Model comparison
Grok 4.1 Fast vs Inkling-Small
Inkling-Small is the stronger model overall, scoring 46.5 to 40.9 on the Noometry Index. Grok 4.1 Fast costs 2.3× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
Summary
- They share 21 benchmarks with published results for both. Grok 4.1 Fast scores higher in 1 category and Inkling-Small in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling-Small leads 48.3 to 32.6.
- Grok 4.1 Fast is cheaper at $0.20 / $0.50 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- Inkling-Small accepts more context: 524K tokens versus 128K.
- Inkling-Small has downloadable open weights; the other is API-only.
Side by side
| Grok 4.1 Fast | Inkling-Small | |
|---|---|---|
| Provider | xAI | Thinking Machines Lab |
| Noometry Index | 40.9 | 46.5 |
| Released | 2025-06-27 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 128K | 524K |
| Max output | 30K | 1.05M |
| Input $ / M tokens | $0.20 | $0.45 |
| Output $ / M tokens | $0.50 | $1.20 |
| Results tracked | 32 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Grok 4.1 Fast: 33.8 (#236), Inkling-Small: 43.3 (#80)
| Benchmark | Grok 4.1 Fast | Inkling-Small |
|---|---|---|
| LMArena WebDev | 1241 | 1408 |
| LMArena Coding | 1411 | 1451 |
| SciCode | — | 48.7% |
| ALE-Bench | 394.93 | — |
Agentic & Tool Use Not comparable
Grok 4.1 Fast: 36.1 (#35), Inkling-Small: —
| Benchmark | Grok 4.1 Fast | Inkling-Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | 69.6% | — |
| τ²-bench Banking | 13.1% | — |
| LMArena Search | 1171 | — |
| Vending-Bench 2 | 1,107 | — |
Reasoning Grok 4.1 Fast leads
Grok 4.1 Fast: 42.3 (#45), Inkling-Small: 39.0 (#53)
| Benchmark | Grok 4.1 Fast | Inkling-Small |
|---|---|---|
| LMArena Hard Prompts | 1407 | 1424 |
| ARC-AGI-2 | — | 40.1% |
| SimpleBench | 56% | — |
| NYT Connections (extended) | 87.4% | — |
| ARC-AGI-1 | — | 84% |
| CritPt | — | 8.3% |
| Chess Puzzles | — | 18% |
| Mystery Game Puzzles | — | 6% |
| DTBench | 87.7% | — |
| Epoch Capabilities Index | — | 150.13 |
| ForecastBench | 61 | — |
Math Inkling-Small leads
Grok 4.1 Fast: 30.9 (#201), Inkling-Small: 44.9 (#65)
| Benchmark | Grok 4.1 Fast | Inkling-Small |
|---|---|---|
| ProofBench | 4% | 6% |
| LMArena Math | 1408 | 1453 |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| MathArena Final-Answer Competitions | 60.9% | — |
| OTIS Mock AIME 2024-2025 | — | 90% |
Knowledge Inkling-Small leads
Grok 4.1 Fast: 32.6 (#203), Inkling-Small: 48.3 (#71)
| Benchmark | Grok 4.1 Fast | Inkling-Small |
|---|---|---|
| LMArena Expert | 1398 | 1442 |
| GPQA Diamond | — | 88.5% |
| SimpleQA Verified | — | 19.1% |
| Vectara Hallucination Rate | 17.8% | — |
Multimodal Inkling-Small leads
Grok 4.1 Fast: 36.3 (#71), Inkling-Small: 38.4 (#59)
| Benchmark | Grok 4.1 Fast | Inkling-Small |
|---|---|---|
| LMArena Vision | 1201 | 1235 |
Multilingual Too close to call
Grok 4.1 Fast: 51.1 (#110), Inkling-Small: 51.7 (#102)
| Benchmark | Grok 4.1 Fast | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1391 | 1400 |
| LMArena Chinese | 1441 | 1458 |
| LMArena French | 1416 | 1438 |
| LMArena German | 1404 | 1412 |
| LMArena Japanese | 1347 | 1399 |
| LMArena Korean | 1361 | 1355 |
| LMArena Russian | 1387 | 1392 |
| LMArena Spanish | 1411 | 1426 |
Instruction Following Inkling-Small leads
Grok 4.1 Fast: 72.8 (#127), Inkling-Small: 73.9 (#112)
| Benchmark | Grok 4.1 Fast | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1376 | 1397 |
Long Context Too close to call
Grok 4.1 Fast: 42.4 (#121), Inkling-Small: 42.7 (#113)
| Benchmark | Grok 4.1 Fast | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1390 | 1401 |
Writing & Preference Inkling-Small leads
Grok 4.1 Fast: 57.4 (#126), Inkling-Small: 59.8 (#102)
| Benchmark | Grok 4.1 Fast | Inkling-Small |
|---|---|---|
| LMArena Text | 1408 | 1413 |
| LMArena Creative Writing | 1394 | 1330 |
| EQ-Bench Creative Writing | 1327 | 1491 |
| LMArena Multi-Turn | 1389 | 1420 |
Frequently asked questions
Is Grok 4.1 Fast better than Inkling-Small?
Inkling-Small is the stronger model overall, scoring 46.5 to 40.9 on the Noometry Index. Grok 4.1 Fast costs 2.3× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Which is cheaper, Grok 4.1 Fast or Inkling-Small?
Grok 4.1 Fast is cheaper. It lists at $0.20 per million input tokens and $0.50 per million output tokens; Inkling-Small lists at $0.45 and $1.20.
Is Grok 4.1 Fast or Inkling-Small better for coding?
Inkling-Small scores higher on coding benchmarks: 43.3 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 128K.
How many benchmarks do Grok 4.1 Fast and Inkling-Small share?
21 benchmarks have published results for both models. Grok 4.1 Fast has 32 scored results on Noometry and Inkling-Small has 33.