qwen3.8-flash real-task evaluations

Every report keeps its original task, method, finding, limitation, evaluator identity and verification date. A community report is evidence about that run, not a universal score.

  • RemakeBench Launch 005: four Flash models on 14 fixtures

    By RemakeBench (@remakebench). Benchmark channel that publishes per-fixture clips, costs, wall-clock times and validation notes Published 2026-09-18; retrieved 2026-09-24; verified 2026-09-24.

    Task
    Fourteen fixtures spanning game building, 3D scenes, CAD, drawing and robot control, run on Qwen 3.8 Flash, DeepSeek V4.1 Flash, GLM 5.3 Flash and Gemini 3.8 Flash
    Method
    Each model's attempt per fixture is shown as a video clip with its displayed cost, wall-clock time and reasoning setting; pass/fail labels are the lab's video judgments.
    Finding
    No model won overall. The lab's editorial preference put Qwen 3.8 Flash ahead in several game and 3D-scene rounds, such as the interactive voxel diorama, but it did not pass the single-turn Rubik's Cube ($0.2616, 48 min 35 s) and timed out on Turbofan CAD without any geometry.
    Limitation
    Pass/fail labels are video judgments without a machine-readable validator, and single attempts do not establish reliability; the lab publishes no aggregate score or overall winner. Two Qwen results are still pending a judge, and its reasoning setting is unreported outside the campaign runs.

  • AI Coding Daily LLM Coding Leaderboard

    By AI Coding Daily (@AICodingDaily). Coding-model testing channel and website that runs its own leaderboard and sells premium tutorials and channel advertising Published 2026-09-24; retrieved 2026-09-24; verified 2026-09-24.

    Task
    Implement and harden production-shaped projects in several stacks, including a Laravel app, a Go service and a React/TypeScript app, from the same prompts
    Method
    Each model and reasoning setting is a separate row run in a coding harness, with the average cost and time per run. Code quality is graded by a judge model against a published 100-point rubric and scaled to 20 points per project; behavioural reliability runs each of four projects five times and scores the checks every attempt fails.
    Finding
    Qwen 3.8 Flash at max reasoning scored 47.22 ($0.04 and 8 min 38 s per run in OpenCode), 28th of 47 rows.
    Limitation
    One author's benchmark whose code-quality half is graded by a judge model; rows run in different harnesses, the page is updated as models are added (read on 2026-09-24, 47 rows), and the author sells premium tutorials and advertising.

  • kzhu's six-question LLM test leaderboard

    By AI产品狙击手 kzhu (@kevinzhu9305). Chinese YouTube reviewer who scores models on a six-question test and publishes every score with per-question notes Published 2026-09-24; retrieved 2026-09-24; verified 2026-09-24.

    Task
    Six questions scored out of 10: constrained sentence writing, two reasoning puzzles (replaced by pelican and compound-bow SVG animations in version 2.2), a browser OS with a space shooter, a 3D racing game and a Trello-style board
    Method
    Each row names the harness the model ran in (Pi, Claude Code, WorkBuddy and others) and the date; the author scores every question with a note, and warns that totals are only comparable within one test version.
    Finding
    Qwen 3.8 Flash scored 51/60 on version 2.1 in Claude Code: both maths puzzles right, but many small coding flaws, such as an overflowing browser-OS pop-up, a racing game that ends on the first crash and off-centre Trello buttons.
    Limitation
    One author's scores on six questions; rows use different harnesses and test versions (2.1 or 2.2), and a few rows' table total differs by one point from the author's note.