Qwen3.8 Max (0902) vs Inkling 2 Small
Qwen3.8 Max (0902) leads Inkling 2 Small on coding, 67.3 to 48.9 on the Vibe Coding Index, and Inkling 2 Small costs 6.0x less per output token ($1.00 vs $6.00 per million). Updated November 14, 2026; 44 benchmarks have a result for both.
vs boards won of 44 shared
Qwen3.8 Max (0902) or Inkling 2 Small: which to pick
Pick Qwen3.8 Max (0902) for coding: it scores 67.3 on the Vibe Coding Index against 48.9 for Inkling 2 Small.
Pick Inkling 2 Small for output tokens 6.0x cheaper ($1.00 vs $6.00 per million) and a larger context window (1.05M against 1M tokens).
Model AQwen3.8 Max (0902)Qwen67.3/1005 independent benchmarks$1.32 per solved taskModel BInkling 2 SmallThinking Machines48.9/1003 independent benchmarksNo cost per solved task
- Shared results
- 44
- Qwen3.8 Max (0902) only
- 84
- Inkling 2 Small only
- 7
- Like-for-like categories
- 7 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
Qwen3.8 Max (0902)
Qwen3.8 Max (0902) scores 67.3 against 48.9.
5 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
Qwen3.8 Max (0902)
Qwen3.8 Max (0902) leads, 33.7 against 30.6.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Qwen3.8 Max (0902) has a AA Agentic Index result, 56.0.
Directional only
Reasoning
GPQA Diamond
No call
Only Qwen3.8 Max (0902) has a GPQA Diamond result, 93.7%.
Directional only
Knowledge
MMLU Pro
No call
Only Qwen3.8 Max (0902) has a MMLU Pro result, 88.6%.
Directional only
Web design
Design Arena: websites
No call
Only Qwen3.8 Max (0902) has a Design Arena: websites result, 1269.
Directional only
General
Vals Index
Qwen3.8 Max (0902)
Qwen3.8 Max (0902) leads, 59.1% against 56.1%.
Same board, both measured
Long documents
Listed context window
Inkling 2 Small
Inkling 2 Small takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Inkling 2 Small
Qwen3.8 Max (0902) $0.0050, Inkling 2 Small $0.0008 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Qwen3.8 Max (0902) has the number, $1.32.
Directional only
At a glance
- Coding index
- Qwen3.8 Max (0902) 67.3 from 5 benchmarks, Inkling 2 Small 48.9 from 3 benchmarks.
- Widest category
- General, 12.5 points apart on average over 14 shared benchmarks.
- Widest single gap
- CyberBench (Vals AI): Qwen3.8 Max (0902) 28.6% against Inkling 2 Small 72.7%, 44.2 points apart on a 0 to 100 scale.
- Output price
- Qwen3.8 Max (0902) $6.00 against Inkling 2 Small $1.00 per million output tokens, 6.0x apart.
- Context window
- Qwen3.8 Max (0902) takes 1M tokens, Inkling 2 Small 1.05M.
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 | Qwen3.8 Max (0902) | Bars | Inkling 2 Small | Ties |
|---|---|---|---|---|
| Coding | 7 | 6 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 4 | 1 | ||
| Reasoning | 3 | 4 | ||
| Math | 1 | 0 | ||
| Knowledge | 2 | 1 | ||
| General | 12 | 2 | ||
| All shared boards | 30 | 14 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index76
| Benchmark | Qwen3.8 Max (0902) | Inkling 2 Small | Leader |
|---|---|---|---|
| LiveBench coding | 60.9% | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena WebDev | 1676 | 1647 | Qwen3.8 Max (0902) |
| AA Coding Index | 76.2 | Not measured | Only Qwen3.8 Max (0902) measured |
| LiveCodeBench (Vals AI) | 87.8% | Not measured | Only Qwen3.8 Max (0902) measured |
| SWE-bench Verified (Vals AI) | 85.6% | Not measured | Only Qwen3.8 Max (0902) measured |
| Terminal-Bench 4 (Vals AI) | 38.9% | 12.6% | Qwen3.8 Max (0902) |
| Vibe Code Bench (Vals AI) | 77.1% | 81.5% | Inkling 2 Small |
| Code migration (Vals AI) | 24.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| ProgramBench (Vals AI) | 0.0% | 0.5% | Inkling 2 Small |
| IOI (Vals AI) | 68.9% | Not measured | Only Qwen3.8 Max (0902) measured |
| Terminal-Bench 2.1 (Vals AI) | 67.4% | Not measured | Only Qwen3.8 Max (0902) measured |
| SWE-bench Multimodal (Vals AI) | 42.5% | 43.1% | Inkling 2 Small |
| Vibe Code Bench 1-100 (Vals AI) | 24.8% | Not measured | Only Qwen3.8 Max (0902) measured |
| SkillsBench (Vals AI) | 42.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| CyberBench (Vals AI) | 28.6% | 72.7% | Inkling 2 Small |
| SciCode | 53.2% | 52.3% | Qwen3.8 Max (0902) |
| Terminal-Bench 4.0 (Artificial Analysis run) | 38.9% | 13.1% | Qwen3.8 Max (0902) |
| FrontierCode 2.0 | 23.4% | 25.4% | Inkling 2 Small |
| FrontierSWE | 17.8% | Not measured | Only Qwen3.8 Max (0902) measured |
| MirrorCode | 52.2% | Not measured | Only Qwen3.8 Max (0902) measured |
| ALE-Bench | 1679.1 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: coding | 1502 | 1455 | Qwen3.8 Max (0902) |
| LMArena Text: software and IT | 1500 | 1443 | Qwen3.8 Max (0902) |
| LMArena WebDev: React | 1698 | 1660 | Qwen3.8 Max (0902) |
| LMArena WebDev: HTML | 1654 | 1661 | Inkling 2 Small |
| LMArena WebDev: from an image | 1638 | Not measured | Only Qwen3.8 Max (0902) measured |
| SWE-Bench Pro V2 | Not measured | 97.7% | Only Inkling 2 Small measured |
| GameBench 2 | 69.6 | Not measured | Only Qwen3.8 Max (0902) measured |
| Terminal-Bench 4.0 | 27.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| Neither model has a result on the other 23 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Qwen3.8 Max (0902) | Inkling 2 Small | Leader |
|---|---|---|---|
| AA Intelligence Index | 33.7 | 30.6 | Qwen3.8 Max (0902) |
| Epoch Capabilities Index | 157.6 | Not measured | Only Qwen3.8 Max (0902) measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index41
| Benchmark | Qwen3.8 Max (0902) | Inkling 2 Small | Leader |
|---|---|---|---|
| AA Agentic Index | 56.0 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building web apps | 1278 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building full-stack apps | 1279 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building mobile apps | 1223 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building Android apps | 1196 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building Godot games | 1215 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: PowerPoint slides | 1252 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: spreadsheets | 1011 | Not measured | Only Qwen3.8 Max (0902) measured |
| LiveBench research | 72.8% | Not measured | Only Qwen3.8 Max (0902) measured |
| LiveBench browser | 49.4% | Not measured | Only Qwen3.8 Max (0902) measured |
| LiveBench long agentic | 26.6% | Not measured | Only Qwen3.8 Max (0902) measured |
| SREBench (Vals AI) | Not measured | 1.9% | Only Inkling 2 Small measured |
| Finance Agent (Vals AI) | 57.9% | Not measured | Only Qwen3.8 Max (0902) measured |
| Tax Agent Bench (Vals AI) | 49.7% | 38.9% | Qwen3.8 Max (0902) |
| Legal Research Bench (Vals AI) | 47.6% | 46.6% | Qwen3.8 Max (0902) |
| Harvey's Legal Agent Benchmark (Vals AI) | 15.4% | 21.7% | Inkling 2 Small |
| Excel Modeling Benchmark (Vals AI) | 72.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| BioMysteryBench (Vals AI) | Not measured | 70.0% | Only Inkling 2 Small measured |
| Terminal-Bench-Science (Vals AI) | 12.9% | 2.9% | Qwen3.8 Max (0902) |
| Vals Science Index | Not measured | 32.7% | Only Inkling 2 Small measured |
| APEX-Agents | 63.3% | 46.8% | Qwen3.8 Max (0902) |
| LMArena Search | 1260 | Not measured | Only Qwen3.8 Max (0902) measured |
| MCP Atlas | Not measured | 85.4% | Only Inkling 2 Small measured |
| τ³-Banking | 55.2% | Not measured | Only Qwen3.8 Max (0902) measured |
| Neither model has a result on the other 20 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index34
| Benchmark | Qwen3.8 Max (0902) | Inkling 2 Small | Leader |
|---|---|---|---|
| GPQA Diamond | 93.7% | Not measured | Only Qwen3.8 Max (0902) measured |
| LiveBench reasoning | 88.2% | Not measured | Only Qwen3.8 Max (0902) measured |
| MysteryMechanism (Vals AI) | 23.9% | 25.2% | Inkling 2 Small |
| MMMU Pro (Vals AI) | 88.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| GPQA Diamond (Artificial Analysis run) | 92.8% | Not measured | Only Qwen3.8 Max (0902) measured |
| Humanity's Last Exam (Artificial Analysis run) | 43.1% | 44.1% | Inkling 2 Small |
| HLE-Diamond (Artificial Analysis run) | 24.0% | 28.7% | Inkling 2 Small |
| CritPt v2, hard subset (Artificial Analysis run) | 29.5% | 35.0% | Inkling 2 Small |
| GPQA Diamond (Epoch AI run) | 92.7% | Not measured | Only Qwen3.8 Max (0902) measured |
| ARC-AGI | Not measured | 96.5% | Only Inkling 2 Small measured |
| ARC-AGI-2 | Not measured | 81.7% | Only Inkling 2 Small measured |
| Chess puzzles | 46.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| Mystery game puzzles | 38.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: hard prompts | 1499 | 1421 | Qwen3.8 Max (0902) |
| LMArena Text: expert | 1510 | 1478 | Qwen3.8 Max (0902) |
| LMArena Text: hard prompts in English | 1505 | 1424 | Qwen3.8 Max (0902) |
| LMArena Vision: diagrams | 1321 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Vision: homework | 1335 | Not measured | Only Qwen3.8 Max (0902) measured |
| Neither model has a result on the other 8 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Qwen3.8 Max (0902) | Inkling 2 Small | Leader |
|---|---|---|---|
| OTIS Mock AIME | 100.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| FrontierMath, tiers 1 to 3 | 74.7% | Not measured | Only Qwen3.8 Max (0902) measured |
| FrontierMath, tier 4 | 46.3% | Not measured | Only Qwen3.8 Max (0902) measured |
| ProofBench | 58.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: math | 1509 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: mathematical work | 1497 | Not measured | Only Qwen3.8 Max (0902) measured |
| MathArena | 47.1% | 42.4% | Qwen3.8 Max (0902) |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | Qwen3.8 Max (0902) | Inkling 2 Small | Leader |
|---|---|---|---|
| MMLU Pro | 88.6% | Not measured | Only Qwen3.8 Max (0902) measured |
| LegalBench (Vals AI) | 83.6% | Not measured | Only Qwen3.8 Max (0902) measured |
| CorpFin (Vals AI) | 65.8% | Not measured | Only Qwen3.8 Max (0902) measured |
| TaxEval (Vals AI) | 75.5% | Not measured | Only Qwen3.8 Max (0902) measured |
| MortgageTax (Vals AI) | 64.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| MedCode (Vals AI) | 40.7% | Not measured | Only Qwen3.8 Max (0902) measured |
| AA-Omniscience | 10.5 | 16.1 | Inkling 2 Small |
| SimpleQA Verified | 47.3% | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: science | 1514 | 1409 | Qwen3.8 Max (0902) |
| LMArena Text: medicine and healthcare | 1514 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: legal and government | 1498 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: business and finance | 1481 | 1415 | Qwen3.8 Max (0902) |
| FACTS Benchmark Suite | 60.3% | Not measured | Only Qwen3.8 Max (0902) measured |
| Neither model has a result on the other 8 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Qwen3.8 Max (0902) | Inkling 2 Small | Leader |
|---|---|---|---|
| Design Arena: websites | 1269 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: UI components | 1335 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: game dev | 1310 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: data viz | 1281 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: 3D | 1318 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: all code categories | 1287 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: ASCII art | 1189 | Not measured | Only Qwen3.8 Max (0902) measured |
| LiveBench design | 76.6% | Not measured | Only Qwen3.8 Max (0902) measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index122
| Benchmark | Qwen3.8 Max (0902) | Inkling 2 Small | Leader |
|---|---|---|---|
| Vals Index | 59.1% | 56.1% | Qwen3.8 Max (0902) |
| LiveBench data analysis | 78.4% | Not measured | Only Qwen3.8 Max (0902) measured |
| Public Benefits Bench (Vals AI) | 67.1% | Not measured | Only Qwen3.8 Max (0902) measured |
| SAGE (Vals AI) | 81.8% | 88.6% | Inkling 2 Small |
| MedScribe (Vals AI) | 85.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| Vals Multimodal Index | 65.4% | Not measured | Only Qwen3.8 Max (0902) measured |
| Long context reasoning (AA-LCR) | 80.3% | 83.3% | Inkling 2 Small |
| GDPval-AA | 1674 | 1630 | Qwen3.8 Max (0902) |
| DTBench | 92.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| LMCA | 46.2% | Not measured | Only Qwen3.8 Max (0902) measured |
| Furniture assembly | 20.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text | 1485 | 1403 | Qwen3.8 Max (0902) |
| LMArena Text: instruction following | 1483 | 1408 | Qwen3.8 Max (0902) |
| LMArena Text: creative writing | 1482 | 1348 | Qwen3.8 Max (0902) |
| LMArena Vision | 1312 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: English | 1494 | 1418 | Qwen3.8 Max (0902) |
| LMArena Text: non-English | 1475 | 1390 | Qwen3.8 Max (0902) |
| LMArena Text: Chinese | 1543 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: German | 1475 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: Japanese | 1463 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: Korean | 1455 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: French | 1504 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: Spanish | 1494 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: Russian | 1488 | 1377 | Qwen3.8 Max (0902) |
| LMArena Text: Polish | 1477 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: multi-turn | 1492 | 1408 | Qwen3.8 Max (0902) |
| LMArena Text: longer queries | 1493 | 1403 | Qwen3.8 Max (0902) |
| LMArena Text: writing and language | 1480 | 1381 | Qwen3.8 Max (0902) |
| LMArena Text: entertainment and media | 1470 | 1359 | Qwen3.8 Max (0902) |
| LMArena Vision: English | 1310 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Vision: Chinese | 1353 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Vision: reading text | 1322 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Vision: humor | 1309 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Vision: creative writing | 1310 | Not measured | Only Qwen3.8 Max (0902) measured |
| Neither model has a result on the other 15 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Qwen3.8 Max (0902) | Inkling 2 Small | 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
Qwen3.8 Max (0902)$0.0050Fits in one request
Inkling 2 Small$0.0008Fits in one request
Inkling 2 Small costs less
Repository review
50K input + 3K output tokens
Qwen3.8 Max (0902)$0.118Fits in one request
Inkling 2 Small$0.018Fits in one request
Inkling 2 Small costs less
Agent loop
200K input + 10K output tokens
Qwen3.8 Max (0902)$0.460Fits in one request
Inkling 2 Small$0.070Fits in one request
Inkling 2 Small 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 | Qwen3.8 Max (0902) | Thinking Machines Inkling 2 Small |
|---|---|---|
| Maker | Qwen | Thinking Machines |
| Weights | No public weights listed | Open weights |
| Released | September 3, 2026 | November 9, 2026 |
| Context window | 1M | 1.05M |
| Input $/Mtok | $2.00 | $0.30 |
| Output $/Mtok | $6.00 | $1.00 |
| Coding index | 67.3 | 48.9 |
| Independent measurements behind it | 5 | 3 |
| Cost per solved task | $1.32 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Qwen3.8 Max (0902) better than Inkling 2 Small for coding?
Pick Qwen3.8 Max (0902) for coding: it scores 67.3 on the Vibe Coding Index against 48.9 for Inkling 2 Small. Pick Inkling 2 Small for output tokens 6.0x cheaper ($1.00 vs $6.00 per million) and a larger context window (1.05M against 1M tokens).
Which is cheaper, Qwen3.8 Max (0902) or Inkling 2 Small?
Qwen3.8 Max (0902) costs $2.00 per million input tokens and $6.00 per million output tokens; Inkling 2 Small costs $0.30 and $1.00. Cost per solved task is known for Qwen3.8 Max (0902) only.
Which has the bigger context window, Qwen3.8 Max (0902) or Inkling 2 Small?
Inkling 2 Small, with 1.05M tokens against 1M.
How many benchmarks is the Qwen3.8 Max (0902) vs Inkling 2 Small comparison based on?
44 benchmarks have a result for both models as of November 14, 2026. Qwen3.8 Max (0902)'s coding index rests on 5 independent benchmarks and Inkling 2 Small's on 3. Where only one model has a result, the page says so instead of naming a winner.