Inkling Small vs Solar Mini 4
Inkling Small leads Solar Mini 4 on the Artificial Analysis Intelligence Index, 25.7 to 24.1, and Solar Mini 4 costs 6.0x less per output token ($0.20 vs $1.20 per million). Updated October 21, 2026; 4 benchmarks have a result for both.
Inkling Small or Solar Mini 4: which to pick
Only Inkling Small has a coding score, 27.3 on the Vibe Coding Index; Solar Mini 4 has none, so the two cannot be ranked on coding.
Pick Solar Mini 4 for output tokens 6.0x cheaper ($0.20 vs $1.20 per million) and work measured by Long context reasoning (AA-LCR), where it leads.
- Shared results
- 4
- Inkling Small only
- 80
- Solar Mini 4 only
- 3
- Like-for-like categories
- 4 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
No call
Only Inkling Small has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Inkling Small
Inkling Small leads, 25.7 against 24.1.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Inkling Small has a AA Agentic Index result, 23.5.
Directional only
Reasoning
GPQA Diamond
No call
Only Inkling Small has a GPQA Diamond result, 83.6%.
Directional only
Knowledge
MMLU Pro
No call
Only Inkling Small has a MMLU Pro result, 85.6%.
Directional only
Web design
Design Arena: websites
No call
Only Solar Mini 4 has a Design Arena: websites result, 1159.
Directional only
General
Vals Index
No call
Only Inkling Small has a Vals Index result, 27.6%.
Directional only
Long documents
Listed context window
No call
Both take 524K tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Solar Mini 4
Inkling Small $0.0010, Solar Mini 4 $0.0001 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Inkling Small has the number, $0.16.
Directional only
At a glance
- Coding index
- Inkling Small 27.3 from 4 benchmarks, Solar Mini 4 not benchmarked.
- Widest category
- General, 7.7 points apart on average over 1 shared benchmark.
- Widest single gap
- Long context reasoning (AA-LCR): Inkling Small 75.7% against Solar Mini 4 83.3%, 7.7 points apart on a 0 to 100 scale.
- Output price
- Inkling Small $1.20 against Solar Mini 4 $0.20 per million output tokens, 6.0x apart.
- Context window
- Both take 524K tokens.
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 | Inkling Small | Bars | Solar Mini 4 | Ties |
|---|---|---|---|---|
| Coding | 1 | 0 | ||
| Intelligence | 1 | 0 | ||
| Reasoning | 1 | 0 | ||
| General | 0 | 1 | ||
| All shared boards | 3 | 1 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index10
| Benchmark | Inkling Small | Solar Mini 4 | Leader |
|---|---|---|---|
| LMArena WebDev | 1409 | Not measured | Only Inkling Small measured |
| AA Coding Index | 52.9 | Not measured | Only Inkling Small measured |
| LiveCodeBench (Vals AI) | 85.9% | Not measured | Only Inkling Small measured |
| SWE-bench Verified (Vals AI) | 82.2% | Not measured | Only Inkling Small measured |
| Terminal-Bench 4 (Vals AI) | 0.0% | Not measured | Only Inkling Small measured |
| Vibe Code Bench (Vals AI) | 19.1% | Not measured | Only Inkling Small measured |
| Code migration (Vals AI) | 13.7% | Not measured | Only Inkling Small measured |
| ProgramBench (Vals AI) | 0.5% | Not measured | Only Inkling Small measured |
| IOI (Vals AI) | 9.3% | Not measured | Only Inkling Small measured |
| Terminal-Bench 2.1 (Vals AI) | 55.1% | Not measured | Only Inkling Small measured |
| SkillsBench (Vals AI) | 33.6% | Not measured | Only Inkling Small measured |
| CyberBench (Vals AI) | 64.1% | Not measured | Only Inkling Small measured |
| SciCode | 49.7% | 47.6% | Inkling Small |
| LMArena Text: coding | 1450 | Not measured | Only Inkling Small measured |
| LMArena Text: software and IT | 1447 | Not measured | Only Inkling Small measured |
| LMArena WebDev: React | 1399 | Not measured | Only Inkling Small measured |
| LMArena WebDev: HTML | 1398 | Not measured | Only Inkling Small measured |
| LMArena WebDev: from an image | 1410 | Not measured | Only Inkling Small measured |
| Neither model has a result on the other 21 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Inkling Small | Solar Mini 4 | Leader |
|---|---|---|---|
| AA Intelligence Index | 25.7 | 24.1 | Inkling Small |
| Epoch Capabilities Index | 150.3 | Not measured | Only Inkling Small measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Inkling Small | Solar Mini 4 | Leader |
|---|---|---|---|
| AA Agentic Index | 23.5 | Not measured | Only Inkling Small measured |
| Finance Agent (Vals AI) | 41.3% | Not measured | Only Inkling Small measured |
| Tax Agent Bench (Vals AI) | 15.4% | Not measured | Only Inkling Small measured |
| Legal Research Bench (Vals AI) | 25.5% | Not measured | Only Inkling Small measured |
| Harvey's Legal Agent Benchmark (Vals AI) | 2.9% | Not measured | Only Inkling Small measured |
| Excel Modeling Benchmark (Vals AI) | 31.8% | Not measured | Only Inkling Small measured |
| Neither model has a result on the other 35 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Inkling Small | Solar Mini 4 | Leader |
|---|---|---|---|
| GPQA Diamond | 83.6% | Not measured | Only Inkling Small measured |
| GPQA Diamond (Artificial Analysis run) | 89.5% | Not measured | Only Inkling Small measured |
| Humanity's Last Exam (Artificial Analysis run) | 33.3% | 25.8% | Inkling Small |
| GPQA Diamond (Epoch AI run) | 88.5% | Not measured | Only Inkling Small measured |
| ARC-AGI | 84.0% | Not measured | Only Inkling Small measured |
| ARC-AGI-2 | 40.1% | Not measured | Only Inkling Small measured |
| Mystery game puzzles | 6.0% | Not measured | Only Inkling Small measured |
| LMArena Text: hard prompts | 1423 | Not measured | Only Inkling Small measured |
| LMArena Text: expert | 1441 | Not measured | Only Inkling Small measured |
| LMArena Text: hard prompts in English | 1429 | Not measured | Only Inkling Small measured |
| LMArena Vision: diagrams | 1251 | Not measured | Only Inkling Small measured |
| LMArena Vision: homework | 1257 | Not measured | Only Inkling Small measured |
| Neither model has a result on the other 10 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Inkling Small | Solar Mini 4 | Leader |
|---|---|---|---|
| OTIS Mock AIME | 90.0% | Not measured | Only Inkling Small measured |
| FrontierMath, tiers 1 to 3 | 46.3% | Not measured | Only Inkling Small measured |
| FrontierMath, tier 4 | 17.1% | Not measured | Only Inkling Small measured |
| ProofBench | 6.0% | Not measured | Only Inkling Small measured |
| LMArena Text: math | 1459 | Not measured | Only Inkling Small measured |
| LMArena Text: mathematical work | 1441 | Not measured | Only Inkling Small measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
| Benchmark | Inkling Small | Solar Mini 4 | Leader |
|---|---|---|---|
| MMLU Pro | 85.6% | Not measured | Only Inkling Small measured |
| LegalBench (Vals AI) | 83.0% | Not measured | Only Inkling Small measured |
| CorpFin (Vals AI) | 69.6% | Not measured | Only Inkling Small measured |
| TaxEval (Vals AI) | 75.5% | Not measured | Only Inkling Small measured |
| MortgageTax (Vals AI) | 62.3% | Not measured | Only Inkling Small measured |
| MedCode (Vals AI) | 37.9% | Not measured | Only Inkling Small measured |
| SimpleQA Verified | 19.1% | Not measured | Only Inkling Small measured |
| LMArena Text: science | 1428 | Not measured | Only Inkling Small measured |
| LMArena Text: medicine and healthcare | 1413 | Not measured | Only Inkling Small measured |
| LMArena Text: legal and government | 1415 | Not measured | Only Inkling Small measured |
| LMArena Text: business and finance | 1413 | Not measured | Only Inkling Small measured |
| Neither model has a result on the other 7 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Inkling Small | Solar Mini 4 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1159 | Only Solar Mini 4 measured |
| Design Arena: game dev | Not measured | 1109 | Only Solar Mini 4 measured |
| Design Arena: all code categories | Not measured | 1150 | Only Solar Mini 4 measured |
| Neither model has a result on the other 6 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Inkling Small | Solar Mini 4 | Leader |
|---|---|---|---|
| Vals Index | 27.6% | Not measured | Only Inkling Small measured |
| Public Benefits Bench (Vals AI) | 59.4% | Not measured | Only Inkling Small measured |
| SAGE (Vals AI) | 32.7% | Not measured | Only Inkling Small measured |
| MedScribe (Vals AI) | 84.1% | Not measured | Only Inkling Small measured |
| Vals Multimodal Index | 50.0% | Not measured | Only Inkling Small measured |
| Long context reasoning (AA-LCR) | 75.7% | 83.3% | Solar Mini 4 |
| LMArena Text | 1413 | Not measured | Only Inkling Small measured |
| LMArena Text: instruction following | 1399 | Not measured | Only Inkling Small measured |
| LMArena Text: creative writing | 1334 | Not measured | Only Inkling Small measured |
| LMArena Vision | 1237 | Not measured | Only Inkling Small measured |
| LMArena Text: English | 1421 | Not measured | Only Inkling Small measured |
| LMArena Text: non-English | 1401 | Not measured | Only Inkling Small measured |
| LMArena Text: Chinese | 1464 | Not measured | Only Inkling Small measured |
| LMArena Text: German | 1408 | Not measured | Only Inkling Small measured |
| LMArena Text: Japanese | 1401 | Not measured | Only Inkling Small measured |
| LMArena Text: Korean | 1367 | Not measured | Only Inkling Small measured |
| LMArena Text: French | 1435 | Not measured | Only Inkling Small measured |
| LMArena Text: Spanish | 1422 | Not measured | Only Inkling Small measured |
| LMArena Text: Russian | 1394 | Not measured | Only Inkling Small measured |
| LMArena Text: Polish | 1428 | Not measured | Only Inkling Small measured |
| LMArena Text: multi-turn | 1416 | Not measured | Only Inkling Small measured |
| LMArena Text: longer queries | 1402 | Not measured | Only Inkling Small measured |
| LMArena Text: writing and language | 1357 | Not measured | Only Inkling Small measured |
| LMArena Text: entertainment and media | 1352 | Not measured | Only Inkling Small measured |
| LMArena Vision: English | 1243 | Not measured | Only Inkling Small measured |
| LMArena Vision: Chinese | 1292 | Not measured | Only Inkling Small measured |
| LMArena Vision: reading text | 1243 | Not measured | Only Inkling Small measured |
| LMArena Vision: humor | 1207 | Not measured | Only Inkling Small measured |
| LMArena Vision: creative writing | 1205 | Not measured | Only Inkling Small measured |
| Neither model has a result on the other 17 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Inkling Small | Solar Mini 4 | 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
Solar Mini 4 costs less
Repository review
50K input + 3K output tokens
Solar Mini 4 costs less
Agent loop
200K input + 10K output tokens
Solar Mini 4 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 | Thinking Machines Inkling Small | Upstage Solar Mini 4 |
|---|---|---|
| Maker | Thinking Machines | Upstage |
| Weights | Open weights | No public weights listed |
| Released | July 30, 2026 | September 23, 2026 |
| Context window | 524K | 524K |
| Input $/Mtok | $0.45 | $0.05 |
| Output $/Mtok | $1.20 | $0.20 |
| Coding index | 27.3 | Not benchmarked |
| Independent measurements behind it | 4 | 0 |
| Cost per solved task | $0.16 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Inkling Small better than Solar Mini 4 for coding?
Only Inkling Small has a coding score, 27.3 on the Vibe Coding Index; Solar Mini 4 has none, so the two cannot be ranked on coding. Pick Solar Mini 4 for output tokens 6.0x cheaper ($0.20 vs $1.20 per million) and work measured by Long context reasoning (AA-LCR), where it leads.
Which is cheaper, Inkling Small or Solar Mini 4?
Inkling Small costs $0.45 per million input tokens and $1.20 per million output tokens; Solar Mini 4 costs $0.05 and $0.20. Cost per solved task is known for Inkling Small only.
Which has the bigger context window, Inkling Small or Solar Mini 4?
Neither: both take 524K tokens.
How many benchmarks is the Inkling Small vs Solar Mini 4 comparison based on?
4 benchmarks have a result for both models as of October 21, 2026. Inkling Small's coding index rests on 4 independent benchmarks and Solar Mini 4's on 0. Where only one model has a result, the page says so instead of naming a winner.