HuggingFace Agent Benchmark
Qwen-14B 93.5% leads since Sep 2023 Dropped Agents write Python code that calls Hugging Face Transformers tools to solve short tasks. Scores cover tool selection, tools used, and code correctness.
It shipped with Transformers Agents, which Hugging Face later replaced with smolagents.
- Level
- School Students, from grade school to high school
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Code A program or patch run against tests.
Qwen-14B leads with 93.5% among models released by Nov 2023
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
The newest model with a score here came out in Nov 2023, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 16 more
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
The best score passed 85% in Sep 2023
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Labs dropped it from launch posts once the best score passed 85%
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 25 Sep 2023 | Qwen-14B | 93.5 | HuggingFace Agent Benchmark - Run Mode, Tool Selection |
3 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 28 Sep 2023 | Qwen-7B technical report | 87 | Hugging Face Agent benchmark, Run Mode Tool Selection. Run Mode Tool Used 87.0, Code Correctness 71.5. Chat Mode 94.7 / 94.7 / 85.1 (Table 9) | Capabilities |
| 28 Sep 2023 | Qwen-14B technical report | 93.5 | Hugging Face Agent benchmark, Run Mode Tool Selection. Run Mode Tool Used 94.4, Code Correctness 87.0. Chat Mode 97.9 / 97.9 / 95.5 (Table 9) | Capabilities |
| 28 Sep 2023 | Qwen-1_8B technical report | 85.2 | Hugging Face Agent benchmark, Run Mode Tool Selection. Run Mode Tool Used 84.3, Code Correctness 61.1. Chat Mode 93.6 / 93.6 / 73.2 (Table 9) | Capabilities |
More in Tool use
- AutomationBench In use Agent completes end-to-end business workflows inside a simulated company exposing dozens of REST APIs. Graded on resulting state.
Gemini 4 Carbon 53.9% - MCP Atlas In use Multi-step workflows over real MCP servers. Scores tool-use competency on realistic tasks.
Muse Spark 1.1 88.1% - BFCL V4 In use Models call functions and tools, including multi-turn agentic tasks with web search and memory. Checked against expected calls and outcomes. Qwen3.7-Max 75%
- τ³-bench Banking In use Agents act as banking customer-service reps over many turns with a simulated user, following policy. Pass^1 on the final database state. Qwen 3.8 Max 55.1%
- Claw-Eval In use 300 human-verified agent tasks (service orchestration, multimodal, multi-turn dialogue) audited via traces and snapshots. Rubric scores with Pass^3 consistency. Claude Sonnet 4.6 81.4%
- DeepSearchQA In use Questions that need multi-step search and synthesis. Final answers graded against references. Kimi K3 95%