Mistral Large 4 vs Inkling 2 Mini
Mistral Large 4 leads Inkling 2 Mini on coding, 61.1 to 39.5 on the Vibe Coding Index, and Inkling 2 Mini costs 6.5x less per output token ($0.325 vs $2.10 per million). Updated November 22, 2026; 21 benchmarks have a result for both.
Mistral Large 4 or Inkling 2 Mini: which to pick
Pick Mistral Large 4 for coding: it scores 61.1 on the Vibe Coding Index against 39.5 for Inkling 2 Mini.
Pick Inkling 2 Mini for output tokens 6.5x cheaper ($0.325 vs $2.10 per million) and work measured by SWE-bench Multimodal (Vals AI) or FrontierCode 2.0, where it leads.
- Shared results
- 21
- Mistral Large 4 only
- 70
- Inkling 2 Mini only
- 8
- 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
Mistral Large 4
Mistral Large 4 scores 61.1 against 39.5.
5 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
Mistral Large 4
Mistral Large 4 leads, 26.1 against 20.1.
Same board, both measured
Web design
Design Arena: websites
No call
Only Mistral Large 4 has a Design Arena: websites result, 1253.
Directional only
General
Vals Index
Mistral Large 4
Mistral Large 4 leads, 56.5% against 46.5%.
Same board, both measured
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Inkling 2 Mini
Mistral Large 4 $0.0018, Inkling 2 Mini $0.0002 per turn.
List prices
At a glance
- Coding index
- Mistral Large 4 61.1 from 5 benchmarks, Inkling 2 Mini 39.5 from 2 benchmarks.
- Widest category
- Agentic work, 16.5 points apart on average over 4 shared benchmarks.
- Widest single gap
- IOI (Vals AI): Mistral Large 4 45.3% against Inkling 2 Mini 11.6%, 33.7 points apart on a 0 to 100 scale.
- Output price
- Mistral Large 4 $2.10 against Inkling 2 Mini $0.325 per million output tokens, 6.5x apart.
- Context window
- Both take 1.05M tokens.
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 | Mistral Large 4 | Bars | Inkling 2 Mini | Ties |
|---|---|---|---|---|
| Coding | 4 | 2 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 4 | 0 | ||
| Reasoning | 2 | 1 | ||
| Knowledge | 2 | 0 | ||
| Web design | 0 | 3 | ||
| General | 1 | 1 | ||
| All shared boards | 14 | 7 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index42
| Benchmark | Mistral Large 4 | Inkling 2 Mini | Leader |
|---|---|---|---|
| LiveBench coding | 79.4% | Not measured | Only Mistral Large 4 measured |
| LMArena WebDev | 1573 | Not measured | Only Mistral Large 4 measured |
| Terminal-Bench 4 (Vals AI) | 27.8% | 6.6% | Mistral Large 4 |
| Vibe Code Bench (Vals AI) | 81.6% | 77.9% | Mistral Large 4 |
| Code migration (Vals AI) | 30.6% | Not measured | Only Mistral Large 4 measured |
| ProgramBench (Vals AI) | Not measured | 0.5% | Only Inkling 2 Mini measured |
| IOI (Vals AI) | 45.3% | 11.6% | Mistral Large 4 |
| SWE-bench Multimodal (Vals AI) | 33.1% | 37.9% | Inkling 2 Mini |
| Vibe Code Bench 1-100 (Vals AI) | 14.3% | Not measured | Only Mistral Large 4 measured |
| SkillsBench (Vals AI) | Not measured | 43.2% | Only Inkling 2 Mini measured |
| CyberBench (Vals AI) | Not measured | 74.6% | Only Inkling 2 Mini measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | 24.7% | 5.6% | Mistral Large 4 |
| FrontierCode 2.0 | 15.0% | 15.1% | Inkling 2 Mini |
| FrontierCode | 39.4% | Not measured | Only Mistral Large 4 measured |
| MirrorCode | 40.0% | Not measured | Only Mistral Large 4 measured |
| ALE-Bench | 1213.2 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: coding | 1459 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: software and IT | 1459 | Not measured | Only Mistral Large 4 measured |
| LMArena WebDev: React | 1582 | Not measured | Only Mistral Large 4 measured |
| LMArena WebDev: HTML | 1560 | Not measured | Only Mistral Large 4 measured |
| GameBench 2 | 57.9 | Not measured | Only Mistral Large 4 measured |
| Terminal-Bench 4.0 | 27.9% | Not measured | Only Mistral Large 4 measured |
| Neither model has a result on the other 30 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Mistral Large 4 | Inkling 2 Mini | Leader |
|---|---|---|---|
| AA Intelligence Index | 26.1 | 20.1 | Mistral Large 4 |
| Epoch Capabilities Index | 154.6 | Not measured | Only Mistral Large 4 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Mistral Large 4 | Inkling 2 Mini | Leader |
|---|---|---|---|
| LiveBench research | 80.3% | Not measured | Only Mistral Large 4 measured |
| LiveBench browser | 17.4% | Not measured | Only Mistral Large 4 measured |
| LiveBench long agentic | 24.7% | Not measured | Only Mistral Large 4 measured |
| SREBench (Vals AI) | Not measured | 0.0% | Only Inkling 2 Mini measured |
| Finance Agent (Vals AI) | 54.7% | Not measured | Only Mistral Large 4 measured |
| Tax Agent Bench (Vals AI) | 30.7% | 14.1% | Mistral Large 4 |
| Legal Research Bench (Vals AI) | 35.6% | 17.8% | Mistral Large 4 |
| Harvey's Legal Agent Benchmark (Vals AI) | 17.5% | 5.0% | Mistral Large 4 |
| Excel Modeling Benchmark (Vals AI) | 56.2% | Not measured | Only Mistral Large 4 measured |
| BioMysteryBench (Vals AI) | 67.0% | 47.8% | Mistral Large 4 |
| Terminal-Bench-Science (Vals AI) | Not measured | 0.0% | Only Inkling 2 Mini measured |
| Vals Science Index | Not measured | 23.6% | Only Inkling 2 Mini measured |
| APEX-Agents | 51.6% | Not measured | Only Mistral Large 4 measured |
| Neither model has a result on the other 31 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | Mistral Large 4 | Inkling 2 Mini | Leader |
|---|---|---|---|
| LiveBench reasoning | 85.2% | Not measured | Only Mistral Large 4 measured |
| MysteryMechanism (Vals AI) | 12.2% | 23.0% | Inkling 2 Mini |
| HLE-Diamond (Artificial Analysis run) | 17.3% | 15.2% | Mistral Large 4 |
| CritPt v2, hard subset (Artificial Analysis run) | 27.0% | 17.0% | Mistral Large 4 |
| GPQA Diamond (Epoch AI run) | 88.1% | Not measured | Only Mistral Large 4 measured |
| Chess puzzles | 33.0% | Not measured | Only Mistral Large 4 measured |
| Mystery game puzzles | 17.0% | Not measured | Only Mistral Large 4 measured |
| LMArena Text: hard prompts | 1436 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: expert | 1450 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: hard prompts in English | 1442 | Not measured | Only Mistral Large 4 measured |
| LMArena Vision: diagrams | 1273 | Not measured | Only Mistral Large 4 measured |
| LMArena Vision: homework | 1266 | Not measured | Only Mistral Large 4 measured |
| Neither model has a result on the other 14 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | Mistral Large 4 | Inkling 2 Mini | Leader |
|---|---|---|---|
| OTIS Mock AIME | 98.3% | Not measured | Only Mistral Large 4 measured |
| FrontierMath, tiers 1 to 3 | 58.6% | Not measured | Only Mistral Large 4 measured |
| FrontierMath, tier 4 | 26.8% | Not measured | Only Mistral Large 4 measured |
| ProofBench | 10.0% | Not measured | Only Mistral Large 4 measured |
| LMArena Text: math | 1445 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: mathematical work | 1456 | Not measured | Only Mistral Large 4 measured |
| MathArena | 20.7% | Not measured | Only Mistral Large 4 measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Mistral Large 4 | Inkling 2 Mini | Leader |
|---|---|---|---|
| MedCode (Vals AI) | 40.7% | 25.7% | Mistral Large 4 |
| AA-Omniscience | 5.1 | -8.6 | Mistral Large 4 |
| SimpleQA Verified | 20.0% | Not measured | Only Mistral Large 4 measured |
| LMArena Text: science | 1434 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: medicine and healthcare | 1403 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: legal and government | 1427 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: business and finance | 1430 | Not measured | Only Mistral Large 4 measured |
| Neither model has a result on the other 14 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | Mistral Large 4 | Inkling 2 Mini | Leader |
|---|---|---|---|
| Design Arena: websites | 1253 | Not measured | Only Mistral Large 4 measured |
| Design Arena: UI components | 1272 | 1292 | Inkling 2 Mini |
| Design Arena: game dev | 1190 | 1287 | Inkling 2 Mini |
| Design Arena: data viz | 1271 | Not measured | Only Mistral Large 4 measured |
| Design Arena: 3D | 1225 | 1308 | Inkling 2 Mini |
| Design Arena: all code categories | 1247 | Not measured | Only Mistral Large 4 measured |
| Design Arena: SVG | 1216 | Not measured | Only Mistral Large 4 measured |
| Design Arena: ASCII art | 1196 | Not measured | Only Mistral Large 4 measured |
| LiveBench design | 76.3% | Not measured | Only Mistral Large 4 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Mistral Large 4 | Inkling 2 Mini | Leader |
|---|---|---|---|
| Vals Index | 56.5% | 46.5% | Mistral Large 4 |
| LiveBench data analysis | 76.6% | Not measured | Only Mistral Large 4 measured |
| SAGE (Vals AI) | Not measured | 85.9% | Only Inkling 2 Mini measured |
| MedScribe (Vals AI) | 80.4% | 86.4% | Inkling 2 Mini |
| GDPval-AA | Not measured | 1319 | Only Inkling 2 Mini measured |
| DTBench | 88.2% | Not measured | Only Mistral Large 4 measured |
| LMCA | 35.8% | Not measured | Only Mistral Large 4 measured |
| Surface Evolver Bench | 28.1% | Not measured | Only Mistral Large 4 measured |
| Furniture assembly | 20.8% | Not measured | Only Mistral Large 4 measured |
| LMArena Text | 1413 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: instruction following | 1414 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: creative writing | 1341 | Not measured | Only Mistral Large 4 measured |
| LMArena Vision | 1246 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: English | 1423 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: non-English | 1400 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: Chinese | 1466 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: French | 1443 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: Spanish | 1456 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: Russian | 1415 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: multi-turn | 1423 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: longer queries | 1409 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: writing and language | 1367 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: entertainment and media | 1358 | Not measured | Only Mistral Large 4 measured |
| LMArena Vision: English | 1258 | Not measured | Only Mistral Large 4 measured |
| LMArena Vision: Chinese | 1331 | Not measured | Only Mistral Large 4 measured |
| LMArena Vision: reading text | 1261 | Not measured | Only Mistral Large 4 measured |
| LMArena Vision: creative writing | 1213 | Not measured | Only Mistral Large 4 measured |
| Neither model has a result on the other 22 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mistral Large 4 | Inkling 2 Mini | 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
Inkling 2 Mini costs less
Repository review
50K input + 3K output tokens
Inkling 2 Mini costs less
Agent loop
200K input + 10K output tokens
Inkling 2 Mini 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 | Mistral Large 4 | Thinking Machines Inkling 2 Mini |
|---|---|---|
| Maker | Mistral AI | Thinking Machines |
| Weights | Open weights | Open weights |
| Released | October 6, 2026 | November 21, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.70 | $0.0775 |
| Output $/Mtok | $2.10 | $0.325 |
| Coding index | 61.1 | 39.5 |
| Independent measurements behind it | 5 | 2 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Mistral Large 4 better than Inkling 2 Mini for coding?
Pick Mistral Large 4 for coding: it scores 61.1 on the Vibe Coding Index against 39.5 for Inkling 2 Mini. Pick Inkling 2 Mini for output tokens 6.5x cheaper ($0.325 vs $2.10 per million) and work measured by SWE-bench Multimodal (Vals AI) or FrontierCode 2.0, where it leads.
Which is cheaper, Mistral Large 4 or Inkling 2 Mini?
Mistral Large 4 costs $0.70 per million input tokens and $2.10 per million output tokens; Inkling 2 Mini costs $0.0775 and $0.325. Cost per solved task is known for neither of them.
Which has the bigger context window, Mistral Large 4 or Inkling 2 Mini?
Neither: both take 1.05M tokens.
How many benchmarks is the Mistral Large 4 vs Inkling 2 Mini comparison based on?
21 benchmarks have a result for both models as of November 22, 2026. Mistral Large 4's coding index rests on 5 independent benchmarks and Inkling 2 Mini's on 2. Where only one model has a result, the page says so instead of naming a winner.