Compare / Mistral Medium 3.5 vs Inkling Small
Mistral Medium 3.5 vs Inkling Small
Which is cheaper, which is more capable, and which does better at each kind of work, from 32 results on 3 sources that measured both models.
Mistral Medium 3.5 or Inkling Small? The short answer
- Inkling Small is cheaper: $0.64 against $3.00 per million tokens, 4.7 times less.
- Inkling Small scores higher on the Artificial Analysis Intelligence Index: 25.7 against 14.2.
- On our business benchmarks, Mistral Medium 3.5 ranks higher for writing and sticking to the facts.
- On our business benchmarks, Inkling Small ranks higher for agents and tool use, reasoning and knowledge and speed under pressure.
At a glance
| Mistral Medium 3.5 | Inkling Small | |
|---|---|---|
| Price per million tokens | $1.50 in · $7.50 out | $0.45 in · $1.20 out |
| Blended (3 in : 1 out) | $3.00 | $0.64 |
| Cheapest host, blended | $3.00 (Mistral) | – |
| Intelligence Index | 14.2 | 25.7 |
| Spring Prompt overall | 21 | – |
| Output speed, tokens a second | 163 | 173 |
| Context window | 262,144 tokens | 524,288 tokens |
| Weights | Closed | Open |
| Developer based in | France | 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 | Mistral Medium 3.5 | Inkling Small |
|---|---|---|
| Product listingsTurning a sparse product feed and photos into listings that can go live | 13 of 19 | not measured |
| Decks from an analysisTurning a finished analysis into a deck you could present as it is | 14 of 18 | not measured |
| Marketing planningPlanning a year of ad spend without overspending | 18 of 18 | not measured |
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | 87 of 161 | 68 of 161 |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 119 of 195 | 58 of 195 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | 85 of 187 | 100 of 187 |
| Sticking to the factsSummarising without inventing things, and factual answers | 99 of 153 | 126 of 153 |
| Speed under pressureGood decisions against a real clock (fast chess) | 8 of 21 | 4 of 21 |
From our research
Every shared result
| Benchmark | Metric | Mistral Medium 3.5 | Inkling Small |
|---|---|---|---|
| BulletBenchmeasured by us | Cost per gameUS dollars | $0.0354 | $0.0075 |
| BulletBenchmeasured by us | Games lost on time% of games | 0.0% | 0.0% |
| BulletBenchmeasured by us | Invalid moves% of moves | 0.4% | 7.2% |
| BulletBenchmeasured by us | Ladder Eloladder Elo | 572 | 529 |
| BulletBenchmeasured by us | Median move timemilliseconds | 0.5 s | 0.6 s |
| BulletBenchmeasured by us | Cost per gameUS dollars | $0.0297 | $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 | 529 | 571 |
| BulletBenchmeasured by us | Median move timemilliseconds | 0.5 s | 0.6 s |
| Arena (formerly LMArena)reported | Confirmed task successIPS effect estimate | -0.16 | -0.21 |
| Arena (formerly LMArena)reported | Praise over complaintIPS effect estimate | -0.15 | -0.21 |
| Arena (formerly LMArena)reported | SteerabilityIPS effect estimate | -0.07 | -0.12 |
| Arena (formerly LMArena)reported | Tool groundingIPS effect estimate | -0.02 | -0.00 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,430 | 1,425 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,430 | 1,408 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,398 | 1,313 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,434 | 1,445 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,421 | 1,393 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,426 | 1,405 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,404 | 1,344 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 46.9 | 52.9 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 14.2 | 25.7 |
| Artificial Analysisreported | GPQA Diamond% of questions | 74.8% | 89.5% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 13.8% | 33.3% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 69.3% | 75.7% |
| Artificial Analysisreported | Output speedtokens per second | 163 | 173 |
| Artificial Analysisreported | SciCode% of problems | 40.2% | 49.7% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 50.6% | 55.1% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 0.0% | 1.0% |
| Artificial Analysisreported | Time to first answer tokenseconds | 12.9 | 13.6 |
| Artificial Analysisreported | Τ-bench banking% of tasks | 15.1% | 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 Mistral Medium 3.5 better than Inkling Small?
It depends on the task. Among models available today, on our benchmarks and licensed sources, Mistral Medium 3.5 ranks higher for writing and sticking to the facts; Inkling Small ranks higher for agents and tool use, reasoning and knowledge and speed under pressure.
Which is cheaper, Mistral Medium 3.5 or Inkling Small?
Inkling Small costs $0.64 per million tokens (three input to one output), against $3.00 for Mistral Medium 3.5.
Which is faster, Mistral Medium 3.5 or Inkling Small?
Inkling Small writes about 173 tokens a second on its usual API, against 163 for Mistral Medium 3.5 (Artificial Analysis).
Run Mistral Medium 3.5 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.