Model comparison
Grok 4.1 Fast vs Grok 4.6
Grok 4.6 is the stronger model overall, scoring 56.8 to 40.9 on the Noometry Index. Grok 4.1 Fast costs 11× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. Grok 4.1 Fast scores higher in 0 categories and Grok 4.6 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4.6 leads 66.8 to 30.9.
- The biggest single-benchmark swing is ProofBench: 4% for Grok 4.1 Fast and 51% for Grok 4.6.
- Grok 4.1 Fast is cheaper at $0.20 / $0.50 per million input/output tokens, against $2 / $6 for Grok 4.6.
- Grok 4.6 accepts more context: 500K tokens versus 128K.
Side by side
| Grok 4.1 Fast | Grok 4.6 | |
|---|---|---|
| Provider | xAI | xAI |
| Noometry Index | 40.9 | 56.8 |
| Released | 2025-06-27 | 2026-08-12 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 500K |
| Max output | 30K | 500K |
| Input $ / M tokens | $0.20 | $2 |
| Output $ / M tokens | $0.50 | $6 |
| Results tracked | 32 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.6 leads
Grok 4.1 Fast: 33.8 (#236), Grok 4.6: 58.0 (#14)
| Benchmark | Grok 4.1 Fast | Grok 4.6 |
|---|---|---|
| LMArena WebDev | 1241 | 1620 |
| LMArena Coding | 1411 | 1464 |
| ALE-Bench | 394.93 | 1,508 |
| DeepSWE | — | 67.5% |
| FrontierCode | — | 48% |
| CursorBench | — | 41.4% |
| FrontierSWE | — | 25.3% |
| SciCode | — | 56.5% |
| WeirdML | — | 67.3% |
Agentic & Tool Use Grok 4.6 leads
Grok 4.1 Fast: 36.1 (#35), Grok 4.6: 39.4 (#25)
| Benchmark | Grok 4.1 Fast | Grok 4.6 |
|---|---|---|
| Vending-Bench 2 | 1,107 | 9,047 |
| APEX-Agents | — | 65.3% |
| Berkeley Function Calling Leaderboard | 69.6% | — |
| τ²-bench Banking | 13.1% | — |
| GDP.pdf | — | 17.2% |
| LMArena Search | 1171 | — |
Reasoning Grok 4.6 leads
Grok 4.1 Fast: 42.3 (#45), Grok 4.6: 61.3 (#18)
| Benchmark | Grok 4.1 Fast | Grok 4.6 |
|---|---|---|
| SimpleBench | 56% | 75.9% |
| NYT Connections (extended) | 87.4% | 80% |
| LMArena Hard Prompts | 1407 | 1445 |
| DTBench | 87.7% | 97.3% |
| ARC-AGI-2 | — | 67.1% |
| ARC-AGI-1 | — | 87.5% |
| CritPt | — | 19.7% |
| Chess Puzzles | — | 40% |
| EBR-Bench | — | 30.5% |
| Mystery Game Puzzles | — | 34% |
| LMCA | — | 48.5% |
| Epoch Capabilities Index | — | 156.48 |
| ForecastBench | 61 | — |
Math Grok 4.6 leads
Grok 4.1 Fast: 30.9 (#201), Grok 4.6: 66.8 (#19)
| Benchmark | Grok 4.1 Fast | Grok 4.6 |
|---|---|---|
| ProofBench | 4% | 51% |
| LMArena Math | 1408 | 1416 |
| FrontierMath (Tiers 1-3) | — | 66% |
| FrontierMath Tier 4 | — | 31.7% |
| MathArena Final-Answer Competitions | 60.9% | — |
| OTIS Mock AIME 2024-2025 | — | 99.2% |
Knowledge Grok 4.6 leads
Grok 4.1 Fast: 32.6 (#203), Grok 4.6: 63.3 (#18)
| Benchmark | Grok 4.1 Fast | Grok 4.6 |
|---|---|---|
| LMArena Expert | 1398 | 1463 |
| GPQA Diamond | — | 94% |
| SimpleQA Verified | — | 49.3% |
| Vectara Hallucination Rate | 17.8% | — |
Multimodal Grok 4.6 leads
Grok 4.1 Fast: 36.3 (#71), Grok 4.6: 43.9 (#18)
| Benchmark | Grok 4.1 Fast | Grok 4.6 |
|---|---|---|
| LMArena Vision | 1201 | 1265 |
| Blueprint-Bench 2 | — | 33.2% |
| Furniture Assembly | — | 40% |
| LMArena Document | — | 1452 |
Multilingual Grok 4.6 leads
Grok 4.1 Fast: 51.1 (#110), Grok 4.6: 53.3 (#67)
| Benchmark | Grok 4.1 Fast | Grok 4.6 |
|---|---|---|
| LMArena Non-English | 1391 | 1422 |
| LMArena Chinese | 1441 | 1479 |
| LMArena French | 1416 | 1458 |
| LMArena German | 1404 | 1425 |
| LMArena Japanese | 1347 | 1383 |
| LMArena Korean | 1361 | 1395 |
| LMArena Russian | 1387 | 1427 |
| LMArena Spanish | 1411 | 1408 |
Instruction Following Grok 4.6 leads
Grok 4.1 Fast: 72.8 (#127), Grok 4.6: 75.6 (#59)
| Benchmark | Grok 4.1 Fast | Grok 4.6 |
|---|---|---|
| LMArena Instruction Following | 1376 | 1431 |
Long Context Grok 4.6 leads
Grok 4.1 Fast: 42.4 (#121), Grok 4.6: 44.4 (#62)
| Benchmark | Grok 4.1 Fast | Grok 4.6 |
|---|---|---|
| LMArena Longer Query | 1390 | 1453 |
Writing & Preference Grok 4.6 leads
Grok 4.1 Fast: 57.4 (#126), Grok 4.6: 62.5 (#77)
| Benchmark | Grok 4.1 Fast | Grok 4.6 |
|---|---|---|
| LMArena Text | 1408 | 1427 |
| LMArena Creative Writing | 1394 | 1430 |
| LMArena Multi-Turn | 1389 | 1422 |
| EQ-Bench Creative Writing | 1327 | — |
Frequently asked questions
Is Grok 4.1 Fast better than Grok 4.6?
Grok 4.6 is the stronger model overall, scoring 56.8 to 40.9 on the Noometry Index. Grok 4.1 Fast costs 11× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.
Which is cheaper, Grok 4.1 Fast or Grok 4.6?
Grok 4.1 Fast is cheaper. It lists at $0.20 per million input tokens and $0.50 per million output tokens; Grok 4.6 lists at $2 and $6.
Is Grok 4.1 Fast or Grok 4.6 better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.0 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Grok 4.6 does, with 500K tokens against 128K.
How many benchmarks do Grok 4.1 Fast and Grok 4.6 share?
25 benchmarks have published results for both models. Grok 4.1 Fast has 32 scored results on Noometry and Grok 4.6 has 49.