Inkling 2 Small vs Qwen3.7 Plus
Full profiles: Inkling 2 Small (Thinking Machines) and Qwen3.7 Plus (Alibaba): every benchmark, price and rank.
Updated · Data from 9 sources
As of 16 Nov 2026, Inkling 2 Small and Qwen3.7 Plus are neck and neck on quality (57.9 vs 57.6 on the BenchLeader Index, inside the ±7.8 margin), and Inkling 2 Small is 1.5× cheaper at $0.475 vs $0.700 per 1M tokens blended. Choose Inkling 2 Small for coding (60 vs 44), agents & tools (61 vs 46), and long context (66 vs 61), where it also streams ~1.5× faster; choose Qwen3.7 Plus for human preference (64 vs 59) and reasoning (54 vs 53).
Key facts (as of 16 Nov 2026)
- Inkling 2 Small scores 57.9 on the BenchLeader Index and Qwen3.7 Plus scores 57.6 (BenchLeader, 16 Nov 2026).
- Inkling 2 Small costs $0.475 per 1M tokens blended (list price, 16 Nov 2026).
- Qwen3.7 Plus costs $0.700 per 1M tokens blended (list price, 16 Nov 2026).
- Inkling 2 Small streams ~1.5× faster than Qwen3.7 Plus (Artificial Analysis, 7-day median, 16 Nov 2026).
- Of the 28 benchmarks both models have, Inkling 2 Small leads 21 (BenchLeader, 16 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 | 60 vs 44 category score; SciCode 52.3% vs 46.1% | High |
| Agents & tool use | Inkling 2 Small | 61 vs 46 category score; τ³-Banking (AA) 40.4% vs 17.5% | High |
| Reasoning | Qwen3.7 Plus | 54 vs 53 category score; Arena Hard Prompts 1473 vs 1438 | Medium |
| Long documents | Inkling 2 Small | 66 vs 61 category score; AA-LCR v1.1 83.3% vs 73.0% | Medium |
| Images and other media | Inkling 2 Small | 64 vs 62 category score; MMMU-Pro 81.6% vs 80.5% | Medium |
| Chat quality (human preference) | Qwen3.7 Plus | 64 vs 59 on Arena votes | Medium |
| Lowest cost | Inkling 2 Small | $0.475 vs $0.700 per 1M blended; agentic coding session $0.022 vs $0.030 | – |
| Fastest first answer | Either | 49.0 s (Inkling 2 Small) vs 49.8 s (Qwen3.7 Plus) 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
- Inkling 2 Small and Qwen3.7 Plus are neck and neck on quality (57.9 vs 57.6, within the ±7.8 margin).
- Inkling 2 Small is stronger in agents & tools, coding, long context, multimodal.
- Qwen3.7 Plus is stronger in human preference, reasoning.
- Inkling 2 Small is 1.5× cheaper ($0.475 vs $0.700 per 1M blended).
- Inkling 2 Small streams 1.7× faster (100 vs 57 tokens per second).
At a glance
| Spec | Inkling 2 Small | Qwen3.7 Plus |
|---|---|---|
| Developer | Thinking Machines | Alibaba |
| Released | 5 Nov 2026 | 2 Jun 2026 |
| Context window (tokens) | 1,048,576 | 1,000,000 |
| Compared at | Inkling 2 Small | Qwen3.7 Plus |
| Open weights | No | No |
| Price in / out / cached input per 1M | $0.300 / $1.00 / $0.030 | $0.400 / $1.60 / $0.080 |
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 Small | Qwen3.7 Plus | Leader |
|---|---|---|---|
| Reasoning | 52.8 | 54.4 | Qwen3.7 Plus |
| Coding | 60.3 | 43.9 | Inkling 2 Small |
| Agents & tools | 61.1 | 45.5 | Inkling 2 Small |
| Maths | – | 64.2 | not comparable |
| Knowledge | 53.5 | – | not comparable |
| Instruction following | – | 75.9 | not comparable |
| Human preference | 58.6 | 64.0 | Qwen3.7 Plus |
| Multimodal | 64.0 | 62.3 | Inkling 2 Small |
| Long context | 66.4 | 61.0 | Inkling 2 Small |
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: Maths, Knowledge, Instruction following.
Where sources disagree
Across the 28 benchmarks both have, Inkling 2 Small leads 21, Qwen3.7 Plus leads 7. Every overall index that rates both puts Qwen3.7 Plus ahead.
| Overall index | Inkling 2 Small | Qwen3.7 Plus | Leader |
|---|---|---|---|
| BenchLeader Index | 57.9 | 57.6 | neck and neck |
| Arena Text | 1412 | 1455 | Qwen3.7 Plus |
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 Small | Qwen3.7 Plus |
|---|---|---|
| Blended price per 1M tokens | $0.475 | $0.700 |
| Input / output per 1M | $0.300 / $1.00 | $0.400 / $1.60 |
| Cached input per 1M | $0.030 | $0.080 |
| Price per task: chat reply | $0.0004 | $0.0006 |
| Price per task: summarize a 30-page report | $0.0042 | $0.0058 |
| Price per task: code edit | $0.0033 | $0.0048 |
| Price per task: agentic coding session | $0.022 | $0.030 |
| Price per task: structured extraction | $0.0008 | $0.0011 |
| Agentic coding session, input mostly cached | $0.0099 | $0.016 |
| Cost per benchmark task (AA Index) | $1.18 | – |
| Output tokens per task (AA Index) | 150k | – |
| Of which reasoning | 88k | – |
| Time per task (AA Index) | 25 min | – |
| Output speed | 100 tok/s | 57 tok/s |
| Time to first answer | 49.0 s | 49.8 s |
| Time to a complete answer, last measured 13 Nov 2026 | 163.6 s | 114.8 s |
Each model is compared at its best-ranked reasoning-effort setting. Inkling 2 Small scores 57.9 and takes 49 s to its first answer token. Qwen3.7 Plus scores 57.6 and takes 50 s to its first answer token. 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
104 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 Small | Qwen3.7 Plus |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 57.9 | 57.6 |
| Agents & tools score | BenchLeader | 61.1 | 45.5 |
| Coding score | BenchLeader | 60.3 | 43.9 |
| Human preference score | BenchLeader | 58.6 | 64.0 |
| Knowledge score | BenchLeader | 53.5 | – |
| Long context score | BenchLeader | 66.4 | 61.0 |
| Multimodal score | BenchLeader | 64.0 | 62.3 |
| Reasoning score | BenchLeader | 52.8 | 54.4 |
| Instruction following score | BenchLeader | – | 75.9 |
| Maths score | BenchLeader | – | 64.2 |
| Blended price $/M | BenchLeader | $0.475 | $0.700 |
| Output speed | BenchLeader | 100 tok/s | 57 tok/s |
| Time to first answer | BenchLeader | 49.0 s | 49.8 s |
| Context window | BenchLeader | 1,048,576 tokens | 1,000,000 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | – | 87.9% |
| Arena Hard Prompts | Arena (LMArena) | 1438 | 1473 |
| GPQA Diamond (AA) | Artificial Analysis | – | 90.0% |
| Humanity's Last Exam (AA) | Artificial Analysis | 44.1% | 35.6% |
| HLE-Diamond (AA) | Artificial Analysis | 28.7% | 13.9% |
| ARC-AGI-1 | ARC Prize | 96.5%† | – |
| ARC-AGI-2 | ARC Prize | 81.7%† | – |
| CritPt | Artificial Analysis | – | 9.1% |
| CritPt v2 hard subset (AA) | Artificial Analysis | 35.0% | – |
| MysteryMechanism | Vals AI | 25.2% | – |
| Arena Expert | Arena (LMArena) | 1488 | 1485 |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | – | 17.0% |
| LMCA | Epoch AI Benchmarking Hub | – | 37.6% |
| DTBench | Epoch AI Benchmarking Hub | – | 84.0% |
| Coding | |||
| SciCode | SciCode | 52.3% | 46.1% |
| FrontierCode | Cognition | – | 10.2% |
| Arena Coding | Arena (LMArena) | 1485 | 1500 |
| Arena WebDev | Arena (LMArena) | 1647 | – |
| Code Migration | Vals AI | – | 12.9% |
| ProgramBench | Vals AI | 0.5% | – |
| SWE-bench Multimodal | Vals AI | 43.1% | – |
| Vibe Code Bench v1.1 | Vals AI | 81.5% | 46.4% |
| 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% | – |
Show all 104 benchmarks
| Metric | Publisher | Inkling 2 Small | Qwen3.7 Plus |
|---|---|---|---|
| Coding | |||
| 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% | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 13.1% | 1.0% |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 81.3% | 61.0% |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | – | 17.7† |
| Design Arena Website | Design Arena | 1335 | 1261 |
| FrontierCode 2.0 (AA) | Artificial Analysis | 25.4% | – |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 13.0%† | – |
| OSWorld-Verified 2.0 | OSWorld | – | 2.8% |
| APEX-Agents | Mercor | 46.8% | – |
| Arena Agent | Arena (LMArena) | 2.5 | -8 |
| Terminal-Bench Hard | Artificial Analysis | – | 47.0% |
| τ²-Bench Telecom (AA) | Artificial Analysis | – | 93.0% |
| Terminal-Bench 2.1 (Vals) | Vals AI | – | 52.8% |
| MCP Atlas | Scale AI SEAL | 85.4% | – |
| GDPval-AA v2.1, normalised score | Artificial Analysis | – | 13.3% |
| GDPval-AA v2.1 | Artificial Analysis | 1630 | 774 |
| τ³-Banking (AA) | Artificial Analysis | 40.4% | 17.5% |
| Analyst Agent (AA) | Artificial Analysis | 51.3% | – |
| APEX-Agents (AA) | Artificial Analysis | – | 22.4% |
| CyberBench | Vals AI | 72.7% | – |
| Finance Agent v2 | Vals AI | – | 38.2% |
| Finance Agent v2.1 | Vals AI | 67.5% | – |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | 21.7% | – |
| Harvey's Legal Agent Benchmark v1 | Vals AI | – | 0.0% |
| Legal Research Bench | Vals AI | 46.6% | 16.4% |
| SkillsBench | Vals AI | – | 54.3% |
| SREBench | Vals AI | 1.9% | – |
| Tax Agent Bench | Vals AI | 38.9% | 10.5% |
| Terminal-Bench 4.0 (Vals) | Vals AI | 12.6% | – |
| Terminal-Bench Science | Vals AI | 2.9% | – |
| Arena Agent Task Completion | Arena (LMArena) | 3.3 | -10.8 |
| AutomationBench | Artificial Analysis | 45.6% | 17.4% |
| GDP.pdf (AA) | Artificial Analysis | 25.2% | 12.2% |
| EnterpriseOps-Gym | Artificial Analysis | 46.8% | 40.6% |
| AA-Briefcase v1.1 | Artificial Analysis | 1527 | 915 |
| Design Arena Agentic | Design Arena | 1315 | – |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 5.7% | – |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | – | 34.4%† |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | – | 93.3% |
| ArXivMath | MathArena | 31.9% | – |
| BrokenArXiv | MathArena | 63.2% | – |
| Arena Maths | Arena (LMArena) | – | 1465 |
| Knowledge | |||
| AA-Omniscience v1.1 | Artificial Analysis | 16.1 | – |
| BioMysteryBench | Vals AI | 70.0% | – |
| Excel Modeling Benchmark | Vals AI | – | 49.4% |
| Excel Modeling Benchmark v1.1 | Vals AI | 69.5% | – |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | 33.8% | – |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 73.3% | – |
| Instruction following | |||
| IFBench | Artificial Analysis | – | 78.0% |
| Arena Instruction Following | Arena (LMArena) | 1410 | 1447 |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1412 | 1455 |
| Arena Creative Writing | Arena (LMArena) | 1345 | 1431 |
| Arena Multi-turn | Arena (LMArena) | 1415 | 1464 |
| Arena Longer Queries | Arena (LMArena) | 1410 | 1465 |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | – | 1277 |
| MMMU-Pro | Artificial Analysis | 81.6% | 80.5% |
| MortgageTax | Vals AI | – | 66.2% |
| SAGE | Vals AI | 88.6% | 89.2% |
| Humanity's Sixth Sense | Scale AI SEAL | 33.3% | – |
| VIALS-AA | Handshake AI | 42.9% | – |
| Code2Video-AA | Artificial Analysis | 1020 | – |
| AA-3D | Artificial Analysis | 1027 | – |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 83.3% | 73.0% |
| Arena Document | Arena (LMArena) | – | 1446 |
| MLCR | Artificial Analysis | 20.6% | 8.9% |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | – | 147.9 |
| AA Intelligence Index v5.0.1 | Artificial Analysis | 30.6 | – |
| AA Intelligence Index v4.3.2 | Artificial Analysis | – | 25.2 |
| AA Progress Index v1 | Artificial Analysis | – | 283.9 |
| Vals Index | Vals AI | 56.1 | – |
| Vals Finance Index | Vals AI | 61.5% | – |
| Vals Science Index | Vals AI | 32.7% | – |
| Vals Multimodal Index | Vals AI | – | 53.9% |
| 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 2026-11-16. Best configuration of each model; every score links to its source on the model pages.
DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
What changed
- 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.
- Inkling 2 Small: 3 new results (SciCode, APEX-Agents, MLCR).
- Inkling 2 Small: 8 new results (Arena Text, Arena Hard Prompts, Arena Coding…); 2 score revisions.
- Inkling 2 Small: BenchLeader Index 57.5 → 58.4.
- Inkling 2 Small: 1 new result (Arena WebDev).
- Qwen3.7 Plus: 1 score revision.
Related comparisons
- Inkling 2 Small vs Gemini 4 Carbon
- Inkling 2 Small vs Claude Opus 5.5
- Inkling 2 Small vs GPT-6 Astra
- Qwen3.7 Plus vs Claude Opus 5.5
- Qwen3.7 Plus vs GPT-6 Astra
- Qwen3.7 Plus vs GPT-5.6 Sol
- 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 Small vs Qwen3.7 Plus: questions
- Is Inkling 2 Small better than Qwen3.7 Plus?
- Inkling 2 Small and Qwen3.7 Plus are neck and neck on quality (57.9 vs 57.6, within the ±7.8 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 16 Nov 2026, so check the category scores for your use.
- Inkling 2 Small vs Qwen3.7 Plus: which is cheaper, and will that change?
- Inkling 2 Small is cheaper today: $0.475 against $0.700 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is Inkling 2 Small or Qwen3.7 Plus better for coding?
- Inkling 2 Small scores higher in coding (60 vs 44 on the category index, where 50 is average). On SciCode, the top shared coding benchmark, it is 52.3% for Inkling 2 Small against 46.1% for Qwen3.7 Plus.
- Which is faster, Inkling 2 Small or Qwen3.7 Plus?
- Inkling 2 Small streams ~1.5× faster (100 vs 57 output tokens per second, Artificial Analysis 7-day median).
- Is Inkling 2 Small or Qwen3.7 Plus better for agents and tool use?
- Inkling 2 Small scores higher in agentic tasks (61 vs 46 on the category index, where 50 is average). On τ³-Banking (AA), the top shared agents & tools benchmark, it is 40.4% for Inkling 2 Small against 17.5% for Qwen3.7 Plus.
More questions (4)
- Which is better for long documents?
- Inkling 2 Small scores higher on long-context benchmarks (66 vs 61). Both take about 1M tokens: Inkling 2 Small 1,048,576, Qwen3.7 Plus 1,000,000.
- Which has lower latency?
- Inkling 2 Small answers first: 49.0 s against 49.8 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.
- Do independent benchmarks agree on Inkling 2 Small vs Qwen3.7 Plus?
- Across the 28 benchmarks both have, Inkling 2 Small leads 21, Qwen3.7 Plus leads 7. Every overall index that rates both puts Qwen3.7 Plus ahead.
- When was Inkling 2 Small released?
- Inkling 2 Small was released on 5 Nov 2026.