Model comparison
Grok 4.1 Fast vs Inkling
Inkling is the stronger model overall, scoring 44.1 to 41.4 on the Noometry Index. Grok 4.1 Fast costs 9.4× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. Grok 4.1 Fast scores higher in 3 categories and Inkling in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.1 to 33.1.
- The biggest single-benchmark swing is τ²-bench Banking: 13.1% for Grok 4.1 Fast and 25% for Inkling.
- Grok 4.1 Fast is cheaper at $0.20 / $0.50 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Grok 4.1 Fast accepts more context: 128K tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.
Side by side
| Grok 4.1 Fast | Inkling | |
|---|---|---|
| Provider | xAI | Thinking Machines Lab |
| Noometry Index | 41.4 | 44.1 |
| Released | 2025-06-27 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 128K | 66K |
| Max output | 30K | 66K |
| Input $ / M tokens | $0.20 | $1.87 |
| Output $ / M tokens | $0.50 | $4.68 |
| Results tracked | 32 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Grok 4.1 Fast: 34.1 (#245), Inkling: 34.5 (#234)
| Benchmark | Grok 4.1 Fast | Inkling |
|---|---|---|
| LMArena WebDev | 1242 | 1413 |
| LMArena Coding | 1411 | 1464 |
| ALE-Bench | 394.93 | 946 |
| FrontierCode | — | 14% |
| FrontierSWE | — | 4.1% |
| SciCode | — | 47% |
| WeirdML | — | 32.3% |
Agentic & Tool Use Grok 4.1 Fast leads
Grok 4.1 Fast: 36.3 (#39), Inkling: 29.6 (#85)
| Benchmark | Grok 4.1 Fast | Inkling |
|---|---|---|
| τ²-bench Banking | 13.1% | 25% |
| APEX-Agents | — | 33.8% |
| Berkeley Function Calling Leaderboard | 69.6% | — |
| LMArena Search | 1171 | — |
| Vending-Bench 2 | 1,107 | — |
Reasoning Grok 4.1 Fast leads
Grok 4.1 Fast: 43.4 (#49), Inkling: 40.4 (#56)
| Benchmark | Grok 4.1 Fast | Inkling |
|---|---|---|
| SimpleBench | 56% | 50% |
| LMArena Hard Prompts | 1407 | 1451 |
| DTBench | 87.7% | 87.5% |
| ARC-AGI-2 | — | 36.5% |
| NYT Connections (extended) | 87.4% | — |
| ARC-AGI-1 | — | 79.5% |
| CritPt | — | 5.4% |
| Chess Puzzles | — | 21% |
| LMCA | — | 37.6% |
| Epoch Capabilities Index | — | 148.54 |
| ForecastBench | 61 | — |
Math Too close to call
Grok 4.1 Fast: 31.9 (#221), Inkling: 31.3 (#225)
| Benchmark | Grok 4.1 Fast | Inkling |
|---|---|---|
| ProofBench | 4% | 0% |
| LMArena Math | 1408 | 1479 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath Tier 4 | — | 4.9% |
| MathArena Final-Answer Competitions | 60.9% | — |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
Knowledge Inkling leads
Grok 4.1 Fast: 33.1 (#207), Inkling: 55.1 (#49)
| Benchmark | Grok 4.1 Fast | Inkling |
|---|---|---|
| LMArena Expert | 1399 | 1465 |
| GPQA Diamond | — | 88.3% |
| SimpleQA Verified | — | 40.3% |
| Vectara Hallucination Rate | 17.8% | — |
Multimodal Not comparable
Grok 4.1 Fast: 37.0 (#76), Inkling: —
| Benchmark | Grok 4.1 Fast | Inkling |
|---|---|---|
| LMArena Vision | 1201 | — |
Multilingual Inkling leads
Grok 4.1 Fast: 51.0 (#114), Inkling: 54.0 (#52)
| Benchmark | Grok 4.1 Fast | Inkling |
|---|---|---|
| LMArena Non-English | 1391 | 1434 |
| LMArena Chinese | 1441 | 1490 |
| LMArena French | 1415 | 1458 |
| LMArena German | 1404 | 1446 |
| LMArena Japanese | 1349 | 1429 |
| LMArena Korean | 1361 | 1404 |
| LMArena Russian | 1387 | 1429 |
| LMArena Spanish | 1413 | 1448 |
Instruction Following Inkling leads
Grok 4.1 Fast: 72.7 (#133), Inkling: 75.1 (#71)
| Benchmark | Grok 4.1 Fast | Inkling |
|---|---|---|
| LMArena Instruction Following | 1376 | 1426 |
Long Context Inkling leads
Grok 4.1 Fast: 42.4 (#126), Inkling: 43.8 (#86)
| Benchmark | Grok 4.1 Fast | Inkling |
|---|---|---|
| LMArena Longer Query | 1390 | 1434 |
Writing & Preference Inkling leads
Grok 4.1 Fast: 57.2 (#131), Inkling: 65.2 (#51)
| Benchmark | Grok 4.1 Fast | Inkling |
|---|---|---|
| LMArena Text | 1408 | 1441 |
| LMArena Creative Writing | 1394 | 1387 |
| EQ-Bench Creative Writing | 1327 | 1611 |
| LMArena Multi-Turn | 1389 | 1436 |
| EQ-Bench 4 | — | 1226 |
Frequently asked questions
Is Grok 4.1 Fast better than Inkling?
Inkling is the stronger model overall, scoring 44.1 to 41.4 on the Noometry Index. Grok 4.1 Fast costs 9.4× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Which is cheaper, Grok 4.1 Fast or Inkling?
Grok 4.1 Fast is cheaper. It lists at $0.20 per million input tokens and $0.50 per million output tokens; Inkling lists at $1.87 and $4.68.
Is Grok 4.1 Fast or Inkling better for coding?
They score almost the same on coding (34.1 vs 34.5); test both on your own repository before choosing.
Which has the bigger context window?
Grok 4.1 Fast does, with 128K tokens against 66K.
How many benchmarks do Grok 4.1 Fast and Inkling share?
24 benchmarks have published results for both models. Grok 4.1 Fast has 32 scored results on Noometry and Inkling has 41.