aiaimodel.cards
← All benchmarks

OSWorld-Verified

Operating a real desktop through screenshots, mouse and keyboard to finish tasks across common apps.

Your workloadRAG over docs · 12K in · 600 out · 50K requests/mo · 30% cached
  1. 1Claude Fable 5 · Anthropicbest value
    85.0%
  2. 2Qwen3.8-27B · Alibababest value
    84.3%
  3. 3Claude Opus 4.8 · Anthropic
    83.4%
  4. 4Gemini 3.6 Flash · Google
    83.0%
  5. 5Claude Sonnet 5 · Anthropic
    81.2%
  6. 6Muse Spark 1.1 · Meta
    80.8%
  7. 7Gemini 3.5 Flash-Lite · Googlebest value
    74.0%
  8. 8Claude Opus 4.6 · Anthropic
    72.7%
  9. 9Claude Sonnet 4.6 · Anthropic
    72.5%
  10. 10Muse Glimmer 30B · Meta
    65.9%

“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

  • Claude Fable 5 Table 8.1.A, p.251–252

    Rows where the card reports a Fable 5 score. Fable 5 scores include production safeguards and fallback to Opus 4.8, so some are slightly below Mythos 5. Mythos 5 uses adaptive thinking at max effort, averaged over 5 trials. Some Fable rows were run by external evaluators (Surge, Andon Labs, Artificial Analysis, Databricks, Zapier, Harvey). Terminal-Bench 2.1 GPT-5.5 is with Codex CLI, Gemini with Gemini CLI. GDPval-AA Elo as of 6 Jun 2026. Competitor figures from developers' published results or leaderboards. Competitor values for AutomationBench, OfficeQA Pro and Harvey are left blank: they couldn't be matched to columns reliably from the PDF.

  • 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).

  • Claude Opus 4.8 Table 8.1.A, p.194–195

    Opus 4.8 uses adaptive thinking at max effort with default sampling, averaged over 5 trials. Competitor figures come from the developers' own published cards or leaderboards.

  • Gemini 3.6 Flash p.4 (table also on the model card web page)

    Results as of July 2026, as published in Google's model card. Competitor figures are as listed by Google.

  • Claude Sonnet 5 Table 8.1.A, p.115–116; SWE-bench variants §8.2, p.116

    Claude Sonnet 5 results use adaptive thinking at max effort, averaged over five trials. BrowseComp is the single-agent score (86.6% multi-agent) with a 10M-token limit and compaction. GPT-5.5 Terminal-Bench 2.1 figure uses Codex CLI. Competitor figures come from the developers' own published results.

  • Muse Spark 1.1 model page; report §5

    Highest reasoning effort for every model (high for Gemini 3.1 Pro, max for Opus 4.8). "Muse Spark (1.0)" is the earlier model. Third-party scores are Meta's best-effort runs.

  • Gemini 3.5 Flash-Lite p.4

    Results as of July 2026, as published in Google's model card. Competitor figures are as listed by Google.

  • Claude Opus 4.6 Table 2.3.A, p.18

    Opus 4.6 results average 5 trials (SWE-bench: 25) with adaptive thinking at max effort and default sampling. MCP-Atlas is the max-effort score (62.7% at high). Gemini 3 Pro ARC-AGI-2 is Deep Thinking.

  • Claude Sonnet 4.6 Table 2.1.A, p.15

    Claude Sonnet 4.6 results are averaged over 10 trials (SWE-bench over 25) with adaptive thinking at max effort and default sampling; Terminal-Bench 2.0 at default thinking. ARC-AGI-2 is 60.4% at high effort. Competitor columns as reported in the card.

  • Muse Glimmer 30B Benchmarks

    Meta's own results. Muse Glimmer at high reasoning; Gemma4-31B and Qwen3.6-27B in thinking mode. GDPVal-AA v2 is an Elo-style score.

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