Agents / Benchmark profile
An occupational agent benchmark for professional workflows that workers say they most want delegated to AI.
Observed results
20 ranked models · higher is better · labels show rank and score
| Model | Rank | Model ID | Provider | Score | Unit |
|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | #1 | qwen-3-8-flash-next | Alibaba Cloud | 55.7 | percent |
| Muse Spark 1.1 | #2 | muse-spark-1-1 | Meta | 54.7 | percent |
| Qwen3.8 Max | #3 | qwen-3-8-max | Alibaba Cloud | 53.4 | percent |
| Kimi K3 | #4 | kimi-k3 | Moonshot AI | 52.9 | percent |
| Claude Opus 4.7 | #5 | claude-opus-4-7 | Anthropic | 45.9 | percent |
| GPT-5.5 | #6 | gpt-5-5 | OpenAI | 42.7 | percent |
| GPT-5.4 | #7 | gpt-5-4 | OpenAI | 38.9 | percent |
| Claude Sonnet 4.6 | #8 | claude-sonnet-4-6 | Anthropic | 36.9 | percent |
| Claude Opus 4.6 | #9 | claude-opus-4-6 | Anthropic | 36.7 | percent |
| GPT-5.2 | #10 | gpt-5-2 | OpenAI | 34.3 | percent |
| GPT-5.3-Codex | #11 | gpt-5-3-codex | OpenAI | 33.7 | percent |
| Qwen3.8-27B | #12 | qwen-3-8-27b | Alibaba Cloud | 33.4 | percent |
| Claude Opus 4.5 | #13 | claude-opus-4-5 | Anthropic | 32.3 | percent |
| Claude Sonnet 4.5 | #14 | claude-sonnet-4-5 | Anthropic | 27.7 | percent |
| GPT-5.1-Codex | #15 | gpt-5-1-codex | OpenAI | 26.2 | percent |
| GPT-5.2 Codex | #16 | gpt-5-2-codex | OpenAI | 26 | percent |
| Claude 4.1 Opus | #17 | claude-4-1-opus | Anthropic | 21.9 | percent |
| Qwen3.5 Plus | #18 | qwen3-5-plus | Alibaba Cloud | 18.5 | percent |
| Claude 4 Sonnet | #19 | claude-4-sonnet | Anthropic | 18.4 | percent |
| Claude Haiku 4.5 | #20 | claude-haiku-4-5 | Anthropic | 16 | percent |
| Gemini 3 Flash | #21 | gemini-3-flash | 11.4 | percent | |
| Kimi K2.5 | #22 | kimi-k2-5 | Moonshot AI | 8.73 | percent |
| GPT-5 | #23 | gpt-5 | OpenAI | 8.53 | percent |
One best compatible score per canonical product · higher is better
| Rank | Model | Weights | Evidence | Score |
|---|---|---|---|---|
| 01 | Qwen3.8-Flash-NextAlibaba Cloud | Open weights | Public reference | 55.7% |
| 02 | Muse Spark 1.1Meta | Closed weights | Source carrier | 54.7% |
| 03 | Qwen3.8 MaxAlibaba Cloud | Open weights | Public reference | 53.4% |
| 04 | Kimi K3Moonshot AI | Open weights | Source carrier | 52.9% |
| 05 | Claude Opus 4.7Anthropic | Closed weights | Source carrier | 45.9% |
| 06 | GPT-5.5OpenAI | Closed weights | Source carrier | 42.7% |
| 07 | GPT-5.4OpenAI | Closed weights | Source carrier | 38.9% |
| 08 | Claude Sonnet 4.6Anthropic | Closed weights | Source carrier | 36.9% |
| 09 | Claude Opus 4.6Anthropic | Closed weights | Source carrier | 36.7% |
| 10 | GPT-5.2OpenAI | Closed weights | Source carrier | 34.3% |
Each distinct published measurement is retained. Same-snapshot canonical and configuration projections appear once.
| Published model / configuration | Score | Evidence & protocol | Source & dates |
|---|---|---|---|
Qwen3.8-Flash-Next (xhigh default thinking configuration)Qwen3.8-Flash-NextExact identityqwen-3-8-flash-next-xhigh Canonical product: qwen-3-8-flash-next | 55.7% | Public referencesource-checkedVersion & system2026 system:qwen3-8-flash-next:jobbench | Qwen3.8-Flash-Next current official launch pageObserved Checked |
DeepSeek-V4-Flash-0731 (provider-published configuration) as published in Qwen's Qwen3.8-Flash-Next comparison tableDeepSeek V4 Flash 0731Exact identitydeepseek-v4-flash-0731-deepseek-0813-release-unspecified Canonical product: deepseek-v4-flash-0731 | 41.3% | Relative comparisonprovider-reportedVersion & system2026 system:qwen3-8-flash-next-comparison:cell:language:jobbench:3 | Qwen3.8-Flash-Next launch and official provider evaluationsObserved Checked |
Claude Opus 4.6 (Max) as published in Qwen's Qwen3.8-Flash-Next comparison tableClaude Opus 4.6Exact identityclaude-opus-4-6-max Canonical product: claude-opus-4-6 | 36.6% | Relative comparisonprovider-reportedVersion & system2026 system:qwen3-8-flash-next-comparison:cell:language:jobbench:4 | Qwen3.8-Flash-Next launch and official provider evaluationsObserved Checked |
Qwen3.8-27B (xhigh default thinking configuration) as published in Qwen's Qwen3.8-Flash-Next comparison tableQwen3.8-27BExact identityqwen-3-8-27b-xhigh Canonical product: qwen-3-8-27b | 33.4% | Relative comparisonprovider-reportedVersion & system2026 system:qwen3-8-flash-next-comparison:cell:language:jobbench:1 | Qwen3.8-Flash-Next launch and official provider evaluationsObserved Checked |
Qwen3.7-Plus (provider-published configuration) as published in Qwen's Qwen3.8-Flash-Next comparison tableQwen3.7-PlusExact identityqwen-3-7-plus-unspecified Canonical product: qwen-3-7-plus | 27.6% | Relative comparisonprovider-reportedVersion & system2026 system:qwen3-8-flash-next-comparison:cell:language:jobbench:2 | Qwen3.8-Flash-Next launch and official provider evaluationsObserved Checked |
Qwen3.8-27B (xhigh)Qwen3.8-27BExact identityqwen-3-8-27b-xhigh Canonical product: qwen-3-8-27b | 33.4% | Public referenceprovider-reportedVersion & system2026 Qwen3.8-27B official text table | Qwen3.8-27B official model cardObserved Checked |
Qwen3.7-Plus as published by QwenQwen3.7-PlusExact identityqwen-3-7-plus-unspecified Canonical product: qwen-3-7-plus | 27.6% | Relative comparisonprovider-reportedVersion & system2026 Qwen3.8-27B official text table | Qwen3.8-27B official model cardObserved Checked |
Qwen3.6-27B as published by QwenQwen3.6 27BExact identityqwen3-6-27b-default Canonical product: qwen3-6-27b | 21.8% | Relative comparisonprovider-reportedVersion & system2026 Qwen3.8-27B official text table | Qwen3.8-27B official model cardObserved Checked |
Qwen3.8 Max (xhigh, default reasoning effort)Qwen3.8 MaxExact identityqwen-3-8-max-xhigh Canonical product: qwen-3-8-max | 53.4% | Public referenceprovider-reportedVersion & system2026 Qwen provider evaluation | Qwen3.8 Max official releaseObserved Checked |
Exact BenchLM registry variant Muse Spark 1.1; bulk export does not retain a complete upstream harness configuration.Muse Spark 1.1Exact identitySource label without a registered configuration ID Canonical product: muse-spark-1-1 | 54.7% | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
From result to context
An occupational agent benchmark for professional workflows that workers say they most want delegated to AI.
The summary shows one best compatible source result per canonical product. Versions, effort settings and execution systems remain attached to the underlying records.
Scores from different versions or harnesses may not be interchangeable. The published source rows preserve those distinctions and their original units. A source result is not automatically an input to a current index.
This catalogue entry preserves available source evidence. Current indices admit only their specifically reviewed tracks and configurations.
Contamination risk: Unknown. Lifecycle: Active.
