Gemini 3.5 Flash Lite vs Inkling
Gemini 3.5 Flash Lite leads Inkling on coding, 49.0 to 31.5 on the Vibe Coding Index, and Gemini 3.5 Flash Lite costs 1.6x less per output token ($2.50 vs $4.05 per million). Updated October 22, 2026; 73 benchmarks have a result for both.
Gemini 3.5 Flash Lite or Inkling: which to pick
Pick Gemini 3.5 Flash Lite for coding: it scores 49.0 on the Vibe Coding Index against 31.5 for Inkling, though on 3 benchmarks against 6.
Pick Inkling for work measured by AA Coding Index or LiveCodeBench (Vals AI), where it leads.
- Shared results
- 73
- Gemini 3.5 Flash Lite only
- 12
- Inkling only
- 29
- 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
Gemini 3.5 Flash Lite
Gemini 3.5 Flash Lite scores 49.0 against 31.5.
3 and 6 benchmarks behind the scores
Intelligence
AA Intelligence Index
Inkling
Inkling leads, 25.0 against 22.2.
Same board, both measured
Agentic work
AA Agentic Index
Inkling
Inkling leads, 22.5 against 14.3.
Same board, both measured
Reasoning
GPQA Diamond
Inkling
Inkling leads, 87.1% against 83.8%.
Same board, both measured
Knowledge
MMLU Pro
Inkling
Inkling leads, 86.3% against 85.8%.
Same board, both measured
Web design
Design Arena: websites
No call
Only Inkling has a Design Arena: websites result, 1224.
Directional only
General
Vals Index
No call
Only Inkling has a Vals Index result, 29.0%.
Directional only
Long documents
Listed context window
Gemini 3.5 Flash Lite
Gemini 3.5 Flash Lite takes 1.05M tokens against 524K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemini 3.5 Flash Lite
Gemini 3.5 Flash Lite $0.0015, Inkling $0.0030 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Gemini 3.5 Flash Lite
Gemini 3.5 Flash Lite $0.41, Inkling $0.76.
Published attempt cost and pass rate
At a glance
- Coding index
- Gemini 3.5 Flash Lite 49.0 from 3 benchmarks, Inkling 31.5 from 6 benchmarks.
- Widest category
- Math, 9.2 points apart on average over 6 shared benchmarks.
- Widest single gap
- ARC-AGI-2: Gemini 3.5 Flash Lite 10.3% against Inkling 36.5%, 26.3 points apart on a 0 to 100 scale.
- Output price
- Gemini 3.5 Flash Lite $2.50 against Inkling $4.05 per million output tokens, 1.6x apart.
- Context window
- Gemini 3.5 Flash Lite takes 1.05M tokens, Inkling 524K.
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 | Gemini 3.5 Flash Lite | Bars | Inkling | Ties |
|---|---|---|---|---|
| Coding | 5 | 9 | 1 tie | |
| Intelligence | 0 | 2 | ||
| Agentic work | 2 | 4 | ||
| Reasoning | 1 | 9 | 1 tie | |
| Math | 1 | 5 | ||
| Knowledge | 3 | 7 | ||
| General | 10 | 13 | ||
| All shared boards | 22 | 49 | 2 ties |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index59
| Benchmark | Gemini 3.5 Flash Lite | Inkling | Leader |
|---|---|---|---|
| LiveBench coding | Not measured | 64.0% | Only Inkling measured |
| LMArena WebDev | 1435 | 1414 | Gemini 3.5 Flash Lite |
| AA Coding Index | 49.3 | 52.1 | Inkling |
| LiveCodeBench (Vals AI) | 79.0% | 85.5% | Inkling |
| SWE-bench Verified (Vals AI) | 75.0% | 77.6% | Inkling |
| Terminal-Bench 4 (Vals AI) | Not measured | 0.5% | Only Inkling measured |
| Vibe Code Bench (Vals AI) | 37.2% | 19.2% | Gemini 3.5 Flash Lite |
| Code migration (Vals AI) | 6.2% | 11.8% | Inkling |
| ProgramBench (Vals AI) | 0.0% | 0.0% | Tie |
| IOI (Vals AI) | Not measured | 14.9% | Only Inkling measured |
| Terminal-Bench 2.1 (Vals AI) | 50.2% | 47.6% | Gemini 3.5 Flash Lite |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 7.3% | Only Inkling measured |
| SkillsBench (Vals AI) | Not measured | 26.1% | Only Inkling measured |
| CyberBench (Vals AI) | 59.1% | 66.8% | Inkling |
| SciCode | 41.3% | 47.0% | Inkling |
| FrontierCode | Not measured | 14.0% | Only Inkling measured |
| FrontierSWE | Not measured | 4.1% | Only Inkling measured |
| WeirdML | 39.0% | 32.3% | Gemini 3.5 Flash Lite |
| ALE-Bench | 765.3 | 946.0 | Inkling |
| LMArena Text: coding | 1453 | 1466 | Inkling |
| LMArena Text: software and IT | 1451 | 1465 | Inkling |
| LMArena WebDev: React | 1408 | 1404 | Gemini 3.5 Flash Lite |
| LMArena WebDev: HTML | Not measured | 1399 | Only Inkling measured |
| LMArena WebDev: from an image | 1448 | Not measured | Only Gemini 3.5 Flash Lite measured |
| SciCode | 6.2% | Not measured | Only Gemini 3.5 Flash Lite measured |
| Neither model has a result on the other 14 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Gemini 3.5 Flash Lite | Inkling | Leader |
|---|---|---|---|
| AA Intelligence Index | 22.2 | 25.0 | Inkling |
| Epoch Capabilities Index | 144.9 | 148.4 | Inkling |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index24
| Benchmark | Gemini 3.5 Flash Lite | Inkling | Leader |
|---|---|---|---|
| AA Agentic Index | 14.3 | 22.5 | Inkling |
| Design Arena: agents building web apps | Not measured | 1196 | Only Inkling measured |
| LiveBench research | Not measured | 59.9% | Only Inkling measured |
| LiveBench browser | Not measured | 16.0% | Only Inkling measured |
| LiveBench long agentic | Not measured | 14.1% | Only Inkling measured |
| SREBench (Vals AI) | Not measured | 0.0% | Only Inkling measured |
| Finance Agent (Vals AI) | 47.4% | 46.6% | Gemini 3.5 Flash Lite |
| Tax Agent Bench (Vals AI) | 7.2% | 15.3% | Inkling |
| Legal Research Bench (Vals AI) | 13.9% | 28.4% | Inkling |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 3.8% | Only Inkling measured |
| Excel Modeling Benchmark (Vals AI) | 43.2% | 38.4% | Gemini 3.5 Flash Lite |
| APEX-Agents | 29.3% | 33.8% | Inkling |
| Neither model has a result on the other 29 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index19
| Benchmark | Gemini 3.5 Flash Lite | Inkling | Leader |
|---|---|---|---|
| GPQA Diamond | 83.8% | 87.1% | Inkling |
| LiveBench reasoning | Not measured | 78.3% | Only Inkling measured |
| MMMU Pro (Vals AI) | 83.6% | 78.5% | Gemini 3.5 Flash Lite |
| GPQA Diamond (Artificial Analysis run) | 83.8% | 87.2% | Inkling |
| Humanity's Last Exam (Artificial Analysis run) | 18.8% | 31.9% | Inkling |
| GPQA Diamond (Epoch AI run) | 83.3% | 88.3% | Inkling |
| ARC-AGI | 53.5% | 79.5% | Inkling |
| ARC-AGI-2 | 10.3% | 36.5% | Inkling |
| SimpleBench | Not measured | 50.0% | Only Inkling measured |
| Chess puzzles | 21.0% | 21.0% | Tie |
| Mystery game puzzles | 19.0% | Not measured | Only Gemini 3.5 Flash Lite measured |
| LMArena Text: hard prompts | 1441 | 1451 | Inkling |
| LMArena Text: expert | 1434 | 1466 | Inkling |
| LMArena Text: hard prompts in English | 1440 | 1448 | Inkling |
| LMArena Vision: diagrams | 1284 | Not measured | Only Gemini 3.5 Flash Lite measured |
| LMArena Vision: homework | 1291 | Not measured | Only Gemini 3.5 Flash Lite measured |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index15
| Benchmark | Gemini 3.5 Flash Lite | Inkling | Leader |
|---|---|---|---|
| OTIS Mock AIME | 71.1% | 88.9% | Inkling |
| FrontierMath, tiers 1 to 3 | 26.0% | 33.3% | Inkling |
| FrontierMath, tier 4 | 0.0% | 4.9% | Inkling |
| ProofBench | 13.0% | 0.0% | Gemini 3.5 Flash Lite |
| LMArena Text: math | 1434 | 1479 | Inkling |
| LMArena Text: mathematical work | 1433 | 1460 | Inkling |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index37
| Benchmark | Gemini 3.5 Flash Lite | Inkling | Leader |
|---|---|---|---|
| MMLU Pro | 85.8% | 86.3% | Inkling |
| LegalBench (Vals AI) | 84.1% | 83.0% | Gemini 3.5 Flash Lite |
| CorpFin (Vals AI) | 60.7% | 68.6% | Inkling |
| TaxEval (Vals AI) | 72.6% | 75.3% | Inkling |
| MortgageTax (Vals AI) | 68.7% | 64.0% | Gemini 3.5 Flash Lite |
| MedCode (Vals AI) | 43.5% | 41.2% | Gemini 3.5 Flash Lite |
| SimpleQA Verified | Not measured | 40.3% | Only Inkling measured |
| LMArena Text: science | 1451 | 1455 | Inkling |
| LMArena Text: medicine and healthcare | 1438 | 1447 | Inkling |
| LMArena Text: legal and government | 1431 | 1448 | Inkling |
| LMArena Text: business and finance | 1423 | 1438 | Inkling |
| FACTS Benchmark Suite | 53.5% | Not measured | Only Gemini 3.5 Flash Lite measured |
| Neither model has a result on the other 6 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | Gemini 3.5 Flash Lite | Inkling | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1224 | Only Inkling measured |
| Design Arena: UI components | Not measured | 1198 | Only Inkling measured |
| Design Arena: game dev | Not measured | 1165 | Only Inkling measured |
| Design Arena: data viz | Not measured | 1156 | Only Inkling measured |
| Design Arena: 3D | Not measured | 1160 | Only Inkling measured |
| Design Arena: all code categories | Not measured | 1205 | Only Inkling measured |
| Design Arena: SVG | Not measured | 1108 | Only Inkling measured |
| Design Arena: ASCII art | Not measured | 1089 | Only Inkling measured |
| LiveBench design | Not measured | 58.3% | Only Inkling measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index1013
| Benchmark | Gemini 3.5 Flash Lite | Inkling | Leader |
|---|---|---|---|
| Vals Index | Not measured | 29.0% | Only Inkling measured |
| LiveBench data analysis | Not measured | 72.8% | Only Inkling measured |
| Public Benefits Bench (Vals AI) | 51.8% | 58.5% | Inkling |
| SAGE (Vals AI) | 47.3% | 36.5% | Gemini 3.5 Flash Lite |
| MedScribe (Vals AI) | 70.9% | 85.4% | Inkling |
| Vals Multimodal Index | Not measured | 49.4% | Only Inkling measured |
| Long context reasoning (AA-LCR) | 76.0% | 77.3% | Inkling |
| DTBench | 83.5% | 87.5% | Inkling |
| LMCA | 37.6% | 37.6% | Gemini 3.5 Flash Lite |
| LMArena Text | 1435 | 1442 | Inkling |
| LMArena Text: instruction following | 1419 | 1425 | Inkling |
| LMArena Text: creative writing | 1421 | 1390 | Gemini 3.5 Flash Lite |
| LMArena Vision | 1269 | Not measured | Only Gemini 3.5 Flash Lite measured |
| LMArena Text: English | 1438 | 1442 | Inkling |
| LMArena Text: non-English | 1427 | 1434 | Inkling |
| LMArena Text: Chinese | 1468 | 1493 | Inkling |
| LMArena Text: German | 1454 | 1445 | Gemini 3.5 Flash Lite |
| LMArena Text: Japanese | 1426 | 1429 | Inkling |
| LMArena Text: Korean | 1407 | 1403 | Gemini 3.5 Flash Lite |
| LMArena Text: French | 1451 | 1455 | Inkling |
| LMArena Text: Spanish | 1441 | 1449 | Inkling |
| LMArena Text: Russian | 1443 | 1430 | Gemini 3.5 Flash Lite |
| LMArena Text: Polish | 1437 | 1450 | Inkling |
| LMArena Text: multi-turn | 1445 | 1437 | Gemini 3.5 Flash Lite |
| LMArena Text: longer queries | 1435 | 1435 | Gemini 3.5 Flash Lite |
| LMArena Text: writing and language | 1428 | 1404 | Gemini 3.5 Flash Lite |
| LMArena Text: entertainment and media | 1414 | 1394 | Gemini 3.5 Flash Lite |
| LMArena Vision: English | 1269 | Not measured | Only Gemini 3.5 Flash Lite measured |
| LMArena Vision: Chinese | 1311 | Not measured | Only Gemini 3.5 Flash Lite measured |
| LMArena Vision: reading text | 1280 | Not measured | Only Gemini 3.5 Flash Lite measured |
| LMArena Vision: humor | 1287 | Not measured | Only Gemini 3.5 Flash Lite measured |
| LMArena Vision: creative writing | 1260 | Not measured | Only Gemini 3.5 Flash Lite measured |
| Neither model has a result on the other 14 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemini 3.5 Flash Lite | Inkling | 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
Gemini 3.5 Flash Lite costs less
Repository review
50K input + 3K output tokens
Gemini 3.5 Flash Lite costs less
Agent loop
200K input + 10K output tokens
Gemini 3.5 Flash Lite 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 Gemini 3.5 Flash Lite | Thinking Machines Inkling |
|---|---|---|
| Maker | Thinking Machines | |
| Weights | No public weights listed | Open weights |
| Released | July 21, 2026 | July 17, 2026 |
| Context window | 1.05M | 524K |
| Input $/Mtok | $0.30 | $0.975 |
| Output $/Mtok | $2.50 | $4.05 |
| Coding index | 49.0 | 31.5 |
| Independent measurements behind it | 3 | 6 |
| Cost per solved task | $0.41 | $0.76 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemini 3.5 Flash Lite better than Inkling for coding?
Pick Gemini 3.5 Flash Lite for coding: it scores 49.0 on the Vibe Coding Index against 31.5 for Inkling, though on 3 benchmarks against 6. Pick Inkling for work measured by AA Coding Index or LiveCodeBench (Vals AI), where it leads.
Which is cheaper, Gemini 3.5 Flash Lite or Inkling?
Gemini 3.5 Flash Lite costs $0.30 per million input tokens and $2.50 per million output tokens; Inkling costs $0.975 and $4.05. Per solved SWE-bench Verified task, Gemini 3.5 Flash Lite costs $0.41 and Inkling $0.76.
Which has the bigger context window, Gemini 3.5 Flash Lite or Inkling?
Gemini 3.5 Flash Lite, with 1.05M tokens against 524K.
How many benchmarks is the Gemini 3.5 Flash Lite vs Inkling comparison based on?
73 benchmarks have a result for both models as of October 22, 2026. Gemini 3.5 Flash Lite's coding index rests on 3 independent benchmarks and Inkling's on 6. Where only one model has a result, the page says so instead of naming a winner.