STEALTHMARK · HEAD TO HEAD
All comparisons ↗Callstack Apex vs Qwen3.8-Max-0902
Qwen3.8-Max-0902 leads Callstack Apex by 12.9 points on StealthMark, 62.4 to 49.5. Callstack Apex and Qwen3.8-Max-0902 each lead on 4 of the 8 benchmarks with results for both. Qwen3.8-Max-0902 leads Latch. Qwen3.8-Max-0902 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
Cost efficiency
How much Performance you get for your money.
BENCHMARK BY BENCHMARK
Where each model leads
- Callstack Apex
- Qwen3.8-Max-0902
- Other models
- Median
Games
SVG
DATASHEET
Specs and pricing
Callstack Apex is 1.7× cheaper per output token and runs 3.4× faster in our speed test. Qwen3.8-Max-0902 scores higher on StealthMark and takes 3.8× more context.
- Callstack Apex
- Qwen3.8-Max-0902
- Other models
- Median
- Developer
- CallstackQwen / Alibaba Cloud
- Released
- 1 Oct 20262 Sep 2026
- Origin
- PolandChina
- Input → output
- Text → textText, image → text
- Architecture
- Qwen foundation with Callstack domain post-training for React and React NativeMixture-of-Experts; hosted version based on the open Qwen3.8-2.4T-A95B
Full datasheets, every price and sourceCallstack Apex ↗Qwen3.8-Max-0902 ↗
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.
Qwen3.8-Max-0902 72.4/100Rank 5/54

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.
Callstack Apex 100.0/100Rank 47/551 of 5 levels

Qwen3.8-Max-0902 82.6/100Rank 7/55

Points per level
Newton's Mirror
Same task instructionsPhysics, perspective and recursive reflections, tested together. Explore the test ↗
Callstack Apex 32.7/100 Rank 28/58

Qwen3.8-Max-0902 44.7/100 Rank 14/58

The judgment
Callstack Apex
The principal sphere placement and paint contact sequence are supported. Isolated sphere and panel images provide limited optical structure, but missing lateral chains and side-floor continuations prevent a coherent repeating mirror room. The main and reflected spheres lack ordered curved nested imagery, while sparse planar emitter images and incomplete spherical emitter mapping leave most of the reflection system unsupported.
Qwen3.8-Max-0902
The central sphere and differentiated cyan/crimson interaction are supported. The tiny highlighted object above the sphere provides partial airborne-black evidence. The few isolated sphere and panel images preserve limited optical relationships, but most of the repeating mirror-room structure is missing. Core score: 64.5/170; including the floor-damage reward: 64.5/180.
Score breakdown
| Category | Callstack Apex | Qwen3.8-Max-0902 |
|---|---|---|
| State at 600 ms | 20.0/25 | 23.0/25 |
| Camera and placement | 13.0/15 | 12.0/15 |
| Reflections | 10.0/120 | 29.0/120 |
| Materials and scale | 7.0/10 | 8.0/10 |
| 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.
Callstack Apex 74.1/100 Rank 13/58

Qwen3.8-Max-0902 69.7/100 Rank 20/58

The judgment
Callstack Apex
The cheerful yellow bird, cream eyes, orange features and miniature teal console closely match the brief. Clean block edges, restrained colors and soft shadows create an appealing composition. The body reads more like a gridded disc than a fully cubic sphere, and the outlined left wing has limited volume. The right wing reaches the cyan block, though its grip is ambiguous.
Qwen3.8-Max-0902
A coherent ornamental illustration with balanced framing, appealing color and legible magical accessories. The disconnected raised wrist, incorrect raised-arm side and palm orientation, bear-like facial proportions and shallow material modeling limit execution. Clean decoration and compact spatial balance remain strengths.
Score breakdown
| Category | Callstack Apex | Qwen3.8-Max-0902 |
|---|---|---|
| Task & likeness | 8.5/10 | 7.5/10 |
| Anatomy & construction | 7.0/10 | 6.5/10 |
| Space & placement | 7.5/10 | 8.0/10 |
| Light & reflections | 7.5/10 | 7.0/10 |
| Purposeful detail | 7.5/10 | 7.5/10 |
| Artistry & character | 7.0/10 | 7.0/10 |
| Materials & effects | 7.0/10 | 7.5/10 |
| Visual integrity | 7.5/10 | 5.5/10 |
Benchmark task
Callstack Apex
A rounded bird built from small cubes explores a miniature machine. The scene tests block construction, expressive proportions, contact and soft lighting.
Qwen3.8-Max-0902
A floating capybara in ornate robes tests character anatomy, layered fabric and the placement of surrounding luminous forms.
Mona Lisa
Different task instructionsPrecise visual recall and portrait reconstruction.
Callstack Apex 45.9/100 Rank 25/58

Qwen3.8-Max-0902 45.1/100 Rank 26/58

The judgment
Callstack Apex
The framed portrait recalls Mona Lisa through dark hair, folded arms and a hazy landscape. Replication is limited by wide, staring eyes, an elongated neck and a downturned mouth. The overlapping hands lack convincing finger and wrist construction. Soft tonal shading suggests volume, but pervasive blur obscures clothing, landscape and anatomical detail.
Qwen3.8-Max-0902
A recognizable, cohesive Mona Lisa interpretation with readable landscape layers and a restrained expression. Continuous body construction and clean contours support readability, but broad hands, simplified drapery, frontal symmetry and limited facial volume keep the execution basic and uneven.
Score breakdown
| Category | Callstack Apex | Qwen3.8-Max-0902 |
|---|---|---|
| Task & likeness | 3.5/10 | 4.5/10 |
| Anatomy & construction | 4.0/10 | 3.5/10 |
| Space & placement | 4.5/10 | 5.0/10 |
| Light & reflections | 6.0/10 | 5.0/10 |
| Purposeful detail | 4.5/10 | 5.0/10 |
| Artistry & character | 4.5/10 | 5.0/10 |
| Materials & effects | 5.5/10 | 3.5/10 |
| Visual integrity | 5.5/10 | 5.0/10 |
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.
Callstack Apex 61.4/100 Rank 30/58

Qwen3.8-Max-0902 76.9/100 Rank 9/58

The judgment
Callstack Apex
A cohesive sunset beach illustration with lively wildlife, playful accents, and an appealing warm-to-purple palette. Palm framing and the aligned sun reflection organize the scene, while connected silhouettes keep the activities readable. Schematic joints, ambiguous dolphin junctions, loosely matched reflections, and repetitive surface marks limit construction, lighting coherence, and material depth.
Qwen3.8-Max-0902
A strong stylized beach illustration with coherent sunset color, lively dolphin arcs and balanced activity. Clean contours, readable ground contact and an aligned reflection support the finish. Schematic anatomy, sparse small-subject features, flat materials and repetitive water highlights limit physical depth and refinement.
Score breakdown
| Category | Callstack Apex | Qwen3.8-Max-0902 |
|---|---|---|
| Task & likeness | 8.5/10 | 8.5/10 |
| Anatomy & construction | 4.5/10 | 7.5/10 |
| Space & placement | 7.5/10 | 7.5/10 |
| Light & reflections | 5.5/10 | 8.0/10 |
| Purposeful detail | 7.5/10 | 7.0/10 |
| Artistry & character | 6.5/10 | 7.5/10 |
| Materials & effects | 7.0/10 | 6.5/10 |
| Visual integrity | 4.0/10 | 8.5/10 |
Benchmark task
A busy shoreline at sunset tests scene composition, animal forms and the relationship between light and water reflections.
Ground Truth
Same task instructionsPhysical reasoning, light and visual reconstruction.
Callstack Apex 44.1/100 Rank 22/58

Qwen3.8-Max-0902 58.0/100 Rank 14/58

The judgment
Callstack Apex
This benchmark has not been assessed yet.
Qwen3.8-Max-0902
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
Multiple instruction versionsScene composition and interacting subjects.
Callstack Apex 76.8/100 Rank 4/58

Qwen3.8-Max-0902 69.9/100 Rank 12/58

The judgment
Callstack Apex
The raccoon clearly rides the dog's back, and the dog's paws reach the jet ski controls. Expressive faces, a sweeping tail and a strong sunset composition give the illustration character. Limbs remain connected, but the dog's foreleg joints and vehicle seating are loosely constructed. Angular splashes convey speed more successfully than convincing water displacement; lighting and reflections remain decorative.
Qwen3.8-Max-0902
The riding arrangement and steering action are readable, supported by coherent visible attachments and useful character details. Clean shapes, strong color separation and clustered foam make the scene appealing and active. Stiff anatomy, crowded controls, limited directional lighting and simple surface treatments constrain sophistication.
Score breakdown
| Category | Callstack Apex | Qwen3.8-Max-0902 |
|---|---|---|
| Task & likeness | 9.0/10 | 8.0/10 |
| Anatomy & construction | 7.0/10 | 7.0/10 |
| Space & placement | 7.5/10 | 7.0/10 |
| Light & reflections | 7.0/10 | 6.5/10 |
| Purposeful detail | 8.5/10 | 7.0/10 |
| Artistry & character | 7.5/10 | 6.5/10 |
| Materials & effects | 7.0/10 | 6.0/10 |
| Visual integrity | 8.0/10 | 7.5/10 |
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.
Callstack Apex 76.8/100 Rank 9/58
Qwen3.8-Max-0902 72.0/100 Rank 19/58

The judgment
Callstack Apex
An appealing cartoon with a distinctive pelican, expressive eye, warm bill and carefully drawn bicycle wheels. The wing reaches the handlebar, but the feet do not clearly engage the pedals, weakening the riding mechanics. Layered hills create depth; limited ground shadows weaken contact. Clean curves and purposeful feather details give the illustration polish.
Qwen3.8-Max-0902
An appealing graphic illustration with a recognizable pelican, readable bicycle and clean coastal composition. Steering contact and one connected pedal support the action. Ambiguous neck-to-torso construction, an unclear opposing pedal connection, shallow space and limited material and lighting effects constrain its execution.
Score breakdown
| Category | Callstack Apex | Qwen3.8-Max-0902 |
|---|---|---|
| Task & likeness | 8.5/10 | 8.5/10 |
| Anatomy & construction | 6.5/10 | 6.5/10 |
| Space & placement | 7.5/10 | 7.0/10 |
| Light & reflections | 7.5/10 | 6.0/10 |
| Purposeful detail | 8.5/10 | 7.5/10 |
| Artistry & character | 8.0/10 | 7.5/10 |
| Materials & effects | 7.5/10 | 6.0/10 |
| Visual integrity | 8.0/10 | 8.0/10 |
Benchmark task
A cycling pelican tests anatomy, riding posture and contact between the bird and the bicycle.