Grok 4.5 vs Inkling Small
Grok 4.5 leads Inkling Small on coding, 58.6 to 27.3 on the Vibe Coding Index, and Inkling Small costs 5.0x less per output token ($1.20 vs $6.00 per million). Updated October 22, 2026; 80 benchmarks have a result for both.
Grok 4.5 or Inkling Small: which to pick
Pick Grok 4.5 for coding: it scores 58.6 on the Vibe Coding Index against 27.3 for Inkling Small.
Pick Inkling Small for output tokens 5.0x cheaper ($1.20 vs $6.00 per million) and a lower cost per solved task ($0.16 against $0.62).
- Shared results
- 80
- Grok 4.5 only
- 43
- Inkling Small only
- 4
- Like-for-like categories
- 7 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
Grok 4.5
Grok 4.5 scores 58.6 against 27.3.
6 and 4 benchmarks behind the scores
Intelligence
AA Intelligence Index
Grok 4.5
Grok 4.5 leads, 38.8 against 25.7.
Same board, both measured
Agentic work
AA Agentic Index
Grok 4.5
Grok 4.5 leads, 41.2 against 23.5.
Same board, both measured
Reasoning
GPQA Diamond
Grok 4.5
Grok 4.5 leads, 92.9% against 83.6%.
Same board, both measured
Knowledge
MMLU Pro
Grok 4.5
Grok 4.5 leads, 89.2% against 85.6%.
Same board, both measured
Web design
Design Arena: websites
No call
Only Grok 4.5 has a Design Arena: websites result, 1281.
Directional only
General
Vals Index
No call
Only Inkling Small has a Vals Index result, 27.6%.
Directional only
Long documents
Listed context window
Inkling Small
Inkling Small takes 524K tokens against 500K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Inkling Small
Grok 4.5 $0.0050, Inkling Small $0.0010 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Inkling Small
Grok 4.5 $0.62, Inkling Small $0.16.
Published attempt cost and pass rate
At a glance
- Coding index
- Grok 4.5 58.6 from 6 benchmarks, Inkling Small 27.3 from 4 benchmarks.
- Widest category
- Coding, 17.0 points apart on average over 18 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): Grok 4.5 69.0% against Inkling Small 19.1%, 50.0 points apart on a 0 to 100 scale.
- Output price
- Grok 4.5 $6.00 against Inkling Small $1.20 per million output tokens, 5.0x apart.
- Context window
- Grok 4.5 takes 500K tokens, Inkling Small 524K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Grok 4.5 | Bars | Inkling Small | Ties |
|---|---|---|---|---|
| Coding | 17 | 1 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 5 | 0 | ||
| Reasoning | 11 | 0 | ||
| Math | 6 | 0 | ||
| Knowledge | 8 | 3 | ||
| General | 27 | 0 | ||
| All shared boards | 76 | 4 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index171
| Benchmark | Grok 4.5 | Inkling Small | Leader |
|---|---|---|---|
| LiveBench coding | 94.3% | Not measured | Only Grok 4.5 measured |
| LMArena WebDev | 1553 | 1409 | Grok 4.5 |
| AA Coding Index | 72.4 | 52.9 | Grok 4.5 |
| LiveCodeBench (Vals AI) | 87.3% | 85.9% | Grok 4.5 |
| SWE-bench Verified (Vals AI) | 86.6% | 82.2% | Grok 4.5 |
| Terminal-Bench 4 (Vals AI) | 8.6% | 0.0% | Grok 4.5 |
| Vibe Code Bench (Vals AI) | 69.0% | 19.1% | Grok 4.5 |
| Code migration (Vals AI) | 36.6% | 13.7% | Grok 4.5 |
| ProgramBench (Vals AI) | 0.0% | 0.5% | Inkling Small |
| IOI (Vals AI) | 40.6% | 9.3% | Grok 4.5 |
| Terminal-Bench 2.1 (Vals AI) | 67.8% | 55.1% | Grok 4.5 |
| SkillsBench (Vals AI) | 66.0% | 33.6% | Grok 4.5 |
| CyberBench (Vals AI) | 71.0% | 64.1% | Grok 4.5 |
| SciCode | 55.0% | 49.7% | Grok 4.5 |
| FrontierCode | 42.4% | Not measured | Only Grok 4.5 measured |
| WeirdML | 46.4% | Not measured | Only Grok 4.5 measured |
| ALE-Bench | 1309.3 | Not measured | Only Grok 4.5 measured |
| LMArena Text: coding | 1474 | 1450 | Grok 4.5 |
| LMArena Text: software and IT | 1471 | 1447 | Grok 4.5 |
| LMArena WebDev: React | 1556 | 1399 | Grok 4.5 |
| LMArena WebDev: HTML | 1567 | 1398 | Grok 4.5 |
| LMArena WebDev: from an image | 1562 | 1410 | Grok 4.5 |
| SciCode | 6.5% | Not measured | Only Grok 4.5 measured |
| Neither model has a result on the other 16 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Grok 4.5 | Inkling Small | Leader |
|---|---|---|---|
| AA Intelligence Index | 38.8 | 25.7 | Grok 4.5 |
| Epoch Capabilities Index | 154.1 | 150.3 | Grok 4.5 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Grok 4.5 | Inkling Small | Leader |
|---|---|---|---|
| AA Agentic Index | 41.2 | 23.5 | Grok 4.5 |
| Design Arena: agents building web apps | 1218 | Not measured | Only Grok 4.5 measured |
| Design Arena: agents building full-stack apps | 1249 | Not measured | Only Grok 4.5 measured |
| Design Arena: agents building mobile apps | 1220 | Not measured | Only Grok 4.5 measured |
| Design Arena: agents building Android apps | 1236 | Not measured | Only Grok 4.5 measured |
| Design Arena: agents building Godot games | 1229 | Not measured | Only Grok 4.5 measured |
| Design Arena: agents building games | 1236 | Not measured | Only Grok 4.5 measured |
| Design Arena: HTML slides | 1205 | Not measured | Only Grok 4.5 measured |
| Design Arena: PowerPoint slides | 1230 | Not measured | Only Grok 4.5 measured |
| LiveBench research | 85.9% | Not measured | Only Grok 4.5 measured |
| LiveBench browser | 44.0% | Not measured | Only Grok 4.5 measured |
| LiveBench long agentic | 27.9% | Not measured | Only Grok 4.5 measured |
| SREBench (Vals AI) | 0.8% | Not measured | Only Grok 4.5 measured |
| Finance Agent (Vals AI) | 48.4% | 41.3% | Grok 4.5 |
| Tax Agent Bench (Vals AI) | 24.9% | 15.4% | Grok 4.5 |
| Legal Research Bench (Vals AI) | 38.0% | 25.5% | Grok 4.5 |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 2.9% | Only Inkling Small measured |
| Excel Modeling Benchmark (Vals AI) | 52.9% | 31.8% | Grok 4.5 |
| Time Horizon Index (Vals AI) | 6.3% | Not measured | Only Grok 4.5 measured |
| APEX-Agents | 56.2% | Not measured | Only Grok 4.5 measured |
| PostTrainBench | 23.4% | Not measured | Only Grok 4.5 measured |
| Vending-Bench 2 | $3,887 | Not measured | Only Grok 4.5 measured |
| LMArena Search | 1216 | Not measured | Only Grok 4.5 measured |
| Neither model has a result on the other 18 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index110
| Benchmark | Grok 4.5 | Inkling Small | Leader |
|---|---|---|---|
| GPQA Diamond | 92.9% | 83.6% | Grok 4.5 |
| LiveBench reasoning | 87.2% | Not measured | Only Grok 4.5 measured |
| MMMU Pro (Vals AI) | 61.8% | Not measured | Only Grok 4.5 measured |
| GPQA Diamond (Artificial Analysis run) | 93.1% | 89.5% | Grok 4.5 |
| Humanity's Last Exam (Artificial Analysis run) | 42.7% | 33.3% | Grok 4.5 |
| GPQA Diamond (Epoch AI run) | 93.4% | 88.5% | Grok 4.5 |
| ARC-AGI | 87.2% | 84.0% | Grok 4.5 |
| ARC-AGI-2 | 52.6% | 40.1% | Grok 4.5 |
| SimpleBench | 70.0% | Not measured | Only Grok 4.5 measured |
| Chess puzzles | 35.0% | Not measured | Only Grok 4.5 measured |
| Mystery game puzzles | Not measured | 6.0% | Only Inkling Small measured |
| LMArena Text: hard prompts | 1462 | 1423 | Grok 4.5 |
| LMArena Text: expert | 1465 | 1441 | Grok 4.5 |
| LMArena Text: hard prompts in English | 1464 | 1429 | Grok 4.5 |
| LMArena Vision: diagrams | 1304 | 1251 | Grok 4.5 |
| LMArena Vision: homework | 1295 | 1257 | Grok 4.5 |
| Kagi LLM Benchmark | 83.5% | Not measured | Only Grok 4.5 measured |
| Neither model has a result on the other 5 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Grok 4.5 | Inkling Small | Leader |
|---|---|---|---|
| OTIS Mock AIME | 97.8% | 90.0% | Grok 4.5 |
| FrontierMath, tiers 1 to 3 | 57.2% | 46.3% | Grok 4.5 |
| FrontierMath, tier 4 | 24.4% | 17.1% | Grok 4.5 |
| ProofBench | 31.0% | 6.0% | Grok 4.5 |
| LMArena Text: math | 1460 | 1459 | Grok 4.5 |
| LMArena Text: mathematical work | 1482 | 1441 | Grok 4.5 |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index83
| Benchmark | Grok 4.5 | Inkling Small | Leader |
|---|---|---|---|
| MMLU Pro | 89.2% | 85.6% | Grok 4.5 |
| LegalBench (Vals AI) | 86.0% | 83.0% | Grok 4.5 |
| CorpFin (Vals AI) | 67.4% | 69.6% | Inkling Small |
| TaxEval (Vals AI) | 71.7% | 75.5% | Inkling Small |
| MortgageTax (Vals AI) | 61.8% | 62.3% | Inkling Small |
| MedCode (Vals AI) | 43.3% | 37.9% | Grok 4.5 |
| SimpleQA Verified | 48.3% | 19.1% | Grok 4.5 |
| LMArena Text: science | 1464 | 1428 | Grok 4.5 |
| LMArena Text: medicine and healthcare | 1440 | 1413 | Grok 4.5 |
| LMArena Text: legal and government | 1463 | 1415 | Grok 4.5 |
| LMArena Text: business and finance | 1441 | 1413 | Grok 4.5 |
| FACTS Benchmark Suite | 50.2% | Not measured | Only Grok 4.5 measured |
| Neither model has a result on the other 6 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | Grok 4.5 | Inkling Small | Leader |
|---|---|---|---|
| Design Arena: websites | 1281 | Not measured | Only Grok 4.5 measured |
| Design Arena: UI components | 1280 | Not measured | Only Grok 4.5 measured |
| Design Arena: game dev | 1264 | Not measured | Only Grok 4.5 measured |
| Design Arena: data viz | 1266 | Not measured | Only Grok 4.5 measured |
| Design Arena: 3D | 1257 | Not measured | Only Grok 4.5 measured |
| Design Arena: all code categories | 1275 | Not measured | Only Grok 4.5 measured |
| Design Arena: SVG | 1215 | Not measured | Only Grok 4.5 measured |
| Design Arena: ASCII art | 1256 | Not measured | Only Grok 4.5 measured |
| LiveBench design | 78.1% | Not measured | Only Grok 4.5 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index270
| Benchmark | Grok 4.5 | Inkling Small | Leader |
|---|---|---|---|
| Vals Index | Not measured | 27.6% | Only Inkling Small measured |
| LiveBench data analysis | 73.0% | Not measured | Only Grok 4.5 measured |
| Public Benefits Bench (Vals AI) | Not measured | 59.4% | Only Inkling Small measured |
| SAGE (Vals AI) | 35.0% | 32.7% | Grok 4.5 |
| MedScribe (Vals AI) | 86.9% | 84.1% | Grok 4.5 |
| Vals Multimodal Index | 63.4% | 50.0% | Grok 4.5 |
| Long context reasoning (AA-LCR) | 79.3% | 75.7% | Grok 4.5 |
| DTBench | 96.5% | Not measured | Only Grok 4.5 measured |
| LMCA | 45.2% | Not measured | Only Grok 4.5 measured |
| Surface Evolver Bench | 74.4% | Not measured | Only Grok 4.5 measured |
| Furniture assembly | 22.5% | Not measured | Only Grok 4.5 measured |
| LMArena Text | 1448 | 1413 | Grok 4.5 |
| LMArena Text: instruction following | 1445 | 1399 | Grok 4.5 |
| LMArena Text: creative writing | 1442 | 1334 | Grok 4.5 |
| LMArena Vision | 1287 | 1237 | Grok 4.5 |
| LMArena Text: English | 1453 | 1421 | Grok 4.5 |
| LMArena Text: non-English | 1440 | 1401 | Grok 4.5 |
| LMArena Text: Chinese | 1495 | 1464 | Grok 4.5 |
| LMArena Text: German | 1448 | 1408 | Grok 4.5 |
| LMArena Text: Japanese | 1430 | 1401 | Grok 4.5 |
| LMArena Text: Korean | 1406 | 1367 | Grok 4.5 |
| LMArena Text: French | 1457 | 1435 | Grok 4.5 |
| LMArena Text: Spanish | 1451 | 1422 | Grok 4.5 |
| LMArena Text: Russian | 1449 | 1394 | Grok 4.5 |
| LMArena Text: Polish | 1432 | 1428 | Grok 4.5 |
| LMArena Text: multi-turn | 1456 | 1416 | Grok 4.5 |
| LMArena Text: longer queries | 1462 | 1402 | Grok 4.5 |
| LMArena Text: writing and language | 1445 | 1357 | Grok 4.5 |
| LMArena Text: entertainment and media | 1434 | 1352 | Grok 4.5 |
| LMArena Vision: English | 1285 | 1243 | Grok 4.5 |
| LMArena Vision: Chinese | 1345 | 1292 | Grok 4.5 |
| LMArena Vision: reading text | 1293 | 1243 | Grok 4.5 |
| LMArena Vision: humor | 1276 | 1207 | Grok 4.5 |
| LMArena Vision: creative writing | 1293 | 1205 | Grok 4.5 |
| LMArena Document | 1452 | Not measured | Only Grok 4.5 measured |
| Neither model has a result on the other 11 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Grok 4.5 | Inkling Small | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Inkling Small costs less
Repository review
50K input + 3K output tokens
Inkling Small costs less
Agent loop
200K input + 10K output tokens
Inkling Small costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | SpaceXAI Grok 4.5 | Thinking Machines Inkling Small |
|---|---|---|
| Maker | xAI | Thinking Machines |
| Weights | No public weights listed | Open weights |
| Released | July 8, 2026 | July 30, 2026 |
| Context window | 500K | 524K |
| Input $/Mtok | $2.00 | $0.45 |
| Output $/Mtok | $6.00 | $1.20 |
| Coding index | 58.6 | 27.3 |
| Independent measurements behind it | 6 | 4 |
| Cost per solved task | $0.62 | $0.16 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Grok 4.5 better than Inkling Small for coding?
Pick Grok 4.5 for coding: it scores 58.6 on the Vibe Coding Index against 27.3 for Inkling Small. Pick Inkling Small for output tokens 5.0x cheaper ($1.20 vs $6.00 per million) and a lower cost per solved task ($0.16 against $0.62).
Which is cheaper, Grok 4.5 or Inkling Small?
Grok 4.5 costs $2.00 per million input tokens and $6.00 per million output tokens; Inkling Small costs $0.45 and $1.20. Per solved SWE-bench Verified task, Grok 4.5 costs $0.62 and Inkling Small $0.16.
Which has the bigger context window, Grok 4.5 or Inkling Small?
Inkling Small, with 524K tokens against 500K.
How many benchmarks is the Grok 4.5 vs Inkling Small comparison based on?
80 benchmarks have a result for both models as of October 22, 2026. Grok 4.5's coding index rests on 6 independent benchmarks and Inkling Small's on 4. Where only one model has a result, the page says so instead of naming a winner.