Compare / Gemini 3.5 Flash Lite vs Inkling Small
Gemini 3.5 Flash Lite vs Inkling Small
Which is cheaper, which is more capable, and which does better at each kind of work, from 28 results on 3 sources that measured both models.
Gemini 3.5 Flash Lite or Inkling Small? The short answer
- Inkling Small is cheaper: $0.64 against $0.85 per million tokens, 25% less.
- Inkling Small scores higher on the Artificial Analysis Intelligence Index: 25.7 against 22.2.
- Gemini 3.5 Flash Lite writes faster: 330 tokens a second against 173.
- On our business benchmarks, Gemini 3.5 Flash Lite ranks higher for writing, sticking to the facts and speed under pressure.
- On our business benchmarks, Inkling Small ranks higher for agents and tool use and reasoning and knowledge.
At a glance
| Gemini 3.5 Flash Lite | Inkling Small | |
|---|---|---|
| Price per million tokens | $0.30 in · $2.50 out | $0.45 in · $1.20 out |
| Blended (3 in : 1 out) | $0.85 | $0.64 |
| Cheapest host, blended | $0.42 (Google) | – |
| Intelligence Index | 22.2 | 25.7 |
| Spring Prompt overall | 27 | – |
| Output speed, tokens a second | 330 | 173 |
| Context window | 1,048,576 tokens | 524,288 tokens |
| Weights | Closed | Open |
| Developer based in | the US | the US |
Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.
Which is better for what
Each model's rank among models available today, for each kind of work, from our own benchmarks and licensed sources. The better rank is in green.
| Use case | Gemini 3.5 Flash Lite | Inkling Small |
|---|---|---|
| Product listingsTurning a sparse product feed and photos into listings that can go live | 15 of 19 | not measured |
| Decks from an analysisTurning a finished analysis into a deck you could present as it is | 15 of 18 | not measured |
| Marketing planningPlanning a year of ad spend without overspending | 15 of 18 | not measured |
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | 69 of 161 | 68 of 161 |
| Professional workReal tasks from banking, consulting and law, business documents and freelance projects | 46 of 51 | not measured |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 87 of 195 | 58 of 195 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | 45 of 187 | 100 of 187 |
| Sticking to the factsSummarising without inventing things, and factual answers | 60 of 153 | 126 of 153 |
| Speed under pressureGood decisions against a real clock (fast chess) | 2 of 21 | 4 of 21 |
Every shared result
| Benchmark | Metric | Gemini 3.5 Flash Lite | Inkling Small |
|---|---|---|---|
| BulletBenchmeasured by us | Cost per gameUS dollars | $0.0058 | $0.0075 |
| BulletBenchmeasured by us | Games lost on time% of games | 0.0% | 0.0% |
| BulletBenchmeasured by us | Invalid moves% of moves | 0.0% | 7.2% |
| BulletBenchmeasured by us | Ladder Eloladder Elo | 780 | 529 |
| BulletBenchmeasured by us | Median move timemilliseconds | 0.9 s | 0.6 s |
| BulletBenchmeasured by us | Cost per gameUS dollars | $0.0070 | $0.0077 |
| BulletBenchmeasured by us | Games lost on time% of games | 0.0% | 0.0% |
| BulletBenchmeasured by us | Invalid moves% of moves | 0.0% | 5.3% |
| BulletBenchmeasured by us | Ladder Eloladder Elo | 892 | 571 |
| BulletBenchmeasured by us | Median move timemilliseconds | 0.9 s | 0.6 s |
| Arena (formerly LMArena)reported | OverallArena rating | 1,448 | 1,425 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,454 | 1,408 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,435 | 1,313 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,467 | 1,445 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,444 | 1,393 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,456 | 1,405 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,442 | 1,344 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 49.3 | 52.9 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 22.2 | 25.7 |
| Artificial Analysisreported | GPQA Diamond% of questions | 83.8% | 89.5% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 18.8% | 33.3% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 76.0% | 75.7% |
| Artificial Analysisreported | Output speedtokens per second | 330 | 173 |
| Artificial Analysisreported | SciCode% of problems | 41.3% | 49.7% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 53.6% | 55.1% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 1.0% | 1.0% |
| Artificial Analysisreported | Time to first answer tokenseconds | 7.04 | 13.6 |
| Artificial Analysisreported | Τ-bench banking% of tasks | 17.5% | 18.8% |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.
Quick answers
Is Gemini 3.5 Flash Lite better than Inkling Small?
It depends on the task. Among models available today, on our benchmarks and licensed sources, Gemini 3.5 Flash Lite ranks higher for writing, sticking to the facts and speed under pressure; Inkling Small ranks higher for agents and tool use and reasoning and knowledge.
Which is cheaper, Gemini 3.5 Flash Lite or Inkling Small?
Inkling Small costs $0.64 per million tokens (three input to one output), against $0.85 for Gemini 3.5 Flash Lite.
Which is faster, Gemini 3.5 Flash Lite or Inkling Small?
Gemini 3.5 Flash Lite writes about 330 tokens a second on its usual API, against 173 for Inkling Small (Artificial Analysis).
Run Gemini 3.5 Flash Lite and Inkling Small on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.