $0.20 / $0.50 per million input/output tokens, against $2 / $8 for GPT-4.1.
- GPT-4.1 accepts more context: 1.05M tokens versus 128K.
Side by side
| GPT-4.1 | Grok 4.1 Fast | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 35.7 | 40.9 |
| Released | 2025-04-14 | 2025-06-27 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 128K |
| Max output | 33K | 30K |
| Input $ / M tokens | $2 | $0.20 |
| Output $ / M tokens | $8 | $0.50 |
| Results tracked | 52 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-4.1: 34.2 (#228), Grok 4.1 Fast: 33.8 (#236)
| Benchmark | GPT-4.1 | Grok 4.1 Fast |
|---|---|---|
| LMArena Coding | 1391 | 1411 |
| ALE-Bench | 558.1 | 394.93 |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| LMArena WebDev | — | 1241 |
| WeirdML | 39% | — |
| CadEval | 42% | — |
Agentic & Tool Use Grok 4.1 Fast leads
GPT-4.1: 34.4 (#40), Grok 4.1 Fast: 36.1 (#35)
| Benchmark | GPT-4.1 | Grok 4.1 Fast |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | 69.6% |
| τ²-bench Banking | — | 13.1% |
| LMArena Search | — | 1171 |
| Vending-Bench 2 | — | 1,107 |
Reasoning Grok 4.1 Fast leads
GPT-4.1: 11.7 (#334), Grok 4.1 Fast: 42.3 (#45)
| Benchmark | GPT-4.1 | Grok 4.1 Fast |
|---|---|---|
| SimpleBench | 27% | 56% |
| LMArena Hard Prompts | 1384 | 1407 |
| DTBench | 68.3% | 87.7% |
| ForecastBench | 61.5 | 61 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 52.3% | — |
| NYT Connections (extended) | — | 87.4% |
| ARC-AGI-1 | 5.5% | — |
| Chess Puzzles | 6% | — |
| EnigmaEval | 2.2% | — |
| LMCA | 25.6% | — |
| Epoch Capabilities Index | 136.79 | — |
Math Grok 4.1 Fast leads
GPT-4.1: 21.4 (#269), Grok 4.1 Fast: 30.9 (#201)
| Benchmark | GPT-4.1 | Grok 4.1 Fast |
|---|---|---|
| LMArena Math | 1369 | 1408 |
| FrontierMath (Tiers 1-3) | 6% | — |
| MathArena Final-Answer Competitions | — | 60.9% |
| OTIS Mock AIME 2024-2025 | 38.3% | — |
| ProofBench | — | 4% |
| Omni-MATH | 47.1% | — |
| MATH Level 5 | 83% | — |
| FrontierMath (Feb 2025 set) | 5.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GPT-4.1 leads
GPT-4.1: 37.0 (#152), Grok 4.1 Fast: 32.6 (#203)
| Benchmark | GPT-4.1 | Grok 4.1 Fast |
|---|---|---|
| Vectara Hallucination Rate | 5.6% | 17.8% |
| LMArena Expert | 1364 | 1398 |
| GPQA Diamond | 66.9% | — |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | 31.1% | — |
| MMLU-Pro | 81.1% | — |
| GPQA (HELM) | 65.9% | — |
Multimodal GPT-4.1 leads
GPT-4.1: 37.5 (#66), Grok 4.1 Fast: 36.3 (#71)
| Benchmark | GPT-4.1 | Grok 4.1 Fast |
|---|---|---|
| LMArena Vision | 1210 | 1201 |
| GeoBench | 72% | — |
Multilingual Grok 4.1 Fast leads
GPT-4.1: 49.6 (#128), Grok 4.1 Fast: 51.1 (#110)
| Benchmark | GPT-4.1 | Grok 4.1 Fast |
|---|---|---|
| LMArena Non-English | 1370 | 1391 |
| LMArena Chinese | 1382 | 1441 |
| LMArena French | 1383 | 1416 |
| LMArena German | 1380 | 1404 |
| LMArena Japanese | 1320 | 1347 |
| LMArena Korean | 1339 | 1361 |
| LMArena Russian | 1377 | 1387 |
| LMArena Spanish | 1375 | 1411 |
Instruction Following Grok 4.1 Fast leads
GPT-4.1: 71.5 (#148), Grok 4.1 Fast: 72.8 (#127)
| Benchmark | GPT-4.1 | Grok 4.1 Fast |
|---|---|---|
| LMArena Instruction Following | 1367 | 1376 |
| IFEval | 83.8% | — |
Long Context Grok 4.1 Fast leads
GPT-4.1: 40.0 (#158), Grok 4.1 Fast: 42.4 (#121)
| Benchmark | GPT-4.1 | Grok 4.1 Fast |
|---|---|---|
| LMArena Longer Query | 1385 | 1390 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference Too close to call
GPT-4.1: 57.8 (#120), Grok 4.1 Fast: 57.4 (#126)
| Benchmark | GPT-4.1 | Grok 4.1 Fast |
|---|---|---|
| LMArena Text | 1383 | 1408 |
| LMArena Creative Writing | 1363 | 1394 |
| EQ-Bench Creative Writing | 1420 | 1327 |
| LMArena Multi-Turn | 1398 | 1389 |
| WildBench | 85.4% | — |
Frequently asked questions
Is GPT-4.1 better than Grok 4.1 Fast?
Grok 4.1 Fast is the stronger model overall, scoring 40.9 to 35.7 on the Noometry Index.
Which is cheaper, GPT-4.1 or Grok 4.1 Fast?
Grok 4.1 Fast is cheaper. It lists at $0.20 per million input tokens and $0.50 per million output tokens; GPT-4.1 lists at $2 and $8.
Is GPT-4.1 or Grok 4.1 Fast better for coding?
They score almost the same on coding (34.2 vs 33.8); test both on your own repository before choosing.
Which has the bigger context window?
GPT-4.1 does, with 1.05M tokens against 128K.
How many benchmarks do GPT-4.1 and Grok 4.1 Fast share?
25 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Grok 4.1 Fast has 32.