Tax jurisdiction
Route each invoice through the business's tax mode, including destination pricing via the tax authority provider.
Leaderboard
September 2026- 1
Resolution rate: 38.8%Fable 5.1Claude Code - 2
Resolution rate: 33.8%GPT-6 AstraCodex CLI - 3
Resolution rate: 31.2%Gemini 3.8 FlashGemini CLI - 4
Resolution rate: 28.8%GLM 5.3Claude Code - =5
Resolution rate: 23.8%Grok 4.6Grok Build - =5
Resolution rate: 23.8%Muse Spark 1.3Muse Code - 7
Resolution rate: 18.8%Kimi K3Kimi Code - 8Resolution rate: 16.2%GPT-5.6 SolCodex CLI
| # | Model | Harness | Resolution rate |
|---|---|---|---|
| 1 | Fable 5.1 | Claude Code | 38.8% |
| 2 | GPT-6 Astra | Codex CLI | 33.8% |
| 3 | Gemini 3.8 Flash | Gemini CLI | 31.2% |
| 4 | GLM 5.3 | Claude Code | 28.8% |
| =5 | Grok 4.6 | Grok Build | 23.8% |
| =5 | Muse Spark 1.3 | Muse Code | 23.8% |
| 7 | Kimi K3 | Kimi Code | 18.8% |
| 8 | GPT-5.6 Sol | Codex CLI | 16.2% |
We use native harnesses to reflect how enterprise engineers work in practice, evaluating model-and-harness combinations rather than models in isolation.
Private codebases
Agents must navigate proprietary systems whose code and solutions aren’t available on the public internet.
Work with business consequences
Getting billing right, calculating taxes, migrating customers. Changes that affect how a business runs, often across multiple services.
Company-specific complexity
Every company has its own rules and ways of writing code. Agents have to understand those conventions and make changes that work with what’s already there.
Task examples
View analysisMulti-region sweep
Discover every enabled AWS region and sweep block-storage inventory without one bad region collapsing the rest.
Customer identity migration
Move ownership of offerings and usage from services to customers without breaking existing reads.
Evaluation setup
Each agent was run in an isolated sandbox. All tasks are in Harbor format, and verifiers are injected at grading time. The verifiers are inspired by existing test suites in the codebase or use those tests verbatim.
Read the full analysis