STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Inkling-Small vs Mistral Large 4

Mistral Large 4 leads Inkling-Small by 15.7 points on StealthMark, 43.3 to 27.6. It leads on 8 of 9 benchmarks, including Latch, and Inkling-Small on 1, including Foresight. Mistral Large 4 scores higher on Newton's Mirror, with its largest category advantage in camera and placement.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

27.6/100Overall rank 43/53
43.3/100Overall rank 31/53

General Intelligence

25.5/100
34.4/100

Visual Intelligence

31.1/100
58.0/100

Reasoning efficiency

On every task, result quality and reasoning tokens are each compared with all measured models and weighed equally. Each dot is one model.

Single-step reasoning Result quality weighed against reasoning tokens on a single problem

Multi-step reasoning Result quality weighed against reasoning tokens across connected steps, as in agentic workflows

  • Inkling-Small

BENCHMARK BY BENCHMARK

Where each model leads

  • Inkling-Small
  • Mistral Large 4
  • Other models
  • Median

DATASHEET

Specs and pricing

Both take about 1M tokens of context.

  • Inkling-Small
  • Mistral Large 4
  • Other models
  • Median
PricePer 1M output tokens, input below
Inkling-Small: No list priceMistral Large 4: $4.18$1.36 input
Context windowTokens per request, max output below
Inkling-Small: 1MTiedMistral Large 4: 1MTied256K max output
Output speedTokens per second, our measurement
Inkling-Small: Not measuredMistral Large 4: 151tokens/s
SizeTotal and active parameters
Inkling-Small: 276B12B activeMistral Large 4: 1.05T49B active
Developer
Thinking Machines LabMistral AI
Released
Not published6 Oct 2026
Origin
Not publishedFrance
Input → output
Text, image, audio → textText, image → text
Architecture
42-layer decoder-only transformer with sparse mixture-of-experts feed-forward (6 of 256 routed experts plus 2 shared per token); hybrid local and global attention; natively multimodal with a hierarchical patch image encoder and discrete-token audioGranular mixture of experts (MoE); multimodal text and image input, text output.

Full datasheets, every price and sourceInkling-Small ↗Mistral Large 4 ↗

Anticipating threats and planning ahead. Collect coins while avoiding ghosts. Ghosts move before the player each turn, and collisions cost a life. 3 levels in sequence, up to 66 turns in total. Earlier moves and outcomes carry forward, testing learning across levels.

Inkling-Small 30.2/100Rank 29/49

Survived 0 of 3
Foresight: complete playing field
Level 38 ptsTurn 17 / 20

Mistral Large 4 22.0/100Rank 40/49

Survived 0 of 3
Foresight: complete playing field
Level 34 ptsTurn 8 / 20

Points per level

LevelInkling-SmallMistral Large 4
Level 1Second Thoughts
9 ptsOut of lives
1 ptsOut of lives
Level 2Pressure Pot
6 ptsOut of lives
9 ptsOut of lives
Level 3Hide or Flight
8 ptsOut of lives
4 ptsOut of lives

Cooperative planning and learning from experience. Coordinate two robots to push numbered cores onto matching sockets. Pressure plates hold doors open; moving either robot uses one turn. 5 levels in sequence, up to 152 turns in total. Earlier moves and outcomes carry forward, testing learning across levels.

Inkling-Small 34.7/100Rank 34/50

Cleared 3 of 5
Latch: complete playing field
Level 518 ptsTurn 40 / 40

Mistral Large 4 49.4/100Rank 25/50

Cleared 5 of 5
Latch: complete playing field
Level 519.8 ptsTurn 31 / 40

Points per level

LevelInkling-SmallMistral Large 4
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9.8 ptsCleared
9.6 ptsCleared
Level 3Relay vault
2.8 ptsFinished early
15.8 ptsClearedFinished early · 3 beacons left
Level 4Passing bay
8 ptsFinished early
16.2 ptsClearedFinished early · 3 beacons left
Level 5Second thoughts
18 ptsCleared
19.8 ptsCleared

Newton's Mirror

Same task instructions

Physics, perspective and recursive reflections, tested together. Explore the test ↗

The judgment

Inkling-Small

The sphere's apparent floor support, separate dark feature and broad paint ordering justify partial state credit. The major weakness is the largely missing mirror system: isolated side images and faint floor echoes do not establish repeated virtual rooms or curved spherical mapping. Downward framing, the oversized frontal panel, unresolved paint transport and satin surface appearance remain distinct limitations.

Mistral Large 4

The central sphere, airborne black and deformed crimson support substantial state and placement credit. Recent cyan contact and crimson transport remain uncertain. Sparse wall patches and glossy gradients provide little evidence of the required extensive mirror system, while the missing centerline lamp and bulky crimson remain visible weaknesses.

Score breakdown

CategoryInkling-SmallMistral Large 4
State at 600 ms14.0/2517.0/25
Camera and placement3.0/1511.0/15
Reflections8.0/12012.0/120
Materials and scale2.5/105.5/10
Floor-damage reward0.0/100.0/10

Benchmark task

A spinning metal sphere and paint in a mirrored room test physical reasoning, perspective and consistency across repeated reflections.

Selfie

Different task instructions

Visual construction and creative interpretation.

The judgment

Inkling-Small

The faces and dripping caps communicate a cute mushroom scene, but simple construction and weak spatial relationships limit the result. The defining foot-stamping action is unresolved, the flattering portrait is smaller than its painter, and the requested material contrasts are only partly conveyed.

Mistral Large 4

An appealing, coherent illustration whose enormous rounded cat anchors the windblown composition. Warm shading and floating sketches communicate the brief well. Simplified paws, faint ear construction, inconsistent wind cues and limited material texture keep the execution below exceptional.

Score breakdown

CategoryInkling-SmallMistral Large 4
Task & likeness2.5/108.0/10
Anatomy & construction1.5/107.0/10
Space & placement3.5/107.5/10
Light & reflections3.0/107.0/10
Purposeful detail4.5/107.0/10
Artistry & character3.0/107.0/10
Materials & effects3.5/107.0/10
Visual integrity2.0/108.0/10

Benchmark task

Inkling-Small

Character scenes test expression, anatomy, materials and coherent visual construction.

Mistral Large 4

A heavy ginger cat stays planted on a terrace as wind carries papers around it. The scene tests weight, expression and the contrast between stable and moving forms.

Mona Lisa

Different task instructions

Precise visual recall and portrait reconstruction.

The judgment

Inkling-Small

A recognizable but rudimentary Mona Lisa interpretation. Facial shading and subdued colors provide coherence, while the frontal blocklike torso, unresolved wrists, fingerless hands and shallow landscape substantially limit likeness, construction and finish.

Mistral Large 4

A recognizable, cleanly rendered interpretation with a restrained palette and some facial modeling. Its enlarged frontal head, simplified expression, compressed low hands and schematic landscape substantially limit likeness and construction. The smooth rendering does not reproduce the painting's nuanced anatomy, clothing or atmospheric depth.

Score breakdown

CategoryInkling-SmallMistral Large 4
Task & likeness2.5/104.0/10
Anatomy & construction2.5/103.5/10
Space & placement3.0/105.0/10
Light & reflections2.5/104.5/10
Purposeful detail2.0/104.0/10
Artistry & character2.5/104.0/10
Materials & effects2.0/104.5/10
Visual integrity3.0/105.5/10

Benchmark task

An SVG interpretation of the Mona Lisa tests facial likeness, anatomy and the composition of a familiar portrait.

Beach

Different task instructions

Creativity, perspective and visual beauty.

The judgment

Inkling-Small

A recognizable sunset beach with a clear focal sun and appealing color transitions. Connected fish silhouettes and layered scenery establish basic coherence. Primitive figures, ambiguous recreation, sparse descriptive detail and weak grounding limit construction and depth. The aligned reflection supplies a useful lighting cue, but shadows and material effects remain underdeveloped.

Mistral Large 4

A clean, appealing beach illustration with clear subject coverage, a cohesive sunset palette and expressive animal details. Bodies and accessories resolve basic construction coherently, although joints remain schematic. Layered shapes establish modest depth; generic oval shadows and flat surfaces limit physical richness. Repeated forms and sparse articulation leave room for more accomplished drawing.

Score breakdown

CategoryInkling-SmallMistral Large 4
Task & likeness3.5/107.5/10
Anatomy & construction3.0/106.0/10
Space & placement3.0/107.0/10
Light & reflections3.0/106.5/10
Purposeful detail3.0/106.0/10
Artistry & character3.0/106.0/10
Materials & effects2.5/106.5/10
Visual integrity2.0/108.0/10

Benchmark task

A busy shoreline at sunset tests scene composition, animal forms and the relationship between light and water reflections.

Ground Truth

Same task instructions

Physical reasoning, light and visual reconstruction.

The judgment

Inkling-Small

This benchmark has not been assessed yet.

Mistral Large 4

This benchmark has not been assessed yet.

Benchmark task

A plank, computer mouse and blueberry in a steel room test physical stability, spatial relationships, materials and lighting.

Raccoon

Different task instructions

Scene composition and interacting subjects.

The judgment

Inkling-Small

Recognizable animals, readable accessories and an appealing sunset support a coherent basic cartoon. Rounded construction leaves joints, riding support and steering unresolved. Decorative gradients contribute atmosphere, but directional lighting, distinct materials and convincing water displacement are weakly demonstrated.

Mistral Large 4

The central interaction is clear, with recognizable animals, expressive faces and a coherent sunset composition. Clean contours and readable accessories give the cartoon polish. Simplified joints, uncertain steering attachment, shallow hull volume and limited directional lighting constrain its physical resolution.

Score breakdown

CategoryInkling-SmallMistral Large 4
Task & likeness4.0/108.5/10
Anatomy & construction3.0/106.5/10
Space & placement4.0/107.0/10
Light & reflections5.0/105.5/10
Purposeful detail5.5/107.5/10
Artistry & character4.0/106.5/10
Materials & effects5.0/106.5/10
Visual integrity5.0/108.0/10

Benchmark task

A jet-ski scene pairs a canine driver with a raccoon passenger. It tests the placement and contact of interacting subjects, along with vehicle construction.

Pelican

Different task instructions

Subject construction and spatial relationships.

The judgment

Inkling-Small

The pelican is immediately recognizable, and its sweeping neck, shaped bill and orderly spokes provide character. Riding remains only partially realized: legs, pedal engagement, steering and seat support cannot be read confidently. Controlled graphic effects add atmosphere, but simplified construction and weak grounding keep the result basic.

Mistral Large 4

A coherent, appealing pelican illustration with a continuous body silhouette, readable bicycle and grounded wheels. Simplified legs and ambiguous steering and pedal connections limit construction. Clean shapes and expressive accessories succeed, while shallow depth, modest lighting and sparse material differentiation leave substantial room for refinement.

Score breakdown

CategoryInkling-SmallMistral Large 4
Task & likeness4.0/108.5/10
Anatomy & construction3.0/106.0/10
Space & placement3.0/107.0/10
Light & reflections3.0/106.5/10
Purposeful detail4.5/107.0/10
Artistry & character5.0/107.0/10
Materials & effects4.5/106.5/10
Visual integrity3.0/108.0/10

Benchmark task

A cycling pelican tests anatomy, riding posture and contact between the bird and the bicycle.