ComplexFuncBench
Hunyuan-A13B-Instruct 61.2% leads since Jun 2025 Dropped Models make function calls for 1,000 travel booking style samples that need several steps, user constraints, implicit parameter reasoning, long parameter values or 128K context.
The ComplexEval framework scores both the calls and the final answer.
In the authors’ words
Enhancing large language models (LLMs) with real-time APIs can help generate more accurate and up-to-date responses. However, evaluating the function calling abilities of LLMs in real-world scenarios remains under-explored due to the complexity of data collection and evaluation. In this work, we introduce ComplexFuncBench, a benchmark for complex function calling across five real-world scenarios. Compared to existing benchmarks, ComplexFuncBench encompasses multi-step and constrained function calling, which requires long-parameter filing, parameter value reasoning, and 128k long context. Additionally, we propose an automatic framework, ComplexEval, for quantitatively evaluating complex function calling tasks. Through comprehensive experiments, we demonstrate the deficiencies of state-of-the-art LLMs in function calling and suggest future directions for optimizing these capabilities. The data and code are available at https://github.com/THUDM/ComplexFuncBench.
- Level
- University Undergraduates and entry-level professionals
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Agent task Many steps in a terminal, browser, desktop, app, game or robot.
Hunyuan-A13B-Instruct leads with 61.2% among models released by Jun 2025
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 Jun 2025, 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
- 1 Hunyuan-A13B-Instruct 61.2%
- 2 GPT-4.1 mini 49.3%
- 3 GPT-4.1 nano 5.70%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Hunyuan-A13B-Instruct | 61.2% | Jun 2025 | Model card | |
| 2 | GPT-4.1 mini | 49.3% | Apr 2025 | Model card | |
| 3 | GPT-4.1 nano | 5.70% | Apr 2025 | Model card |
2 models have held number one since its release in Jan 2025
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
No launch post has listed it since Jun 2025
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 |
|---|---|---|---|
| 27 Jun 2025 | Hunyuan-A13B-Instruct | 61.2 | ComplexFuncBench |
| 14 Apr 2025 | GPT-4.1 nano | 5.7 | ComplexFuncBench |
| 14 Apr 2025 | GPT-4.1 mini | 49.3 | ComplexFuncBench |
One system card reports it
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 |
|---|---|---|---|---|
| 26 Jun 2025 | Hunyuan-A13B-Instruct technical report | 61.2 | ComplexFuncBench, slow-thinking (Table 3). Fast-thinking 74.0 (Table 4) | 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%