Is Inkling 2 Small state of the art?Yes.Yes on Coding › Web dev (open weights). Not the overall leader.
As of Nov 22, 2026, Inkling 2 Small is tied for state of the art in Coding › Web dev (since Nov 9, 2026; sources LMArena WebDev; methodology v1.0). Inkling 2 Small is tied for SOTA in Coding › Web dev with Kimi K3, DeepSeek V4.1 Flash, Hy4, within the margin of error, since 2026-11-20.
Facts and scores
Inkling 2 Small is an open-weights (Proprietary) text and image model from thinky, nov 5, 2026; 594B parameters, a 1,049K-token context window and $0.475 per 1M tokens blended.
How it scores
- On MedScribe it scores 90.2 (CI 86.4–93.9), #5 of 94 (top 6%); 1.2 behind Claude Opus 5.5; Claude Opus 5 is 0.8 above and Muse Spark 1.2 is 0.1 below.
- On Finance Agent it scores 67.5 (CI 63.6–71.5), #5 of 40 (top 13%); 2.0 behind Claude Fable 5.2; Muse Wonder Full is 0.1 above and Claude Sonnet 5.5 is 0.2 below.
- On LMArena WebDev it scores 1643 (CI 1625–1660), #26 of 165 (top 16%); 181 behind Claude Fable 5.2; Muse Wonder is 4 above and Grok 4.7 is 4 below.
History
First result on isitsota: Nov 19, 2026. Best overall rank so far: #5 in Finance, first held Nov 22, 2026.
The ruling, in plain English
Ranked #131 in General LLM.
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| LMArena Text (style-controlled, overall) Inkling 2 Small | 1412 1400–1424 | 2026-11-19 | INDEP. | snap_280a9b5ca493 |
| LMArena Text (style-controlled, hard prompts) Inkling 2 Small | 1439 1424–1453 | 2026-11-19 | INDEP. | snap_280a9b5ca493 |
| MysteryMechanism thinkingmachines/inkling-2-small · Source: Vals AI | 25.2 19.5–31.0 | 2026-11-21 | INDEP. | snap_vals_54c41eb6660d |
| LMArena Text (style-controlled, coding) Inkling 2 Small | 1485 1462–1509 | 2026-11-19 | INDEP. | snap_280a9b5ca493 |
| LMArena WebDev Inkling 2 Small | 1643 1625–1660 | 2026-11-20 | INDEP. | snap_2f4a3ebc7e46 |
| LMArena Text (style-controlled, longer query) Inkling 2 Small | 1408 1390–1427 | 2026-11-19 | INDEP. | snap_280a9b5ca493 |
| LMArena Text factuality Inkling 2 Small | 1424 1414–1434 | 2026-11-19 | INDEP. | snap_275d95909246 |
| SRE Bench thinkingmachines/inkling-2-small · Source: Vals AI | 1.9 24.8%–3.6 | 2026-11-21 | INDEP. | snap_vals_655377da102f |
| Finance Agent thinkingmachines/inkling-2-small · Source: Vals AI | 67.5 63.6–71.5 | 2026-11-21 | INDEP. | snap_vals_f9cfcd576758 |
| Legal Research Bench thinkingmachines/inkling-2-small · Source: Vals AI | 46.6 39.8–53.4 | 2026-11-21 | INDEP. | snap_vals_e4530282a8b5 |
Rows marked Vals AI come from Vals AI's proprietary benchmarks, republished with permission. Each receipt links to the benchmark on Vals.
Where it sits in the succession
Crown intervals for this model are still empty.
Where it is not the crown
| Category | This model | Rank | Leader |
|---|---|---|---|
| General LLM | #131 in this category | #131 | Gemini 4 Carbon |
| Reasoning | #122 in this category | #122 | Gemini 4 Carbon |
| Science | #18 in this category | #18 | GPT-6.2 Astra |
| Coding | Not enough data | — | Claude Sonnet 5.5 |
| Coding › Web dev | #24 in this category | #24 | Claude Fable 5.2 |
| Long context | #140 in this category | #140 | Gemini 4 Argon |
| Factuality | #115 in this category | #115 | Gemini 4 Carbon |
| Cybersecurity | #21 in this category | #21 | GPT-6 Astra |
Related pages
- General LLM
- Reasoning
- Science
- Coding
- Coding › Web dev
- Long context
- Factuality
- Cybersecurity
- Finance
- Legal
- Compare with the current leader in General LLM: Gemini 4 Argon
- Compare with the current leader in General LLM: Muse Wonder
- Compare with the current leader in Reasoning: Gemini 4 Argon
- Compare with the current leader in Coding › Web dev: Claude Fable 5.2
- Compare with the current leader in Coding › Web dev: Claude Opus 5.5
- Compare with the current leader in Long context: Gemini 4 Argon
- Inkling 2 Small vs Claude Fable 5
- Inkling 2 Small vs Muse Spark 1.2
- Inkling 2 Small vs Claude Fable 5.1
- Announced, pending benchmarks: Inkling 2 Mini
- LMArena WebDev
- SRE Bench
- Legal Research Bench
- LMArena Text (style-controlled, overall)
- LMArena Text (style-controlled, coding)
- LMArena Text (style-controlled, hard prompts)
- LMArena Text (style-controlled, longer query)
- LMArena Text factuality
- Finance Agent
- MysteryMechanism
- Lab: thinky
- Crown change in November 2026 recap
Is Inkling 2 Small SOTA?
As of Nov 22, 2026, Inkling 2 Small is tied for state of the art in Coding › Web dev (since Nov 9, 2026; sources LMArena WebDev; methodology v1.0).
What is Inkling 2 Small best at?
As of Nov 22, 2026, Inkling 2 Small is ranked #5 in Finance (since Nov 22, 2026; sources Finance Agent).
How does Inkling 2 Small rank in Coding?
As of Nov 22, 2026, Inkling 2 Small is short of the evidence for a rank in Coding (since Nov 22, 2026; sources LMArena Text (style-controlled, coding); methodology v1.0).
When was Inkling 2 Small last SOTA?
As of Nov 22, 2026, Inkling 2 Small last held Coding › Web dev from Nov 9, 2026 until Nov 20, 2026.