Model comparison
Grok 4.3 vs Inkling-Small
Inkling-Small is the stronger model overall, scoring 46.5 to 43.8 on the Noometry Index.
Last verified . 29 shared benchmarks.
Summary
- They share 29 benchmarks with published results for both. Grok 4.3 scores higher in 2 categories and Inkling-Small in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where Inkling-Small leads 39.1 to 31.6.
- The biggest single-benchmark swing is SimpleQA Verified: 33.2% for Grok 4.3 and 19.1% for Inkling-Small.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $1.25 / $2.50 for Grok 4.3.
- Grok 4.3 accepts more context: 1M tokens versus 524K.
- Inkling-Small has downloadable open weights; the other is API-only.
Side by side
| Grok 4.3 | Inkling-Small | |
|---|---|---|
| Provider | xAI | Thinking Machines Lab |
| Noometry Index | 43.8 | 46.5 |
| Released | 2026-04-17 | 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 | 40 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Grok 4.3: 41.6 (#121), Inkling-Small: 43.6 (#85)
| Benchmark | Grok 4.3 | Inkling-Small |
|---|---|---|
| LMArena WebDev | 1357 | 1409 |
| SciCode | 47.3% | 48.7% |
| LMArena Coding | 1415 | 1451 |
| WeirdML | 49.9% | — |
| ALE-Bench | 944.17 | — |
Agentic & Tool Use Not comparable
Grok 4.3: 27.7 (#99), Inkling-Small: —
| Benchmark | Grok 4.3 | Inkling-Small |
|---|---|---|
| GDP.pdf | 8% | — |
| LMArena Search | 1165 | — |
| Vending-Bench 2 | 35.26 | — |
Reasoning Inkling-Small leads
Grok 4.3: 35.9 (#68), Inkling-Small: 38.6 (#63)
| Benchmark | Grok 4.3 | Inkling-Small |
|---|---|---|
| CritPt | 8% | 8.3% |
| Chess Puzzles | 25% | 18% |
| LMArena Hard Prompts | 1396 | 1423 |
| Epoch Capabilities Index | 149.16 | 150.15 |
| ARC-AGI-2 | — | 40.1% |
| NYT Connections (extended) | 55.2% | — |
| ARC-AGI-1 | — | 84% |
| Mystery Game Puzzles | — | 6% |
| DTBench | 90.7% | — |
| LMCA | 38.3% | — |
| ForecastBench | 60.3 | — |
Math Too close to call
Grok 4.3: 46.0 (#74), Inkling-Small: 45.1 (#77)
| Benchmark | Grok 4.3 | Inkling-Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | 42.8% | 46.3% |
| FrontierMath Tier 4 | 14.6% | 17.1% |
| OTIS Mock AIME 2024-2025 | 93.3% | 90% |
| ProofBench | 11% | 6% |
| LMArena Math | 1388 | 1459 |
Knowledge Grok 4.3 leads
Grok 4.3: 52.5 (#62), Inkling-Small: 48.2 (#77)
| Benchmark | Grok 4.3 | Inkling-Small |
|---|---|---|
| GPQA Diamond | 88.8% | 88.5% |
| SimpleQA Verified | 33.2% | 19.1% |
| LMArena Expert | 1385 | 1442 |
Multimodal Inkling-Small leads
Grok 4.3: 31.6 (#104), Inkling-Small: 39.1 (#62)
| Benchmark | Grok 4.3 | Inkling-Small |
|---|---|---|
| LMArena Vision | 1229 | 1235 |
| Blueprint-Bench 2 | 0% | — |
Multilingual Inkling-Small leads
Grok 4.3: 50.5 (#120), Inkling-Small: 51.7 (#104)
| Benchmark | Grok 4.3 | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1385 | 1402 |
| LMArena Chinese | 1422 | 1465 |
| LMArena French | 1412 | 1436 |
| LMArena German | 1395 | 1405 |
| LMArena Japanese | 1379 | 1405 |
| LMArena Korean | 1356 | 1363 |
| LMArena Russian | 1399 | 1391 |
| LMArena Spanish | 1398 | 1428 |
Instruction Following Inkling-Small leads
Grok 4.3: 72.1 (#140), Inkling-Small: 73.8 (#114)
| Benchmark | Grok 4.3 | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1366 | 1399 |
Long Context Too close to call
Grok 4.3: 42.5 (#123), Inkling-Small: 42.7 (#118)
| Benchmark | Grok 4.3 | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1393 | 1401 |
Writing & Preference Inkling-Small leads
Grok 4.3: 58.5 (#118), Inkling-Small: 59.6 (#107)
| Benchmark | Grok 4.3 | Inkling-Small |
|---|---|---|
| LMArena Text | 1397 | 1414 |
| LMArena Creative Writing | 1380 | 1331 |
| LMArena Multi-Turn | 1406 | 1418 |
| EQ-Bench Creative Writing | — | 1491 |
| EQ-Bench 4 | 1075 | — |
Frequently asked questions
Is Grok 4.3 better than Inkling-Small?
Inkling-Small is the stronger model overall, scoring 46.5 to 43.8 on the Noometry Index.
Which is cheaper, Grok 4.3 or Inkling-Small?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Grok 4.3 lists at $1.25 and $2.50.
Is Grok 4.3 or Inkling-Small better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 41.6 in the Noometry coding category.
Which has the bigger context window?
Grok 4.3 does, with 1M tokens against 524K.
How many benchmarks do Grok 4.3 and Inkling-Small share?
29 benchmarks have published results for both models. Grok 4.3 has 40 scored results on Noometry and Inkling-Small has 33.