Gemma 4 31B vs Inkling 2 Small
Inkling 2 Small leads Gemma 4 31B on coding, 48.9 to 21.9 on the Vibe Coding Index, and Gemma 4 31B costs 2.5x less per output token ($0.40 vs $1.00 per million). Updated November 14, 2026; 31 benchmarks have a result for both.
Gemma 4 31B or Inkling 2 Small: which to pick
Pick Inkling 2 Small for coding: it scores 48.9 on the Vibe Coding Index against 21.9 for Gemma 4 31B.
Pick Gemma 4 31B for output tokens 2.5x cheaper ($0.40 vs $1.00 per million) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.
- Shared results
- 31
- Gemma 4 31B only
- 48
- Inkling 2 Small only
- 20
- Like-for-like categories
- 5 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
Inkling 2 Small
Inkling 2 Small scores 48.9 against 21.9.
2 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
Inkling 2 Small
Inkling 2 Small leads, 30.6 against 4.4.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Gemma 4 31B has a AA Agentic Index result, 4.2.
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 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemma 4 31B
Gemma 4 31B $0.0003, Inkling 2 Small $0.0008 per turn.
List prices
At a glance
- Coding index
- Gemma 4 31B 21.9 from 2 benchmarks, Inkling 2 Small 48.9 from 3 benchmarks.
- Widest category
- Intelligence, 26.2 points apart on average over 1 shared benchmark.
- Widest single gap
- GDPval-AA: Gemma 4 31B 627 against Inkling 2 Small 1630, 69.2 points apart on a 0 to 100 scale.
- Output price
- Gemma 4 31B $0.40 against Inkling 2 Small $1.00 per million output tokens, 2.5x apart.
- Context window
- Gemma 4 31B takes 262K 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 | Gemma 4 31B | Bars | Inkling 2 Small | Ties |
|---|---|---|---|---|
| Coding | 2 | 6 | ||
| Intelligence | 0 | 1 | ||
| Reasoning | 2 | 4 | ||
| Knowledge | 2 | 1 | ||
| General | 10 | 3 | ||
| All shared boards | 16 | 15 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index26
| Benchmark | Gemma 4 31B | Inkling 2 Small | Leader |
|---|---|---|---|
| LiveBench coding | 20.3% | Not measured | Only Gemma 4 31B measured |
| LMArena WebDev | 1370 | 1647 | Inkling 2 Small |
| AA Coding Index | 43.4 | Not measured | Only Gemma 4 31B measured |
| Terminal-Bench 4 (Vals AI) | Not measured | 12.6% | Only Inkling 2 Small measured |
| Vibe Code Bench (Vals AI) | Not measured | 81.5% | Only Inkling 2 Small measured |
| ProgramBench (Vals AI) | Not measured | 0.5% | Only Inkling 2 Small measured |
| SWE-bench Multimodal (Vals AI) | Not measured | 43.1% | Only Inkling 2 Small measured |
| CyberBench (Vals AI) | Not measured | 72.7% | Only Inkling 2 Small measured |
| SciCode | 45.5% | 52.3% | Inkling 2 Small |
| Terminal-Bench Hard (Artificial Analysis run) | 36.4% | Not measured | Only Gemma 4 31B measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | 0.0% | 13.1% | Inkling 2 Small |
| FrontierCode 2.0 | 0.0% | 25.4% | Inkling 2 Small |
| WeirdML | 52.3% | Not measured | Only Gemma 4 31B measured |
| ALE-Bench | 925.5 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: coding | 1459 | 1455 | Gemma 4 31B |
| LMArena Text: software and IT | 1463 | 1443 | Gemma 4 31B |
| LMArena WebDev: React | 1362 | 1660 | Inkling 2 Small |
| LMArena WebDev: HTML | 1380 | 1661 | Inkling 2 Small |
| SciCode | 8.9% | Not measured | Only Gemma 4 31B measured |
| SWE-Bench Pro V2 | Not measured | 97.7% | Only Inkling 2 Small measured |
| GameBench 2 | 35.1 | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 31 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Gemma 4 31B | Inkling 2 Small | Leader |
|---|---|---|---|
| AA Intelligence Index | 4.4 | 30.6 | Inkling 2 Small |
| Epoch Capabilities Index | 144.3 | Not measured | Only Gemma 4 31B measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index14 boards, none shared
| Benchmark | Gemma 4 31B | Inkling 2 Small | Leader |
|---|---|---|---|
| AA Agentic Index | 4.2 | Not measured | Only Gemma 4 31B measured |
| LiveBench research | 38.1% | Not measured | Only Gemma 4 31B measured |
| LiveBench browser | 0.0% | Not measured | Only Gemma 4 31B measured |
| LiveBench long agentic | 8.5% | Not measured | Only Gemma 4 31B measured |
| SREBench (Vals AI) | Not measured | 1.9% | Only Inkling 2 Small measured |
| Tax Agent Bench (Vals AI) | Not measured | 38.9% | Only Inkling 2 Small measured |
| Legal Research Bench (Vals AI) | Not measured | 46.6% | Only Inkling 2 Small measured |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 21.7% | Only Inkling 2 Small measured |
| BioMysteryBench (Vals AI) | Not measured | 70.0% | Only Inkling 2 Small measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 2.9% | Only Inkling 2 Small measured |
| Vals Science Index | Not measured | 32.7% | Only Inkling 2 Small measured |
| τ²-Bench Telecom | 65.5% | Not measured | Only Gemma 4 31B measured |
| APEX-Agents | Not measured | 46.8% | Only Inkling 2 Small measured |
| MCP Atlas | Not measured | 85.4% | Only Inkling 2 Small measured |
| Neither model has a result on the other 30 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index24
| Benchmark | Gemma 4 31B | Inkling 2 Small | Leader |
|---|---|---|---|
| LiveBench reasoning | 68.3% | Not measured | Only Gemma 4 31B measured |
| MysteryMechanism (Vals AI) | Not measured | 25.2% | Only Inkling 2 Small measured |
| GPQA Diamond (Artificial Analysis run) | 85.7% | Not measured | Only Gemma 4 31B measured |
| Humanity's Last Exam (Artificial Analysis run) | 23.6% | 44.1% | Inkling 2 Small |
| HLE-Diamond (Artificial Analysis run) | 7.2% | 28.7% | Inkling 2 Small |
| CritPt v2, hard subset (Artificial Analysis run) | 4.0% | 35.0% | Inkling 2 Small |
| GPQA Diamond (Epoch AI run) | 75.8% | Not measured | Only Gemma 4 31B measured |
| ARC-AGI | Not measured | 96.5% | Only Inkling 2 Small measured |
| ARC-AGI-2 | Not measured | 81.7% | Only Inkling 2 Small measured |
| LMArena Text: hard prompts | 1447 | 1421 | Gemma 4 31B |
| LMArena Text: expert | 1465 | 1478 | Inkling 2 Small |
| LMArena Text: hard prompts in English | 1456 | 1424 | Gemma 4 31B |
| LMArena Vision: diagrams | 1286 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: homework | 1310 | Not measured | Only Gemma 4 31B measured |
| Kagi LLM Benchmark | 63.5% | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 11 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | Gemma 4 31B | Inkling 2 Small | Leader |
|---|---|---|---|
| OTIS Mock AIME | 73.3% | Not measured | Only Gemma 4 31B measured |
| LMArena Text: math | 1462 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: mathematical work | 1464 | Not measured | Only Gemma 4 31B measured |
| MathArena | Not measured | 42.4% | Only Inkling 2 Small measured |
| Neither model has a result on the other 10 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | Gemma 4 31B | Inkling 2 Small | Leader |
|---|---|---|---|
| CaseLaw (Vals AI) | 52.6% | Not measured | Only Gemma 4 31B measured |
| MortgageTax (Vals AI) | 61.4% | Not measured | Only Gemma 4 31B measured |
| AA-Omniscience | -48.5 | 16.1 | Inkling 2 Small |
| SimpleQA Verified | 10.4% | Not measured | Only Gemma 4 31B measured |
| LMArena Text: science | 1456 | 1409 | Gemma 4 31B |
| LMArena Text: medicine and healthcare | 1450 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: legal and government | 1438 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: business and finance | 1431 | 1415 | Gemma 4 31B |
| FACTS Benchmark Suite | 50.1% | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 12 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Gemma 4 31B | Inkling 2 Small | Leader |
|---|---|---|---|
| LiveBench design | 56.5% | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 8 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index103
| Benchmark | Gemma 4 31B | Inkling 2 Small | Leader |
|---|---|---|---|
| Vals Index | Not measured | 56.1% | Only Inkling 2 Small measured |
| LiveBench data analysis | 53.3% | Not measured | Only Gemma 4 31B measured |
| SAGE (Vals AI) | 82.8% | 88.6% | Inkling 2 Small |
| IFBench | 75.6% | Not measured | Only Gemma 4 31B measured |
| Long context reasoning (AA-LCR) | 69.7% | 83.3% | Inkling 2 Small |
| GDPval-AA | 627 | 1630 | Inkling 2 Small |
| DTBench | 82.7% | Not measured | Only Gemma 4 31B measured |
| LMCA | 39.3% | Not measured | Only Gemma 4 31B measured |
| Surface Evolver Bench | 30.6% | Not measured | Only Gemma 4 31B measured |
| LMArena Text | 1443 | 1403 | Gemma 4 31B |
| LMArena Text: instruction following | 1433 | 1408 | Gemma 4 31B |
| LMArena Text: creative writing | 1415 | 1348 | Gemma 4 31B |
| LMArena Vision | 1279 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: English | 1451 | 1418 | Gemma 4 31B |
| LMArena Text: non-English | 1430 | 1390 | Gemma 4 31B |
| LMArena Text: Chinese | 1476 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: French | 1434 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: Spanish | 1444 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: Russian | 1460 | 1377 | Gemma 4 31B |
| LMArena Text: Polish | 1431 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: multi-turn | 1452 | 1408 | Gemma 4 31B |
| LMArena Text: longer queries | 1445 | 1403 | Gemma 4 31B |
| LMArena Text: writing and language | 1431 | 1381 | Gemma 4 31B |
| LMArena Text: entertainment and media | 1405 | 1359 | Gemma 4 31B |
| LMArena Vision: English | 1272 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: Chinese | 1327 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: reading text | 1285 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: humor | 1280 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: captioning | 1209 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: recognizing things | 1227 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: creative writing | 1286 | Not measured | Only Gemma 4 31B measured |
| LMArena Document | 1434 | Not measured | Only Gemma 4 31B measured |
| EQ-Bench 4 | 1110 | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 16 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemma 4 31B | 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
Gemma 4 31B costs less
Repository review
50K input + 3K output tokens
Gemma 4 31B costs less
Agent loop
200K input + 10K output tokens
Gemma 4 31B 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 | Google Gemma 4 31B | Thinking Machines Inkling 2 Small |
|---|---|---|
| Maker | Thinking Machines | |
| Weights | Open weights | Open weights |
| Released | April 2, 2026 | November 9, 2026 |
| Context window | 262K | 1.05M |
| Input $/Mtok | $0.14 | $0.30 |
| Output $/Mtok | $0.40 | $1.00 |
| Coding index | 21.9 | 48.9 |
| Independent measurements behind it | 2 | 3 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemma 4 31B better than Inkling 2 Small for coding?
Pick Inkling 2 Small for coding: it scores 48.9 on the Vibe Coding Index against 21.9 for Gemma 4 31B. Pick Gemma 4 31B for output tokens 2.5x cheaper ($0.40 vs $1.00 per million) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.
Which is cheaper, Gemma 4 31B or Inkling 2 Small?
Gemma 4 31B costs $0.14 per million input tokens and $0.40 per million output tokens; Inkling 2 Small costs $0.30 and $1.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Gemma 4 31B or Inkling 2 Small?
Inkling 2 Small, with 1.05M tokens against 262K.
How many benchmarks is the Gemma 4 31B vs Inkling 2 Small comparison based on?
31 benchmarks have a result for both models as of November 14, 2026. Gemma 4 31B's coding index rests on 2 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.