Model comparison
Grok 4.5 vs Inkling-Small
Grok 4.5 is the stronger model overall, scoring 55.0 to 46.5 on the Noometry Index. Inkling-Small costs 4.7× less per token, which makes it the better buy when Grok 4.5's lead doesn't matter for your workload.
Last verified . 32 shared benchmarks.
Summary
- They share 32 benchmarks with published results for both. Grok 4.5 scores higher in 8 categories and Inkling-Small in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.5 leads 56.1 to 38.6.
- The biggest single-benchmark swing is SimpleQA Verified: 48.3% for Grok 4.5 and 19.1% for Inkling-Small.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $2 / $6 for Grok 4.5.
- Inkling-Small accepts more context: 524K tokens versus 500K.
- Inkling-Small has downloadable open weights; the other is API-only.
Side by side
| Grok 4.5 | Inkling-Small | |
|---|---|---|
| Provider | xAI | Thinking Machines Lab |
| Noometry Index | 55.0 | 46.5 |
| Released | 2026-07-08 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 500K | 524K |
| Max output | 500K | 1.05M |
| Input $ / M tokens | $2 | $0.45 |
| Output $ / M tokens | $6 | $1.20 |
| Results tracked | 52 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.5 leads
Grok 4.5: 52.2 (#35), Inkling-Small: 43.6 (#85)
| Benchmark | Grok 4.5 | Inkling-Small |
|---|---|---|
| LMArena WebDev | 1553 | 1409 |
| SciCode | 54.1% | 48.7% |
| LMArena Coding | 1474 | 1451 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.4% | — |
| WeirdML | 46.4% | — |
| ALE-Bench | 1,309 | — |
Agentic & Tool Use Not comparable
Grok 4.5: 44.4 (#17), Inkling-Small: —
| Benchmark | Grok 4.5 | Inkling-Small |
|---|---|---|
| APEX-Agents | 56.2% | — |
| τ²-bench Banking | 47.9% | — |
| PostTrainBench | 23.4% | — |
| GBAEval | 65.4% | — |
| GDP.pdf | 14% | — |
| LMArena Search | 1213 | — |
| Vending-Bench 2 | 3,887 | — |
Reasoning Grok 4.5 leads
Grok 4.5: 56.1 (#25), Inkling-Small: 38.6 (#63)
| Benchmark | Grok 4.5 | Inkling-Small |
|---|---|---|
| ARC-AGI-2 | 52.6% | 40.1% |
| ARC-AGI-1 | 87.2% | 84% |
| CritPt | 15.4% | 8.3% |
| Chess Puzzles | 36% | 18% |
| LMArena Hard Prompts | 1462 | 1423 |
| Epoch Capabilities Index | 153.92 | 150.15 |
| SimpleBench | 70% | — |
| Kagi LLM Benchmark | 83.5% | — |
| NYT Connections (extended) | 79.9% | — |
| Mystery Game Puzzles | — | 6% |
| DTBench | 96.5% | — |
| LMCA | 45.2% | — |
| Surface Evolver Bench | 74.4% | — |
Math Grok 4.5 leads
Grok 4.5: 60.9 (#35), Inkling-Small: 45.1 (#77)
| Benchmark | Grok 4.5 | Inkling-Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | 57.2% | 46.3% |
| FrontierMath Tier 4 | 24.4% | 17.1% |
| OTIS Mock AIME 2024-2025 | 97.8% | 90% |
| ProofBench | 31% | 6% |
| LMArena Math | 1459 | 1459 |
Knowledge Grok 4.5 leads
Grok 4.5: 62.3 (#24), Inkling-Small: 48.2 (#77)
| Benchmark | Grok 4.5 | Inkling-Small |
|---|---|---|
| GPQA Diamond | 93.4% | 88.5% |
| SimpleQA Verified | 48.3% | 19.1% |
| LMArena Expert | 1466 | 1442 |
Multimodal Inkling-Small leads
Grok 4.5: 37.6 (#72), Inkling-Small: 39.1 (#62)
| Benchmark | Grok 4.5 | Inkling-Small |
|---|---|---|
| LMArena Vision | 1288 | 1235 |
| Blueprint-Bench 2 | 27.3% | — |
| Furniture Assembly | 22.5% | — |
| LMArena Document | 1452 | — |
Multilingual Grok 4.5 leads
Grok 4.5: 54.4 (#42), Inkling-Small: 51.7 (#104)
| Benchmark | Grok 4.5 | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1440 | 1402 |
| LMArena Chinese | 1496 | 1465 |
| LMArena French | 1456 | 1436 |
| LMArena German | 1446 | 1405 |
| LMArena Japanese | 1428 | 1405 |
| LMArena Korean | 1404 | 1363 |
| LMArena Russian | 1448 | 1391 |
| LMArena Spanish | 1450 | 1428 |
Instruction Following Grok 4.5 leads
Grok 4.5: 76.0 (#48), Inkling-Small: 73.8 (#114)
| Benchmark | Grok 4.5 | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1446 | 1399 |
Long Context Grok 4.5 leads
Grok 4.5: 44.8 (#56), Inkling-Small: 42.7 (#118)
| Benchmark | Grok 4.5 | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1463 | 1401 |
Writing & Preference Grok 4.5 leads
Grok 4.5: 65.8 (#42), Inkling-Small: 59.6 (#107)
| Benchmark | Grok 4.5 | Inkling-Small |
|---|---|---|
| LMArena Text | 1448 | 1414 |
| LMArena Creative Writing | 1442 | 1331 |
| EQ-Bench Creative Writing | 1579 | 1491 |
| LMArena Multi-Turn | 1456 | 1418 |
Frequently asked questions
Is Grok 4.5 better than Inkling-Small?
Grok 4.5 is the stronger model overall, scoring 55.0 to 46.5 on the Noometry Index. Inkling-Small costs 4.7× less per token, which makes it the better buy when Grok 4.5's lead doesn't matter for your workload.
Which is cheaper, Grok 4.5 or Inkling-Small?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Grok 4.5 lists at $2 and $6.
Is Grok 4.5 or Inkling-Small better for coding?
Grok 4.5 scores higher on coding benchmarks: 52.2 versus 43.6 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 500K.
How many benchmarks do Grok 4.5 and Inkling-Small share?
32 benchmarks have published results for both models. Grok 4.5 has 52 scored results on Noometry and Inkling-Small has 33.