Grok 4.7 vs Inkling 2 Mini
Grok 4.7 leads Inkling 2 Mini on coding, 64.8 to 39.5 on the Vibe Coding Index, and Inkling 2 Mini costs 18.5x less per output token ($0.325 vs $6.00 per million). Updated November 22, 2026; 28 benchmarks have a result for both.
Grok 4.7 or Inkling 2 Mini: which to pick
Pick Grok 4.7 for coding: it scores 64.8 on the Vibe Coding Index against 39.5 for Inkling 2 Mini.
Pick Inkling 2 Mini for output tokens 18.5x cheaper ($0.325 vs $6.00 per million) and a larger context window (1.05M against 500K tokens).
- Shared results
- 28
- Grok 4.7 only
- 90
- Inkling 2 Mini only
- 1
- 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 4.7
Grok 4.7 scores 64.8 against 39.5.
5 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
Grok 4.7
Grok 4.7 leads, 35.5 against 20.1.
Same board, both measured
Web design
Design Arena: websites
No call
Only Grok 4.7 has a Design Arena: websites result, 1240.
Directional only
General
Vals Index
Grok 4.7
Grok 4.7 leads, 58.6% against 46.5%.
Same board, both measured
Long documents
Listed context window
Inkling 2 Mini
Inkling 2 Mini takes 1.05M tokens against 500K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Inkling 2 Mini
Grok 4.7 $0.0050, Inkling 2 Mini $0.0002 per turn.
List prices
At a glance
- Coding index
- Grok 4.7 64.8 from 5 benchmarks, Inkling 2 Mini 39.5 from 2 benchmarks.
- Widest category
- Knowledge, 21.9 points apart on average over 2 shared benchmarks.
- Widest single gap
- IOI (Vals AI): Grok 4.7 57.7% against Inkling 2 Mini 11.6%, 46.1 points apart on a 0 to 100 scale.
- Output price
- Grok 4.7 $6.00 against Inkling 2 Mini $0.325 per million output tokens, 18.5x apart.
- Context window
- Grok 4.7 takes 500K tokens, Inkling 2 Mini 1.05M.
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 4.7 | Bars | Inkling 2 Mini | Ties |
|---|---|---|---|---|
| Coding | 6 | 1 | 1 tie | |
| Intelligence | 1 | 0 | ||
| Agentic work | 7 | 0 | ||
| Reasoning | 3 | 0 | ||
| Knowledge | 2 | 0 | ||
| Web design | 1 | 2 | ||
| General | 4 | 0 | ||
| All shared boards | 24 | 3 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index61
| Benchmark | Grok 4.7 | Inkling 2 Mini | Leader |
|---|---|---|---|
| LiveBench coding | 73.1% | Not measured | Only Grok 4.7 measured |
| LMArena WebDev | 1639 | Not measured | Only Grok 4.7 measured |
| Terminal-Bench 4 (Vals AI) | 28.8% | 6.6% | Grok 4.7 |
| Vibe Code Bench (Vals AI) | 86.2% | 77.9% | Grok 4.7 |
| Code migration (Vals AI) | 44.8% | Not measured | Only Grok 4.7 measured |
| ProgramBench (Vals AI) | 0.5% | 0.5% | Tie |
| IOI (Vals AI) | 57.7% | 11.6% | Grok 4.7 |
| Terminal-Bench 2.1 (Vals AI) | 73.4% | Not measured | Only Grok 4.7 measured |
| SWE-bench Multimodal (Vals AI) | 42.9% | 37.9% | Grok 4.7 |
| SkillsBench (Vals AI) | Not measured | 43.2% | Only Inkling 2 Mini measured |
| CyberBench (Vals AI) | 69.5% | 74.6% | Inkling 2 Mini |
| SciCode | 57.4% | Not measured | Only Grok 4.7 measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | 25.8% | 5.6% | Grok 4.7 |
| FrontierCode 2.0 | 28.7% | 15.1% | Grok 4.7 |
| FrontierCode | 47.6% | Not measured | Only Grok 4.7 measured |
| FrontierSWE | 29.5% | Not measured | Only Grok 4.7 measured |
| MirrorCode | 54.4% | Not measured | Only Grok 4.7 measured |
| ALE-Bench | 1545.8 | Not measured | Only Grok 4.7 measured |
| LMArena Text: coding | 1423 | Not measured | Only Grok 4.7 measured |
| LMArena Text: software and IT | 1420 | Not measured | Only Grok 4.7 measured |
| LMArena WebDev: React | 1662 | Not measured | Only Grok 4.7 measured |
| LMArena WebDev: HTML | 1630 | Not measured | Only Grok 4.7 measured |
| LMArena WebDev: from an image | 1592 | Not measured | Only Grok 4.7 measured |
| GameBench 2 | 72.3 | Not measured | Only Grok 4.7 measured |
| Terminal-Bench 4.0 | 37.6% | Not measured | Only Grok 4.7 measured |
| CursorBench 4.0 | 48.6% | Not measured | Only Grok 4.7 measured |
| Neither model has a result on the other 26 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Grok 4.7 | Inkling 2 Mini | Leader |
|---|---|---|---|
| AA Intelligence Index | 35.5 | 20.1 | Grok 4.7 |
| Epoch Capabilities Index | 156.4 | Not measured | Only Grok 4.7 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index70
| Benchmark | Grok 4.7 | Inkling 2 Mini | Leader |
|---|---|---|---|
| Design Arena: agents building mobile apps | 1244 | Not measured | Only Grok 4.7 measured |
| Design Arena: spreadsheets | 1415 | Not measured | Only Grok 4.7 measured |
| LiveBench research | 89.5% | Not measured | Only Grok 4.7 measured |
| LiveBench browser | 49.3% | Not measured | Only Grok 4.7 measured |
| LiveBench long agentic | 45.3% | Not measured | Only Grok 4.7 measured |
| SREBench (Vals AI) | 3.8% | 0.0% | Grok 4.7 |
| Finance Agent (Vals AI) | 52.3% | Not measured | Only Grok 4.7 measured |
| Tax Agent Bench (Vals AI) | 35.8% | 14.1% | Grok 4.7 |
| Legal Research Bench (Vals AI) | 47.1% | 17.8% | Grok 4.7 |
| Harvey's Legal Agent Benchmark (Vals AI) | 18.3% | 5.0% | Grok 4.7 |
| Excel Modeling Benchmark (Vals AI) | 67.0% | Not measured | Only Grok 4.7 measured |
| BioMysteryBench (Vals AI) | 69.3% | 47.8% | Grok 4.7 |
| Terminal-Bench-Science (Vals AI) | 10.0% | 0.0% | Grok 4.7 |
| Vals Science Index | 34.8% | 23.6% | Grok 4.7 |
| Robo-bench (Vals AI) | 0.2% | Not measured | Only Grok 4.7 measured |
| APEX-Agents | 70.0% | Not measured | Only Grok 4.7 measured |
| Vending-Bench 2 | $10,537 | Not measured | Only Grok 4.7 measured |
| Neither model has a result on the other 27 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Grok 4.7 | Inkling 2 Mini | Leader |
|---|---|---|---|
| LiveBench reasoning | 82.7% | Not measured | Only Grok 4.7 measured |
| MysteryMechanism (Vals AI) | 25.2% | 23.0% | Grok 4.7 |
| Humanity's Last Exam (Artificial Analysis run) | 43.1% | Not measured | Only Grok 4.7 measured |
| HLE-Diamond (Artificial Analysis run) | 23.2% | 15.2% | Grok 4.7 |
| CritPt v2, hard subset (Artificial Analysis run) | 33.5% | 17.0% | Grok 4.7 |
| GPQA Diamond (Epoch AI run) | 92.7% | Not measured | Only Grok 4.7 measured |
| ARC-AGI | 90.2% | Not measured | Only Grok 4.7 measured |
| ARC-AGI-2 | 61.4% | Not measured | Only Grok 4.7 measured |
| Chess puzzles | 41.0% | Not measured | Only Grok 4.7 measured |
| Mystery game puzzles | 29.0% | Not measured | Only Grok 4.7 measured |
| LMArena Text: hard prompts | 1415 | Not measured | Only Grok 4.7 measured |
| LMArena Text: expert | 1431 | Not measured | Only Grok 4.7 measured |
| LMArena Text: hard prompts in English | 1420 | Not measured | Only Grok 4.7 measured |
| LMArena Vision: diagrams | 1258 | Not measured | Only Grok 4.7 measured |
| LMArena Vision: homework | 1286 | Not measured | Only Grok 4.7 measured |
| Humanity's Last Exam (Scale run) | 23.4% | Not measured | Only Grok 4.7 measured |
| Neither model has a result on the other 10 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | Grok 4.7 | Inkling 2 Mini | Leader |
|---|---|---|---|
| OTIS Mock AIME | 98.1% | Not measured | Only Grok 4.7 measured |
| FrontierMath, tiers 1 to 3 | 53.0% | Not measured | Only Grok 4.7 measured |
| FrontierMath, tier 4 | 17.1% | Not measured | Only Grok 4.7 measured |
| ProofBench | 26.0% | Not measured | Only Grok 4.7 measured |
| LMArena Text: math | 1412 | Not measured | Only Grok 4.7 measured |
| LMArena Text: mathematical work | 1435 | Not measured | Only Grok 4.7 measured |
| MathArena | 34.9% | Not measured | Only Grok 4.7 measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Grok 4.7 | Inkling 2 Mini | Leader |
|---|---|---|---|
| LegalBench (Vals AI) | 84.4% | Not measured | Only Grok 4.7 measured |
| MedCode (Vals AI) | 49.5% | 25.7% | Grok 4.7 |
| AA-Omniscience | 31.2 | -8.6 | Grok 4.7 |
| SimpleQA Verified | 56.0% | Not measured | Only Grok 4.7 measured |
| GeoBench | 61.0% | Not measured | Only Grok 4.7 measured |
| LMArena Text: science | 1412 | Not measured | Only Grok 4.7 measured |
| LMArena Text: medicine and healthcare | 1395 | Not measured | Only Grok 4.7 measured |
| LMArena Text: legal and government | 1418 | Not measured | Only Grok 4.7 measured |
| LMArena Text: business and finance | 1390 | Not measured | Only Grok 4.7 measured |
| FACTS Benchmark Suite | 62.3% | Not measured | Only Grok 4.7 measured |
| Neither model has a result on the other 11 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index12
| Benchmark | Grok 4.7 | Inkling 2 Mini | Leader |
|---|---|---|---|
| Design Arena: websites | 1240 | Not measured | Only Grok 4.7 measured |
| Design Arena: UI components | 1274 | 1292 | Inkling 2 Mini |
| Design Arena: game dev | 1291 | 1287 | Grok 4.7 |
| Design Arena: data viz | 1219 | Not measured | Only Grok 4.7 measured |
| Design Arena: 3D | 1239 | 1308 | Inkling 2 Mini |
| Design Arena: all code categories | 1259 | Not measured | Only Grok 4.7 measured |
| Design Arena: SVG | 1258 | Not measured | Only Grok 4.7 measured |
| LiveBench design | 75.0% | Not measured | Only Grok 4.7 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Grok 4.7 | Inkling 2 Mini | Leader |
|---|---|---|---|
| Vals Index | 58.6% | 46.5% | Grok 4.7 |
| LiveBench data analysis | 76.9% | Not measured | Only Grok 4.7 measured |
| Public Benefits Bench (Vals AI) | 65.6% | Not measured | Only Grok 4.7 measured |
| SAGE (Vals AI) | 88.7% | 85.9% | Grok 4.7 |
| MedScribe (Vals AI) | 89.4% | 86.4% | Grok 4.7 |
| Long context reasoning (AA-LCR) | 76.7% | Not measured | Only Grok 4.7 measured |
| GDPval-AA | 1717 | 1319 | Grok 4.7 |
| DTBench | 96.0% | Not measured | Only Grok 4.7 measured |
| LMCA | 49.4% | Not measured | Only Grok 4.7 measured |
| Furniture assembly | 20.8% | Not measured | Only Grok 4.7 measured |
| LMArena Text | 1400 | Not measured | Only Grok 4.7 measured |
| LMArena Text: instruction following | 1403 | Not measured | Only Grok 4.7 measured |
| LMArena Text: creative writing | 1384 | Not measured | Only Grok 4.7 measured |
| LMArena Vision | 1231 | Not measured | Only Grok 4.7 measured |
| LMArena Text: English | 1409 | Not measured | Only Grok 4.7 measured |
| LMArena Text: non-English | 1388 | Not measured | Only Grok 4.7 measured |
| LMArena Text: Chinese | 1440 | Not measured | Only Grok 4.7 measured |
| LMArena Text: German | 1377 | Not measured | Only Grok 4.7 measured |
| LMArena Text: Japanese | 1365 | Not measured | Only Grok 4.7 measured |
| LMArena Text: Korean | 1368 | Not measured | Only Grok 4.7 measured |
| LMArena Text: French | 1431 | Not measured | Only Grok 4.7 measured |
| LMArena Text: Spanish | 1395 | Not measured | Only Grok 4.7 measured |
| LMArena Text: Russian | 1401 | Not measured | Only Grok 4.7 measured |
| LMArena Text: Polish | 1405 | Not measured | Only Grok 4.7 measured |
| LMArena Text: multi-turn | 1394 | Not measured | Only Grok 4.7 measured |
| LMArena Text: longer queries | 1416 | Not measured | Only Grok 4.7 measured |
| LMArena Text: writing and language | 1395 | Not measured | Only Grok 4.7 measured |
| LMArena Text: entertainment and media | 1380 | Not measured | Only Grok 4.7 measured |
| LMArena Vision: English | 1230 | Not measured | Only Grok 4.7 measured |
| LMArena Vision: Chinese | 1275 | Not measured | Only Grok 4.7 measured |
| LMArena Vision: reading text | 1244 | Not measured | Only Grok 4.7 measured |
| LMArena Vision: humor | 1213 | Not measured | Only Grok 4.7 measured |
| LMArena Vision: creative writing | 1204 | Not measured | Only Grok 4.7 measured |
| Neither model has a result on the other 16 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Grok 4.7 | Inkling 2 Mini | 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 2 Mini costs less
Repository review
50K input + 3K output tokens
Inkling 2 Mini costs less
Agent loop
200K input + 10K output tokens
Inkling 2 Mini 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 | SpaceXSI Grok 4.7 | Thinking Machines Inkling 2 Mini |
|---|---|---|
| Maker | xAI | Thinking Machines |
| Weights | No public weights listed | Open weights |
| Released | September 21, 2026 | November 21, 2026 |
| Context window | 500K | 1.05M |
| Input $/Mtok | $2.00 | $0.0775 |
| Output $/Mtok | $6.00 | $0.325 |
| Coding index | 64.8 | 39.5 |
| Independent measurements behind it | 5 | 2 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Grok 4.7 better than Inkling 2 Mini for coding?
Pick Grok 4.7 for coding: it scores 64.8 on the Vibe Coding Index against 39.5 for Inkling 2 Mini. Pick Inkling 2 Mini for output tokens 18.5x cheaper ($0.325 vs $6.00 per million) and a larger context window (1.05M against 500K tokens).
Which is cheaper, Grok 4.7 or Inkling 2 Mini?
Grok 4.7 costs $2.00 per million input tokens and $6.00 per million output tokens; Inkling 2 Mini costs $0.0775 and $0.325. Cost per solved task is known for neither of them.
Which has the bigger context window, Grok 4.7 or Inkling 2 Mini?
Inkling 2 Mini, with 1.05M tokens against 500K.
How many benchmarks is the Grok 4.7 vs Inkling 2 Mini comparison based on?
28 benchmarks have a result for both models as of November 22, 2026. Grok 4.7's coding index rests on 5 independent benchmarks and Inkling 2 Mini's on 2. Where only one model has a result, the page says so instead of naming a winner.