Inkling 2 Small vs Solar Mini 4
Solar Mini 4 costs 5.0x less per output token than Inkling 2 Small ($0.20 vs $1.00 per million). Updated November 14, 2026; 6 benchmarks have a result for both.
Inkling 2 Small or Solar Mini 4: which to pick
Only Inkling 2 Small has a coding score, 48.9 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 5.0x cheaper ($0.20 vs $1.00 per million).
- Shared results
- 6
- Inkling 2 Small only
- 45
- Solar Mini 4 only
- 6
- 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 2 Small has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
No call
Only Inkling 2 Small has a AA Intelligence Index result, 30.6.
Directional only
Web design
Design Arena: websites
No call
Only Solar Mini 4 has a Design Arena: websites result, 1144.
Directional only
General
Vals Index
No call
Only Inkling 2 Small has a Vals Index result, 56.1%.
Directional only
Long documents
Listed context window
Inkling 2 Small
Inkling 2 Small takes 1.05M tokens against 524K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Solar Mini 4
Inkling 2 Small $0.0008, Solar Mini 4 $0.0001 per turn.
List prices
At a glance
- Coding index
- Inkling 2 Small 48.9 from 3 benchmarks, Solar Mini 4 not benchmarked.
- Widest category
- General, 22.4 points apart on average over 2 shared benchmarks.
- Widest single gap
- GDPval-AA: Inkling 2 Small 1630 against Solar Mini 4 1092, 44.8 points apart on a 0 to 100 scale.
- Output price
- Inkling 2 Small $1.00 against Solar Mini 4 $0.20 per million output tokens, 5.0x apart.
- Context window
- Inkling 2 Small takes 1.05M tokens, Solar Mini 4 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 | Inkling 2 Small | Bars | Solar Mini 4 | Ties |
|---|---|---|---|---|
| Coding | 2 | 0 | ||
| Reasoning | 1 | 0 | ||
| Knowledge | 1 | 0 | ||
| General | 1 | 0 | 1 tie | |
| All shared boards | 5 | 0 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
| Benchmark | Inkling 2 Small | Solar Mini 4 | Leader |
|---|---|---|---|
| LMArena WebDev | 1647 | Not measured | Only Inkling 2 Small measured |
| Terminal-Bench 4 (Vals AI) | 12.6% | Not measured | Only Inkling 2 Small measured |
| Vibe Code Bench (Vals AI) | 81.5% | Not measured | Only Inkling 2 Small measured |
| ProgramBench (Vals AI) | 0.5% | Not measured | Only Inkling 2 Small measured |
| SWE-bench Multimodal (Vals AI) | 43.1% | Not measured | Only Inkling 2 Small measured |
| CyberBench (Vals AI) | 72.7% | Not measured | Only Inkling 2 Small measured |
| SciCode | 52.3% | 47.6% | Inkling 2 Small |
| Terminal-Bench 4.0 (Artificial Analysis run) | 13.1% | 1.0% | Inkling 2 Small |
| FrontierCode 2.0 | 25.4% | Not measured | Only Inkling 2 Small measured |
| LMArena Text: coding | 1455 | Not measured | Only Inkling 2 Small measured |
| LMArena Text: software and IT | 1443 | Not measured | Only Inkling 2 Small measured |
| LMArena WebDev: React | 1660 | Not measured | Only Inkling 2 Small measured |
| LMArena WebDev: HTML | 1661 | Not measured | Only Inkling 2 Small measured |
| SWE-Bench Pro V2 | 97.7% | Not measured | Only Inkling 2 Small measured |
| Neither model has a result on the other 38 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Inkling 2 Small | Solar Mini 4 | Leader |
|---|---|---|---|
| AA Intelligence Index | 30.6 | Not measured | Only Inkling 2 Small measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | Inkling 2 Small | Solar Mini 4 | Leader |
|---|---|---|---|
| SREBench (Vals AI) | 1.9% | Not measured | Only Inkling 2 Small measured |
| Tax Agent Bench (Vals AI) | 38.9% | Not measured | Only Inkling 2 Small measured |
| Legal Research Bench (Vals AI) | 46.6% | Not measured | Only Inkling 2 Small measured |
| Harvey's Legal Agent Benchmark (Vals AI) | 21.7% | Not measured | Only Inkling 2 Small measured |
| BioMysteryBench (Vals AI) | 70.0% | Not measured | Only Inkling 2 Small measured |
| Terminal-Bench-Science (Vals AI) | 2.9% | Not measured | Only Inkling 2 Small measured |
| Vals Science Index | 32.7% | Not measured | Only Inkling 2 Small measured |
| APEX-Agents | 46.8% | Not measured | Only Inkling 2 Small measured |
| MCP Atlas | 85.4% | Not measured | Only Inkling 2 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 2 Small | Solar Mini 4 | Leader |
|---|---|---|---|
| MysteryMechanism (Vals AI) | 25.2% | Not measured | Only Inkling 2 Small measured |
| Humanity's Last Exam (Artificial Analysis run) | 44.1% | 25.8% | Inkling 2 Small |
| HLE-Diamond (Artificial Analysis run) | 28.7% | Not measured | Only Inkling 2 Small measured |
| CritPt v2, hard subset (Artificial Analysis run) | 35.0% | Not measured | Only Inkling 2 Small measured |
| ARC-AGI | 96.5% | Not measured | Only Inkling 2 Small measured |
| ARC-AGI-2 | 81.7% | Not measured | Only Inkling 2 Small measured |
| LMArena Text: hard prompts | 1421 | Not measured | Only Inkling 2 Small measured |
| LMArena Text: expert | 1478 | Not measured | Only Inkling 2 Small measured |
| LMArena Text: hard prompts in English | 1424 | Not measured | Only Inkling 2 Small measured |
| Neither model has a result on the other 17 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Inkling 2 Small | Solar Mini 4 | Leader |
|---|---|---|---|
| MathArena | 42.4% | Not measured | Only Inkling 2 Small measured |
| Neither model has a result on the other 13 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Inkling 2 Small | Solar Mini 4 | Leader |
|---|---|---|---|
| AA-Omniscience | 16.1 | -11.6 | Inkling 2 Small |
| LMArena Text: science | 1409 | Not measured | Only Inkling 2 Small measured |
| LMArena Text: business and finance | 1415 | Not measured | Only Inkling 2 Small measured |
| Neither model has a result on the other 18 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Inkling 2 Small | Solar Mini 4 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1144 | Only Solar Mini 4 measured |
| Design Arena: UI components | Not measured | 1087 | Only Solar Mini 4 measured |
| Design Arena: game dev | Not measured | 1097 | Only Solar Mini 4 measured |
| Design Arena: data viz | Not measured | 1135 | Only Solar Mini 4 measured |
| Design Arena: 3D | Not measured | 1084 | Only Solar Mini 4 measured |
| Design Arena: all code categories | Not measured | 1127 | Only Solar Mini 4 measured |
| Neither model has a result on the other 3 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Inkling 2 Small | Solar Mini 4 | Leader |
|---|---|---|---|
| Vals Index | 56.1% | Not measured | Only Inkling 2 Small measured |
| SAGE (Vals AI) | 88.6% | Not measured | Only Inkling 2 Small measured |
| Long context reasoning (AA-LCR) | 83.3% | 83.3% | Tie |
| GDPval-AA | 1630 | 1092 | Inkling 2 Small |
| LMArena Text | 1403 | Not measured | Only Inkling 2 Small measured |
| LMArena Text: instruction following | 1408 | Not measured | Only Inkling 2 Small measured |
| LMArena Text: creative writing | 1348 | Not measured | Only Inkling 2 Small measured |
| LMArena Text: English | 1418 | Not measured | Only Inkling 2 Small measured |
| LMArena Text: non-English | 1390 | Not measured | Only Inkling 2 Small measured |
| LMArena Text: Russian | 1377 | Not measured | Only Inkling 2 Small measured |
| LMArena Text: multi-turn | 1408 | Not measured | Only Inkling 2 Small measured |
| LMArena Text: longer queries | 1403 | Not measured | Only Inkling 2 Small measured |
| LMArena Text: writing and language | 1381 | Not measured | Only Inkling 2 Small measured |
| LMArena Text: entertainment and media | 1359 | Not measured | Only Inkling 2 Small measured |
| Neither model has a result on the other 35 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Inkling 2 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 2 Small | Upstage Solar Mini 4 |
|---|---|---|
| Maker | Thinking Machines | Upstage |
| Weights | Open weights | No public weights listed |
| Released | November 9, 2026 | September 23, 2026 |
| Context window | 1.05M | 524K |
| Input $/Mtok | $0.30 | $0.05 |
| Output $/Mtok | $1.00 | $0.20 |
| Coding index | 48.9 | Not benchmarked |
| Independent measurements behind it | 3 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Inkling 2 Small better than Solar Mini 4 for coding?
Only Inkling 2 Small has a coding score, 48.9 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 5.0x cheaper ($0.20 vs $1.00 per million).
Which is cheaper, Inkling 2 Small or Solar Mini 4?
Inkling 2 Small costs $0.30 per million input tokens and $1.00 per million output tokens; Solar Mini 4 costs $0.05 and $0.20. Cost per solved task is known for neither of them.
Which has the bigger context window, Inkling 2 Small or Solar Mini 4?
Inkling 2 Small, with 1.05M tokens against 524K.
How many benchmarks is the Inkling 2 Small vs Solar Mini 4 comparison based on?
6 benchmarks have a result for both models as of November 14, 2026. Inkling 2 Small's coding index rests on 3 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.