Model comparison
Grok 4.20 (Non-Reasoning) vs Inkling-Small
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 46.5 on the Noometry Index. Inkling-Small costs 2.5× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.
Last verified . 30 shared benchmarks.
Summary
- They share 30 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 7 categories and Inkling-Small in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 38.6.
- The biggest single-benchmark swing is ARC-AGI-2: 65.1% for Grok 4.20 (Non-Reasoning) and 40.1% for Inkling-Small.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
- Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 524K.
- Inkling-Small has downloadable open weights; the other is API-only.
Side by side
| Grok 4.20 (Non-Reasoning) | Inkling-Small | |
|---|---|---|
| Provider | xAI | Thinking Machines Lab |
| Noometry Index | 48.6 | 46.5 |
| Released | 2026-02-17 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 1M | 524K |
| Max output | 30K | 1.05M |
| Input $ / M tokens | $1.25 | $0.45 |
| Output $ / M tokens | $2.50 | $1.20 |
| Results tracked | 46 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Grok 4.20 (Non-Reasoning): 42.1 (#112), Inkling-Small: 43.6 (#85)
| Benchmark | Grok 4.20 (Non-Reasoning) | Inkling-Small |
|---|---|---|
| LMArena WebDev | 1375 | 1409 |
| LMArena Coding | 1459 | 1451 |
| SciCode | — | 48.7% |
| WeirdML | 52.3% | — |
| ALE-Bench | 1,150 | — |
Agentic & Tool Use Not comparable
Grok 4.20 (Non-Reasoning): 34.4 (#46), Inkling-Small: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Inkling-Small |
|---|---|---|
| Terminal-Bench | 57.3% | — |
| τ²-bench Banking | 18% | — |
| LMArena Search | 1189 | — |
| Vending-Bench 2 | 4,663 | — |
Reasoning Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.3 (#32), Inkling-Small: 38.6 (#63)
| Benchmark | Grok 4.20 (Non-Reasoning) | Inkling-Small |
|---|---|---|
| ARC-AGI-2 | 65.1% | 40.1% |
| ARC-AGI-1 | 89.5% | 84% |
| Chess Puzzles | 24% | 18% |
| LMArena Hard Prompts | 1451 | 1423 |
| Epoch Capabilities Index | 151.98 | 150.15 |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 85.4% | — |
| CritPt | — | 8.3% |
| Thematic Generalization | 63.8% | — |
| Mystery Game Puzzles | — | 6% |
| DTBench | 90.1% | — |
| LMCA | 38.7% | — |
| ForecastBench | 61.4 | — |
Math Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 48.2 (#65), Inkling-Small: 45.1 (#77)
| Benchmark | Grok 4.20 (Non-Reasoning) | Inkling-Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | 44.9% | 46.3% |
| FrontierMath Tier 4 | 17.1% | 17.1% |
| OTIS Mock AIME 2024-2025 | 92.2% | 90% |
| ProofBench | 14% | 6% |
| LMArena Math | 1455 | 1459 |
Knowledge Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.8 (#60), Inkling-Small: 48.2 (#77)
| Benchmark | Grok 4.20 (Non-Reasoning) | Inkling-Small |
|---|---|---|
| GPQA Diamond | 89.3% | 88.5% |
| SimpleQA Verified | 30.2% | 19.1% |
| LMArena Expert | 1439 | 1442 |
Multimodal Inkling-Small leads
Grok 4.20 (Non-Reasoning): 33.3 (#98), Inkling-Small: 39.1 (#62)
| Benchmark | Grok 4.20 (Non-Reasoning) | Inkling-Small |
|---|---|---|
| LMArena Vision | 1263 | 1235 |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1416 | — |
Multilingual Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 54.5 (#40), Inkling-Small: 51.7 (#104)
| Benchmark | Grok 4.20 (Non-Reasoning) | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1441 | 1402 |
| LMArena Chinese | 1481 | 1465 |
| LMArena French | 1476 | 1436 |
| LMArena German | 1465 | 1405 |
| LMArena Japanese | 1449 | 1405 |
| LMArena Korean | 1417 | 1363 |
| LMArena Russian | 1458 | 1391 |
| LMArena Spanish | 1443 | 1428 |
Instruction Following Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 74.8 (#83), Inkling-Small: 73.8 (#114)
| Benchmark | Grok 4.20 (Non-Reasoning) | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1420 | 1399 |
Long Context Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 45.5 (#34), Inkling-Small: 42.7 (#118)
| Benchmark | Grok 4.20 (Non-Reasoning) | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1437 | 1401 |
| CL-bench | 22.2% | — |
| CL-bench Life | 11.9% | — |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 65.7 (#44), Inkling-Small: 59.6 (#107)
| Benchmark | Grok 4.20 (Non-Reasoning) | Inkling-Small |
|---|---|---|
| LMArena Text | 1451 | 1414 |
| LMArena Creative Writing | 1438 | 1331 |
| EQ-Bench Creative Writing | 1574 | 1491 |
| LMArena Multi-Turn | 1456 | 1418 |
Frequently asked questions
Is Grok 4.20 (Non-Reasoning) better than Inkling-Small?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 46.5 on the Noometry Index. Inkling-Small costs 2.5× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.
Which is cheaper, Grok 4.20 (Non-Reasoning) or Inkling-Small?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.
Is Grok 4.20 (Non-Reasoning) or Inkling-Small better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 42.1 in the Noometry coding category.
Which has the bigger context window?
Grok 4.20 (Non-Reasoning) does, with 1M tokens against 524K.
How many benchmarks do Grok 4.20 (Non-Reasoning) and Inkling-Small share?
30 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Inkling-Small has 33.