Inkling 2 Mini vs Inkling 2 Small
Full profiles: Inkling 2 Mini (Thinking Machines) and Inkling 2 Small (Thinking Machines): every benchmark, price and rank.
Updated · Data from 8 sources
As of 21 Nov 2026, there are not enough shared benchmarks for a verdict, and Inkling 2 Mini is 2.0× cheaper at $0.238 vs $0.475 per 1M tokens blended. Inkling 2 Small leads in every category we measure both in. Inkling 2 Mini streams ~2× faster.
Inkling 2 Mini was released on 20 Nov 2026 and has no BenchLeader Index yet (it needs five independent results across two categories). So this page gives no quality verdict: it compares what is published so far for both, price, context window, speed and the benchmarks both have results on. First results are tracked on Inkling 2 Mini's page.
Key facts (as of 21 Nov 2026)
- Inkling 2 Mini costs $0.238 per 1M tokens blended (list price, 21 Nov 2026).
- Inkling 2 Small costs $0.475 per 1M tokens blended (list price, 21 Nov 2026).
- Inkling 2 Mini streams ~2× faster than Inkling 2 Small (Artificial Analysis, 7-day median, 21 Nov 2026).
- Of the 15 benchmarks both models have, Inkling 2 Small leads 15 (BenchLeader, 21 Nov 2026).
Which to pick for…
The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.
| Use case | Pick | Why | Confidence |
|---|---|---|---|
| Coding | Inkling 2 Small | 59 vs 44 category score; FrontierCode 2.0 (AA) 25.4% vs 15.1% | High |
| Reasoning | Inkling 2 Small | 52 vs 40 category score; HLE-Diamond (AA) 28.7% vs 15.2% | High |
| Knowledge | Inkling 2 Small | 53 vs 41 category score; AA-Omniscience v1.1 16.1 vs -8.6 | High |
| Chat quality (human preference) | – | Only Inkling 2 Small has an Arena rating (59 category score) | Not comparable |
| Lowest cost | Inkling 2 Mini | $0.238 vs $0.475 per 1M blended; agentic coding session $0.011 vs $0.022 | – |
| Fastest first answer | Inkling 2 Mini | 9.7 s (Inkling 2 Mini) vs 45.2 s (Inkling 2 Small) to the first answer token | – |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- Not enough shared benchmarks for a verdict.
- Inkling 2 Small is stronger in coding, knowledge, reasoning.
- Inkling 2 Mini is 2.0× cheaper ($0.238 vs $0.475 per 1M blended).
- Inkling 2 Mini streams 2.5× faster (280 vs 111 tokens per second).
At a glance
| Spec | Inkling 2 Mini | Inkling 2 Small |
|---|---|---|
| Developer | Thinking Machines | Thinking Machines |
| Released | 20 Nov 2026 | 5 Nov 2026 |
| Context window (tokens) | 1,048,576 | 1,048,576 |
| Compared at | Inkling 2 Mini | Inkling 2 Small |
| Open weights | Yes | No |
| Price in / out / cached input per 1M | $0.150 / $0.500 / $0.015 | $0.300 / $1.00 / $0.030 |
Category by category
Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.
| Category | Inkling 2 Mini | Inkling 2 Small | Leader |
|---|---|---|---|
| Reasoning | 39.8 | 52.1 | Inkling 2 Small |
| Coding | 43.9 | 59.4 | Inkling 2 Small |
| Agents & tools | – | 58.3 | not comparable |
| Knowledge | 40.8 | 53.3 | Inkling 2 Small |
| Human preference | – | 58.5 | not comparable |
| Multimodal | – | 63.6 | not comparable |
| Long context | – | 66.4 | not comparable |
On one chart
Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.
Not drawn, measured for fewer than two of these models: Agents & tools, Maths, Instruction following, Long context, Multimodal, Human preference.
Where sources disagree
Across the 15 benchmarks both have, Inkling 2 Mini leads 0, Inkling 2 Small leads 15. Every overall index that rates both puts Inkling 2 Small ahead.
| Overall index | Inkling 2 Mini | Inkling 2 Small | Leader |
|---|---|---|---|
| AA Intelligence Index v5.0.1 | 20.1 | 30.6 | Inkling 2 Small |
Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).
Price, speed and latency
List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.
| Measure | Inkling 2 Mini | Inkling 2 Small |
|---|---|---|
| Blended price per 1M tokens | $0.238 | $0.475 |
| Input / output per 1M | $0.150 / $0.500 | $0.300 / $1.00 |
| Cached input per 1M | $0.015 | $0.030 |
| Price per task: chat reply | $0.0002 | $0.0004 |
| Price per task: summarize a 30-page report | $0.0021 | $0.0042 |
| Price per task: code edit | $0.0017 | $0.0033 |
| Price per task: agentic coding session | $0.011 | $0.022 |
| Price per task: structured extraction | $0.0004 | $0.0008 |
| Agentic coding session, input mostly cached | $0.0049 | $0.0099 |
| Cost per benchmark task (AA Index) | $0.587 | $1.18 |
| Output tokens per task (AA Index) | 152k | 150k |
| Of which reasoning | 93k | 88k |
| Time per task (AA Index) | 9 min | 22 min |
| Output speed | 280 tok/s | 111 tok/s |
| Time to first answer | 9.7 s | 45.2 s |
| Time to a complete answer, last measured 13 Nov 2026 | – | 163.6 s |
Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $0.587 on Inkling 2 Mini and $1.18 on Inkling 2 Small, and Inkling 2 Mini wrote 1.0× as many output tokens for the same work.
Each model is compared at its best-ranked reasoning-effort setting. Inkling 2 Mini and takes 10 s to its first answer token. Inkling 2 Small scores 57.2 and takes 45 s to its first answer token; Inkling 2 Small (xhigh) scores 52.1 in 45 s. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.
Every benchmark
81 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.
| Metric | Publisher | Inkling 2 Mini | Inkling 2 Small |
|---|---|---|---|
| BenchLeader Index | BenchLeader | – | 57.2 |
| Coding score | BenchLeader | 43.9 | 59.4 |
| Knowledge score | BenchLeader | 40.8 | 53.3 |
| Reasoning score | BenchLeader | 39.8 | 52.1 |
| Agents & tools score | BenchLeader | – | 58.3 |
| Human preference score | BenchLeader | – | 58.5 |
| Long context score | BenchLeader | – | 66.4 |
| Multimodal score | BenchLeader | – | 63.6 |
| Blended price $/M | BenchLeader | $0.238 | $0.475 |
| Output speed | BenchLeader | 280 tok/s | 111 tok/s |
| Time to first answer | BenchLeader | 9.7 s | 45.2 s |
| Context window | BenchLeader | 1,048,576 tokens | 1,048,576 tokens |
| Reasoning | |||
| Arena Hard Prompts | Arena (LMArena) | – | 1439 |
| Humanity's Last Exam (AA) | Artificial Analysis | – | 44.1% |
| HLE-Diamond (AA) | Artificial Analysis | 15.2% | 28.7% |
| ARC-AGI-1 | ARC Prize | 84.5%† | 96.5%† |
| ARC-AGI-2 | ARC Prize | 49.3%† | 81.7%† |
| ARC-AGI-3 | ARC Prize | – | 2.6%† |
| CritPt v2 hard subset (AA) | Artificial Analysis | 17.0% | 35.0% |
| MysteryMechanism | Vals AI | – | 25.2% |
| Arena Expert | Arena (LMArena) | – | 1488 |
| Coding | |||
| SciCode | SciCode | – | 52.3% |
| Arena Coding | Arena (LMArena) | – | 1485 |
| Arena WebDev | Arena (LMArena) | – | 1643 |
| ProgramBench | Vals AI | – | 0.5% |
| SWE-bench Multimodal | Vals AI | – | 43.1% |
| Vibe Code Bench v1.1 | Vals AI | – | 81.5% |
| SWE Atlas v1.1 | Scale AI SEAL | – | 61.9%† |
| SWE Atlas v1.1: Codebase QnA | Scale AI SEAL | – | 74.2%† |
| SWE Atlas v1.1: Test Writing | Scale AI SEAL | – | 58.1%† |
| SWE Atlas v1.1: Refactoring | Scale AI SEAL | – | 53.3%† |
| SWE-Bench Pro V2 | Scale AI SEAL | – | 97.7%† |
| SWE-Bench Pro V2 HARD | Scale AI SEAL | – | 86.3%† |
| FrontierSWE | Epoch AI Benchmarking Hub | – | 25.1%† |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 5.6% | 13.1% |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | – | 81.3% |
| Design Arena Code | Design Arena | – | 1377 |
Show all 81 benchmarks
| Metric | Publisher | Inkling 2 Mini | Inkling 2 Small |
|---|---|---|---|
| Coding | |||
| FrontierCode 2.0 (AA) | Artificial Analysis | 15.1% | 25.4% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | – | 13.0%† |
| APEX-Agents | Mercor | – | 46.8% |
| Arena Agent | Arena (LMArena) | – | 1.5 |
| MCP Atlas | Scale AI SEAL | – | 85.4%† |
| GDPval-AA v2.1 | Artificial Analysis | 1319 | 1630 |
| τ³-Banking (AA) | Artificial Analysis | – | 40.4% |
| Analyst Agent (AA) | Artificial Analysis | 46.3% | 51.3% |
| CyberBench | Vals AI | – | 72.7% |
| Finance Agent v2.1 | Vals AI | – | 67.5% |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | – | 21.7% |
| Legal Research Bench | Vals AI | – | 46.6% |
| SREBench | Vals AI | – | 1.9% |
| Tax Agent Bench | Vals AI | – | 38.9% |
| Terminal-Bench 4.0 (Vals) | Vals AI | – | 12.6% |
| Terminal-Bench Science | Vals AI | – | 2.9% |
| Arena Agent Task Completion | Arena (LMArena) | – | 2.4 |
| AutomationBench | Artificial Analysis | 41.8% | 45.6% |
| GDP.pdf (AA) | Artificial Analysis | 16.8% | 25.2% |
| EnterpriseOps-Gym | Artificial Analysis | 42.0% | 46.8% |
| AA-Briefcase v1.1 | Artificial Analysis | 1263 | 1527 |
| Design Arena Agentic | Design Arena | – | 1303 |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 1.4% | 5.7% |
| Maths | |||
| ArXivMath | MathArena | – | 31.9% |
| BrokenArXiv | MathArena | – | 63.2% |
| Knowledge | |||
| AA-Omniscience v1.1 | Artificial Analysis | -8.6 | 16.1 |
| BioMysteryBench | Vals AI | – | 70.0% |
| Excel Modeling Benchmark v1.1 | Vals AI | – | 69.5% |
| MedCode | Vals AI | – | 44.1% |
| MedScribe | Vals AI | – | 90.2% |
| Arena Text Factuality | Arena (LMArena) | – | 1424 |
| GDP.pdf | Epoch AI Benchmarking Hub | – | 43.6%† |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | 20.5% | 33.8% |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 63.4% | 73.3% |
| Instruction following | |||
| Arena Instruction Following | Arena (LMArena) | – | 1409 |
| Human preference | |||
| Arena Text | Arena (LMArena) | – | 1412 |
| Arena Creative Writing | Arena (LMArena) | – | 1344 |
| Arena Multi-turn | Arena (LMArena) | – | 1413 |
| Arena Longer Queries | Arena (LMArena) | – | 1408 |
| Multimodal | |||
| MMMU-Pro | Artificial Analysis | – | 81.6% |
| SAGE | Vals AI | – | 88.6% |
| Humanity's Sixth Sense | Scale AI SEAL | – | 33.3%† |
| VIALS-AA | Handshake AI | – | 42.9% |
| Code2Video-AA | Artificial Analysis | 870 | 1020 |
| AA-3D | Artificial Analysis | – | 1027 |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | – | 83.3% |
| MLCR | Artificial Analysis | – | 20.6% |
| Composite | |||
| AA Intelligence Index v5.0.1 | Artificial Analysis | 20.1 | 30.6 |
| AA Progress Index v1 | Artificial Analysis | – | 317.6 |
| Vals Index | Vals AI | – | 56.1 |
| Vals Finance Index | Vals AI | – | 61.5% |
| Vals Science Index | Vals AI | – | 32.7% |
| Vals Legal Index | Vals AI | – | 73.9% |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | – | 16.2%† |
| DistressBench | Scale AI SEAL | – | 82.3%† |
| Metadata | |||
| AA Openness Index | Artificial Analysis | – | 38.9 |
Data as of 2026-11-21. Best configuration of each model; every score links to its source on the model pages.
What changed
- Inkling 2 Small: BenchLeader Index 57.9 → 57.2.
- Inkling 2 Mini: first results.
- Inkling 2 Small: 2 score revisions.
- Inkling 2 Small: 3 new results (AA Progress Index v1, MedCode, MedScribe).
- Inkling 2 Small: 1 score revision.
- Inkling 2 Small: 1 score revision; Inkling 2 Small cached input price moved from $0.060/M to $0.030/M (50% down).
- Inkling 2 Small: 1 score revision.
- Inkling 2 Small: BenchLeader Index 58.4 → 57.9.
- Inkling 2 Small: 2 new results (FORTRESS, Design Arena Agentic).
- Inkling 2 Small: 2 new results (MysteryMechanism, Vals Science Index); 1 score revision.
Related comparisons
- Inkling 2 Mini vs Inkling
- Inkling 2 Small vs Gemini 4 Carbon
- Inkling 2 Small vs GPT-6 Astra
- Inkling 2 Small vs Claude Opus 5.5
- Inkling 2 Small vs Claude Fable 5.1
- Inkling Small vs Inkling 2 Small
- Inkling 2 Small vs GPT-6.1 Sol
- Inkling 2 Small vs Claude Fable 5
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
Inkling 2 Mini vs Inkling 2 Small: questions
- Inkling 2 Mini vs Inkling 2 Small: which is cheaper, and will that change?
- Inkling 2 Mini is cheaper today: $0.238 against $0.475 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is Inkling 2 Mini or Inkling 2 Small better for coding?
- Inkling 2 Small scores higher in coding (59 vs 44 on the category index, where 50 is average). On FrontierCode 2.0 (AA), the top shared coding benchmark, it is 15.1% for Inkling 2 Mini against 25.4% for Inkling 2 Small.
- Which is faster, Inkling 2 Mini or Inkling 2 Small?
- Inkling 2 Mini streams ~2× faster (280 vs 111 output tokens per second, Artificial Analysis 7-day median).
- Which is better for long documents?
- Both accept 1,048,576 tokens of context.
- Which has lower latency?
- Inkling 2 Mini answers first: 9.7 s against 45.2 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
More questions (2)
- Do independent benchmarks agree on Inkling 2 Mini vs Inkling 2 Small?
- Across the 15 benchmarks both have, Inkling 2 Mini leads 0, Inkling 2 Small leads 15. Every overall index that rates both puts Inkling 2 Small ahead.
- When was Inkling 2 Mini released?
- Inkling 2 Mini was released on 20 Nov 2026.