aiaimodel.cards
← All benchmarks

HLE

We haven't written a description for this benchmark yet; see the card notes below for how each maker ran it.

Your workloadRAG over docs · 12K in · 600 out · 50K requests/mo · 30% cached
  1. 1Qwen3.8-Max · Alibababest value
    43.6%
  2. 2Qwen3.8-Flash · Alibababest value
    35.9%
  3. 3Qwen3.7-Plus · Alibaba
    34.7%
  4. 4Qwen3.8-27B · Alibaba
    30.8%

“Best value”: no other model here reports a higher score at a lower cost for your workload. Scores are self-reported by each maker with different settings, so treat close calls as ties.

How each maker reported it

  • Qwen3.8-Max model card (Benchmark Results)

    Qwen's own table. Terminal Bench 2.1 run with Claude Code (avg@10); competitor scores are the best published across harnesses. SWE-bench Pro uses a corrected task set. Rows marked in-house are Qwen benchmarks. Fable 5 results may involve fallbacks. Agents' Last Exam is split into pass rate and score.

  • Qwen3.8-Flash model card (Benchmark Results)

    Qwen's own tables. SWE tasks use Claude Code or mini-SWE-agent at temperature 1.0 and 256K context; HLE judged by GPT-4o. OSWorld 2.0 and two-setting rows are split. DeepSeek-V4-Flash is not in the vision table.

  • Qwen3.7-Plus Qwen3.8-Flash-Next model card (Benchmark Results)

    Qwen published Qwen3.7-Plus scores as a comparison column in its Qwen3.8 cards. The Qwen3.8-27B card reports slightly different Qwen3.7-Plus numbers for some rows (e.g. SWE-bench Pro 57.6, DeepSWE 14.2).

  • Qwen3.8-27B model card (Text Performance, VL Performance)

    Qwen's own tables. SWE-bench Pro uses Claude Code on a corrected task set (Opus 4.6 is its published score). HLE judged by GPT-4o. Muse Glimmer-30B's CharXiv cell (78.8) does not say which setting, so it is left out. Qwen3.7-Plus figures here differ slightly from the Flash-Next card (e.g. SWE-bench Pro 57.6 vs 55.8).

Only each model's own maker's number is shown; scores a maker reports for rival models are left out.