STEALTHMARK · HEAD TO HEAD
All comparisons ↗LongCat-2.0 vs Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) leads LongCat-2.0 by 37.1 points on StealthMark, 62.6 to 25.5. It leads on 6 of the 7 benchmarks with results for both and LongCat-2.0 on 1. Union Alpha scores higher on Newton's Mirror, with its largest category advantage in reflections.
See the difference ↘Overall StealthMark
General Intelligence
Visual Intelligence
Reasoning efficiency
How many reasoning tokens a model needs for the quality it delivers.
Single-step reasoning How much it reasons to understand a task
Multi-step reasoning How much it keeps reasoning as a task goes on
- LongCat-2.0Multi-step reasoning not measured
- Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)Not measured
Cost efficiency
How much Performance you get for your money.
BENCHMARK BY BENCHMARK
Where each model leads
- LongCat-2.0
- Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
- Other models
- Median
Games
SVG
DATASHEET
Specs and pricing
LongCat-2.0 takes 3.8× more context and runs 3.4× faster in our speed test. Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) scores higher on StealthMark.
- LongCat-2.0
- Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
- Other models
- Median
- Developer
- MeituanCircuit & Chisel / Unbiased
- Released
- Not published20 Sep 2026
- Origin
- ChinaUnited States
- Input → output
- Text → textText, image → text
- Architecture
- Mixture-of-Experts with LongCat Sparse AttentionNot published
Full datasheets, every price and sourceLongCat-2.0 ↗Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) ↗
Foresight
Play Foresight yourselfAnticipating 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.
Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) 78.7/100Rank 1/54

Points per level
Latch
Play Latch yourselfCooperative 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.
LongCat-2.0No run
Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) 36.5/100Rank 37/55

Points per level
Newton's Mirror
Same task instructionsPhysics, perspective and recursive reflections, tested together. Explore the test ↗
LongCat-2.0 23.1/100 Rank 40/58

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) 52.0/100 Rank 8/58

The judgment
LongCat-2.0
Cyan lies on the sphere's facing middle rather than showing its recent interaction near the apex. Separate airborne black and elongated crimson support part of the timing sequence. Small side images and an overlapping lower image provide limited reflection ordering, but recursive room structure, nested imagery and emitter mappings are largely absent. The main sphere is smaller and higher in the frame than prescribed, and the surfaces have a soft, matte appearance.
Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
Recognizable near-field sphere placement and bilateral convergence provide limited optical structure. Broad gray regions interrupt lateral sightlines and truncate side-floor images. Missing outer chains, absent nested sphere imagery and incomplete planar and curved emitter mappings dominate the reflection system.
Score breakdown
| Category | LongCat-2.0 | Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) |
|---|---|---|
| State at 600 ms | 9.5/25 | 24.0/25 |
| Camera and placement | 6.5/15 | 13.5/15 |
| Reflections | 12.5/120 | 34.5/120 |
| Materials and scale | 5.5/10 | 10.0/10 |
| Floor-damage reward | 0.0/10 | 0.0/10 |
Benchmark task
A spinning metal sphere and paint in a mirrored room test physical reasoning, perspective and consistency across repeated reflections.
Selfie
Different task instructionsVisual construction and creative interpretation.
LongCat-2.0 61.6/100 Rank 31/58

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) 76.5/100 Rank 6/58

The judgment
LongCat-2.0
Amber slit eyes, a pointed beak, cream feathers and gold-trimmed black clothing establish the secretive owl rogue. The head appears frontal rather than lowered, with much of the face exposed. The centered silhouette is effective, but stiff cloak geometry, shallow facial modeling and extremely dark clothing limit depth and finish. Sparse gold markings suggest the requested circuitry only loosely.
Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
A strong futuristic emblem with clear hierarchy, controlled negative space and distinctive typography. Silver and gunmetal layers give the sweeping ribbons convincing graphic depth, while red accents remain restrained. Ambiguous concealed connections and occasionally abrupt highlight bands limit the construction and material realism.
Score breakdown
| Category | LongCat-2.0 | Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) |
|---|---|---|
| Task & likeness | 7.0/10 | 9.0/10 |
| Anatomy & construction | 6.0/10 | 7.5/10 |
| Space & placement | 6.0/10 | 8.5/10 |
| Light & reflections | 5.5/10 | 7.5/10 |
| Purposeful detail | 6.0/10 | 7.0/10 |
| Artistry & character | 6.5/10 | 7.5/10 |
| Materials & effects | 5.5/10 | 7.5/10 |
| Visual integrity | 6.5/10 | 7.0/10 |
Benchmark task
LongCat-2.0
A cloaked owl with luminous eyes tests expression, fabric folds and the separation of dark forms.
Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
An interwoven metallic emblem tests ribbon geometry, overlapping forms and the appearance of reflective metal against a dark background.
Mona Lisa
Different task instructionsPrecise visual recall and portrait reconstruction.
LongCat-2.0 4.1/100 Rank 54/58

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) 59.1/100 Rank 8/58

The judgment
LongCat-2.0
The centered portrait, slight smile, overlapping hands and distant landscape suggest Mona Lisa, but replication is weak. The face has little volume, the shoulders and torso form a narrow wedge, and the hands are fingerless ovals with unresolved wrists. Broad gray background bands provide limited depth. A bright head rim and pale hands contrast with an almost featureless dark figure.
Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
The centered portrait, folded hands, dark clothing and hazy landscape clearly evoke the Mona Lisa. Muted colors and soft facial shading create a coherent illustration, but replication remains schematic: the face is broad, eyes outlined, smile simplified and overlapping fingers poorly resolved. Angular landscape shapes and flat fabric limit depth and painterly richness.
Score breakdown
| Category | LongCat-2.0 | Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) |
|---|---|---|
| Task & likeness | 0.5/10 | 6.5/10 |
| Anatomy & construction | 0.5/10 | 5.0/10 |
| Space & placement | 0.5/10 | 6.5/10 |
| Light & reflections | 0.5/10 | 6.0/10 |
| Purposeful detail | 0.0/10 | 5.5/10 |
| Artistry & character | 0.5/10 | 6.5/10 |
| Materials & effects | 0.0/10 | 5.0/10 |
| Visual integrity | 0.5/10 | 7.0/10 |
Benchmark task
An SVG interpretation of the Mona Lisa tests facial likeness, anatomy and the composition of a familiar portrait.
Beach
Different task instructionsCreativity, perspective and visual beauty.
LongCat-2.0 54.4/100 Rank 41/58

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) 71.5/100 Rank 16/58

The judgment
LongCat-2.0
The sunset, palms, birds and beach animals create a cheerful, readable scene. Clean silhouettes and a vivid sky establish the composition, but construction remains schematic. The right palm appears rooted in open water, shadows have limited connection to the sunset, and the sun’s reflection consists of rigid bands. Small creatures and beach equipment are recognizable but minimally developed.
Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
A cohesive sunset palette, sweeping shoreline and playful animals make an appealing beach illustration. The sun’s reflection establishes a clear focal axis, balanced by the palm and umbrella. Clean silhouettes and small decorative features reward inspection, though simplified anatomy, repetitive reflection bars and generic oval shadows limit volume and naturalism.
Score breakdown
| Category | LongCat-2.0 | Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) |
|---|---|---|
| Task & likeness | 7.5/10 | 9.0/10 |
| Anatomy & construction | 5.5/10 | 7.0/10 |
| Space & placement | 5.5/10 | 8.0/10 |
| Light & reflections | 6.0/10 | 7.0/10 |
| Purposeful detail | 5.0/10 | 7.0/10 |
| Artistry & character | 5.0/10 | 6.0/10 |
| Materials & effects | 3.0/10 | 6.5/10 |
| Visual integrity | 4.0/10 | 7.0/10 |
Benchmark task
A busy shoreline at sunset tests scene composition, animal forms and the relationship between light and water reflections.
Ground Truth
Same task instructionsPhysical reasoning, light and visual reconstruction.
LongCat-2.0 12.9/100 Rank 55/58

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) 63.3/100 Rank 9/58

The judgment
LongCat-2.0
This benchmark has not been assessed yet.
Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
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 instructionsScene composition and interacting subjects.
LongCat-2.0 42.6/100 Rank 46/58

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) 68.7/100 Rank 18/58

The judgment
LongCat-2.0
The raccoon is recognizable and expressive, with a clear mask and striped tail. The dog's anatomy is poorly resolved, and the flattened craft lacks convincing steering and seating. Feet extend below the hull, weakening the sense of support. An appealing palette, clean shapes and decorative water effects give the illustration some polish.
Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
Expressive animals, a readable riding arrangement and sweeping spray create an appealing cartoon. The raccoon sits convincingly on the dog's back, but the dog's paw does not clearly grip the handlebar, whose connection to the hull is unresolved. Flat lighting provides little volume or reflection. A dark rectangular strip interrupts the upper-right background.
Score breakdown
| Category | LongCat-2.0 | Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) |
|---|---|---|
| Task & likeness | 4.0/10 | 8.0/10 |
| Anatomy & construction | 3.0/10 | 6.5/10 |
| Space & placement | 4.5/10 | 7.5/10 |
| Light & reflections | 5.5/10 | 5.5/10 |
| Purposeful detail | 6.0/10 | 7.0/10 |
| Artistry & character | 3.0/10 | 7.0/10 |
| Materials & effects | 5.5/10 | 7.5/10 |
| Visual integrity | 5.0/10 | 7.0/10 |
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 instructionsSubject construction and spatial relationships.
LongCat-2.0 79.0/100 Rank 3/58

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) 67.0/100 Rank 25/58

The judgment
LongCat-2.0
A clearly recognizable pelican cycles through a well-composed coastal sunset. Warm colors, flowing scarf, feather contours and bicycle details give the illustration character. The legs connect to the body, but the farther foot's pedal contact and the wing's handlebar grip remain ambiguous. Clean vector shapes provide polish, with limited material texture and directional shading.
Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
The pelican is immediately recognizable, with an expressive face, convincing bill silhouette and appealing pastel composition. Both legs connect to feet, and the wing reaches the handlebar. Bicycle construction is less resolved: the far pedal lacks a clear crank connection and no chain is visible. Clean contours and orderly spokes support the illustration, while flat lighting and simplified surfaces limit depth.
Score breakdown
| Category | LongCat-2.0 | Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) |
|---|---|---|
| Task & likeness | 8.5/10 | 8.0/10 |
| Anatomy & construction | 7.0/10 | 6.0/10 |
| Space & placement | 8.0/10 | 7.0/10 |
| Light & reflections | 7.5/10 | 6.0/10 |
| Purposeful detail | 8.0/10 | 6.0/10 |
| Artistry & character | 8.5/10 | 6.0/10 |
| Materials & effects | 7.0/10 | 6.0/10 |
| Visual integrity | 8.5/10 | 8.5/10 |
Benchmark task
A cycling pelican tests anatomy, riding posture and contact between the bird and the bicycle.