JobBench
Citation frequency 2/3
- What does it measure?
- Tests how well an AI agent (an AI that uses tools to carry out a task end to end) performs tasks close to real workplace work.
- Who evaluates it, and how?
- 65 tasks drawn from 35 occupations, which the AI completes with tools. Grading criteria also inspect the output files. The maintainers run every model in the same OpenCode environment.
- Reading the score
- Scores run from 0 to 100%. Higher is better.
Top score75.4%
Models tested30
Scoring basisHigher is better
Last updated2026.09.22
Model release date
Can it pull scattered facts from several long documents into one answer?Long Context Reasoning
Kimi K3🥇
Kimi K3🥇Long Context Reasoning
Kimi K3🥇Can it read tables and reshape them as needed?LiveBench 2.0 Data Analysis
Gemini 4 Argon🥇
Gemini 4 Argon🥇LiveBench 2.0 Data Analysis
Gemini 4 Argon🥇Which AI gives the business answers people prefer most?Arena Business, Management & Finance
Gemini 4 Argon🥇
Gemini 4 Argon🥇Arena Business, Management & Finance
Gemini 4 Argon🥇
Can it do real work from many different jobs?
JobBench
- 🥇AnthropicClaude Opus 5.575.4%
- 🥈MetaMuse Wonder75.3%
- 🥉AnthropicClaude Fable 5.173.1%
- #4OpenAIGPT-6 Astra66.1%
- #5AnthropicClaude Opus 565.7%
- #6MetaMuse Spark 1.364.9%
- #7XiaomiMiMo-V2.6-Pro62.0%
- #8TencentHy4Reasoning effort: Max61.7%
- #9MetaMuse Spark 1.261.6%
- #10Z.aiGLM 5.361.4%
- #11XiaomiMiMo-V2.6-Flash61.2%
- #12StepfunStep-5Reasoning effort: High59.0%
- #13AnthropicClaude Fable 557.4%
- #14AlibabaQwen3.8 Flash55.7%
- #15MetaMuse Spark 1.154.7%
- #16Moonshot AIKimi K354.3%
- #17AnthropicClaude Opus 4.848.4%
- #18OpenAIGPT-5.6 Sol45.4%
- #19AnthropicClaude Opus 4.744.5%
- #20Z.aiGLM 5.243.4%
- #21OpenAIGPT-5.538.3%
- #22AnthropicClaude Sonnet 4.636.6%
- #23OpenAIGPT-5.432.2%
- #24GoogleGemini 3.5 Flash31.5%
- #25AlibabaQwen3.7 Plus27.6%
- #26NVIDIANemotron 3 Ultra27.2%
- #27XiaomiMiMo V2.5 Pro25.0%
- #28AnthropicClaude Sonnet 4.520.7%
- #29MetaMuse Spark17.0%
- #30GoogleGemini 3.1 Pro15.9%
Half of models ≤ 54.5%
The "harness" is the agent program the AI used to carry out the task. The same model can score very differently depending on its harness and reasoning effort.