STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Claude Haiku 5.5 vs DeepSeek-V4.1-Flash-1017

DeepSeek-V4.1-Flash-1017 leads Claude Haiku 5.5 by 9.7 points on StealthMark, 59.2 to 49.5. It leads on 7 of 9 benchmarks, including Foresight, and Claude Haiku 5.5 on 2, including Latch. DeepSeek-V4.1-Flash-1017 scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

49.5/100Overall rank 17/53
59.2/100Overall rank 9/53

General Intelligence

47.6/100
56.8/100

Visual Intelligence

52.8/100
63.5/100

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

  • Claude Haiku 5.5

Open or local

Open modelMIT

BENCHMARK BY BENCHMARK

Where each model leads

  • Claude Haiku 5.5
  • DeepSeek-V4.1-Flash-1017
  • Other models
  • Median

DATASHEET

Specs and pricing

Claude Haiku 5.5 is 2.4× cheaper per output token and runs 30% faster in our speed test. DeepSeek-V4.1-Flash-1017 scores higher on StealthMark. Both take about 1M tokens of context.

  • Claude Haiku 5.5
  • DeepSeek-V4.1-Flash-1017
  • Other models
  • Median
PricePer 1M output tokens, input below
Claude Haiku 5.5: $0.502.4× cheaper$0.10 inputDeepSeek-V4.1-Flash-1017: $1.20$0.30 input
Context windowTokens per request, max output below
Claude Haiku 5.5: 1MTied128K max outputDeepSeek-V4.1-Flash-1017: 1MTied384K max output
Output speedTokens per second, our measurement
Claude Haiku 5.5: 40230% fastertokens/sDeepSeek-V4.1-Flash-1017: 310tokens/s
SizeTotal and active parameters
Claude Haiku 5.5: Not disclosedDeepSeek-V4.1-Flash-1017: 763B16B activeEstimated
Developer
AnthropicDeepSeek-AI
Released
7 Oct 202617 Oct 2026
Origin
United StatesChina
Input → output
Text, image → textBoth
Architecture
Not publishedSparse mixture-of-experts with a causal encoder-decoder design and native image understanding.

Full datasheets, every price and sourceClaude Haiku 5.5 ↗DeepSeek-V4.1-Flash-1017 ↗

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.

Claude Haiku 5.5 34.4/100Rank 25/47

Survived 1 of 3
Foresight: complete playing field
Level 39 ptsTurn 20 / 20

DeepSeek-V4.1-Flash-1017 52.9/100Rank 15/47

Survived 1 of 3
Foresight: complete playing field
Level 310 ptsTurn 15 / 20

Points per level

LevelClaude Haiku 5.5DeepSeek-V4.1-Flash-1017
Level 1Second Thoughts
4 ptsOut of lives
26 ptsSurvived
Level 2Pressure Pot
7 ptsOut of lives
7 ptsOut of lives
Level 3Hide or Flight
9 ptsSurvived
10 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.

Claude Haiku 5.5 78.3/100Rank 10/48

Cleared 5 of 5
Latch: complete playing field
Level 520.6 ptsTurn 27 / 40

DeepSeek-V4.1-Flash-1017 73.9/100Rank 13/48

Cleared 5 of 5
Latch: complete playing field
Level 520 ptsTurn 30 / 40

Points per level

LevelClaude Haiku 5.5DeepSeek-V4.1-Flash-1017
Level 1Hold the door
5 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9.8 ptsCleared
9.8 ptsCleared
Level 3Relay vault
18.8 ptsCleared
19.2 ptsCleared
Level 4Passing bay
18.2 ptsClearedFinished early · 3 beacons left
16.4 ptsClearedFinished early · 3 beacons left
Level 5Second thoughts
20.6 ptsCleared
20 ptsCleared

Newton's Mirror

Same task instructions

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

The judgment

Claude Haiku 5.5

The centered sphere, compact airborne black blob and differentiated cyan/crimson interaction support substantial state and placement credit. The few recognizable sphere and panel images establish limited optical relationships, but most of the required mirror system is missing. Rounded volume and localized paint warrant substantial material credit despite the soft, illustrative finish.

DeepSeek-V4.1-Flash-1017

Principal sphere and airborne-black placements are supported, and diminishing bilateral chains provide limited optical structure. Missing nested imagery, incomplete outer chains, distorted first images and sparse emitter recurrence remain the dominant weaknesses. Oversized paint bodies and unresolved cyan contact impose separate limitations.

Score breakdown

CategoryClaude Haiku 5.5DeepSeek-V4.1-Flash-1017
State at 600 ms25.0/2523.0/25
Camera and placement8.0/1513.5/15
Reflections24.5/12034.0/120
Materials and scale7.5/108.5/10
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

Claude Haiku 5.5

A coherent coral squid emblem with a compact mantle, restrained face and clean centered presentation. Its radial silhouette and floating placement work, but sharp arm tips, crowded roots and sparse surface modeling limit softness, construction and finish.

DeepSeek-V4.1-Flash-1017

An expressive, intricately drawn storybook scene with a complete flowing silhouette and differentiated glossy materials. The supported main lens and continuous shrimp body make the central interaction readable, but reciprocal eye lines, facial magnification and the smaller lens grip remain ambiguous. Bright granular fringes and crowded accessory lines limit the finish.

Score breakdown

CategoryClaude Haiku 5.5DeepSeek-V4.1-Flash-1017
Task & likeness6.5/107.5/10
Anatomy & construction4.0/107.5/10
Space & placement6.5/108.0/10
Light & reflections4.0/107.0/10
Purposeful detail3.5/107.5/10
Artistry & character3.5/108.0/10
Materials & effects4.5/107.5/10
Visual integrity7.0/106.5/10

Benchmark task

Claude Haiku 5.5

A coral squid with spreading arms tests connected anatomy, balanced composition and soft surface shading.

DeepSeek-V4.1-Flash-1017

A whale and a tiny shrimp examine one another through bubble lenses, with an octopus nearby. The scene tests interacting characters, differences in scale and transparent materials.

Mona Lisa

Same task instructions

Precise visual recall and portrait reconstruction.

The judgment

Claude Haiku 5.5

A recognizable but basic Mona Lisa reinterpretation. Clean contours and smooth facial lighting provide coherence and volume. Replication remains limited by the frontal pose, elongated neck, schematic expression, unresolved crossed hands and sparse landscape. Lighting is more successful than anatomical construction and purposeful detail.

DeepSeek-V4.1-Flash-1017

A coherent graphic interpretation with controlled contours, modeled facial volume and purposeful portrait details. Replication remains limited by the frontal pose, enlarged face, altered expression and ambiguous crossed hands. Landscape layering provides depth, while schematic fabric, smooth surfaces and tonal bands constrain the finish.

Score breakdown

CategoryClaude Haiku 5.5DeepSeek-V4.1-Flash-1017
Task & likeness3.0/105.0/10
Anatomy & construction4.0/105.0/10
Space & placement4.0/106.0/10
Light & reflections5.5/106.0/10
Purposeful detail2.5/105.5/10
Artistry & character3.5/105.5/10
Materials & effects2.5/105.5/10
Visual integrity5.5/106.0/10

Benchmark task

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

Beach

Same task instructions

Creativity, perspective and visual beauty.

The judgment

Claude Haiku 5.5

A cheerful, coherent beach illustration with attractive sunset colors, readable accessories and clean silhouettes. Its sun and sailboat reflections establish useful physical relationships. Simple animal construction, flattened foreground placement, sparse directional shadows and minimally differentiated surfaces limit its drawing refinement.

DeepSeek-V4.1-Flash-1017

A coherent, colorful beach illustration with controlled curves, clean layering and varied readable accessories. Castle details and small animal features strengthen its finish. Schematic airborne animals, uncertain board support, shallow architectural depth and decorative reflections limit physical coherence and drawing sophistication.

Score breakdown

CategoryClaude Haiku 5.5DeepSeek-V4.1-Flash-1017
Task & likeness8.5/107.0/10
Anatomy & construction6.5/105.5/10
Space & placement7.0/105.5/10
Light & reflections7.0/106.0/10
Purposeful detail7.0/106.5/10
Artistry & character6.0/105.0/10
Materials & effects6.0/105.5/10
Visual integrity8.5/104.5/10

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

Claude Haiku 5.5

This benchmark has not been assessed yet.

DeepSeek-V4.1-Flash-1017

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

Claude Haiku 5.5

A tidy, appealing cartoon with recognizable animals and a pleasing sunset palette. Steering lacks visible controls, while schematic limbs and uncertain raccoon support weaken the requested interaction. Shallow vehicle construction, flat character lighting and modest displacement limit physical coherence. Clean shapes and readable identifying details remain strengths.

DeepSeek-V4.1-Flash-1017

An appealing cartoon with recognizable riders, expressive faces and a cohesive twilight palette. Clean shapes support the composition, but ambiguous limb overlaps, weak seat contact and loosely resolved steering limit physical coherence. Lighting and water effects are decorative, with modest material differentiation and drawing complexity.

Score breakdown

CategoryClaude Haiku 5.5DeepSeek-V4.1-Flash-1017
Task & likeness4.0/108.0/10
Anatomy & construction3.5/107.0/10
Space & placement5.5/107.0/10
Light & reflections4.0/106.5/10
Purposeful detail5.5/107.0/10
Artistry & character4.5/107.0/10
Materials & effects5.5/106.5/10
Visual integrity4.5/108.0/10

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

Same task instructions

Subject construction and spatial relationships.

The judgment

Claude Haiku 5.5

A cheerful, recognizable illustration with clean contours and a balanced warm palette. Aligned wheels and readable frame geometry establish the bicycle, but shoulder construction, feet and steering contact remain imprecise. Sparse drivetrain detail, flat materials and absent grounding shadows limit anatomical and spatial conviction.

DeepSeek-V4.1-Flash-1017

An expressive, controlled illustration with continuous body construction, substantial bicycle detail and effective landscape depth. Unclear foot-to-pedal and wing-to-handlebar contacts limit physical conviction and local readability. Purposeful detail and composition are stronger than directional lighting and material treatment.

Score breakdown

CategoryClaude Haiku 5.5DeepSeek-V4.1-Flash-1017
Task & likeness8.0/108.5/10
Anatomy & construction5.5/107.0/10
Space & placement6.5/107.5/10
Light & reflections5.0/106.5/10
Purposeful detail6.0/107.5/10
Artistry & character5.0/107.0/10
Materials & effects5.0/107.0/10
Visual integrity8.0/107.5/10

Benchmark task

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