---
id: finish-reason-by-model-october-2026
slug: finish-reason-mix-by-model-october-2026
title: "finish_reason mix per model, October 2026"
topic: agentic
period: Oct 2026
updated: 2026-11-11
license: CC BY 4.0
canonical: https://www.requesty.ai/data/finish-reason-mix-by-model-october-2026
---

# finish_reason mix per model, October 2026

> Which models are used most for tool calling? In October 2026 deepseek-v4.1-flash-1017 ended 73% of successful completions with tool_calls, the highest among the busiest models. gpt-4.1-mini was at 0%, used almost entirely for plain completions.

*Topic: Agentic workloads. Period: Oct 2026. Last updated 2026-11-11.*

## Why it matters

Models with a high tool_calls share are the ones teams run inside agents. A low share points to chat, extraction or batch use.

## Questions this answers

- Which LLM is used most for tool calling?
- What is the finish_reason mix by model?
- Which models are used for agents?

## Key findings

1. deepseek-v4.1-flash-1017: 73% tool_calls.
2. gemini-3.8-flash: 63% tool_calls.
3. deepseek-v4.1-flash: 58% tool_calls.
4. glm-5.3-flash: 48% tool_calls.
5. gpt-6-luna: 27% tool_calls.

## Data

| Model | tool_calls (percent) | stop (percent) | length (percent) |
| --- | --- | --- | --- |
| deepseek-v4.1-flash-1017 | 72.88% | 25.57% | 1.55% |
| gemini-3.8-flash | 63.13% | 34.99% | 1.88% |
| deepseek-v4.1-flash | 57.78% | 40.56% | 1.66% |
| glm-5.3-flash | 48.34% | 43.74% | 7.92% |
| gpt-6-luna | 27.17% | 72.30% | 0.53% |
| claude-opus-5-5 | 25.20% | 72.76% | 2.03% |
| gpt-5.6-luna | 24.76% | 74.59% | 0.65% |
| claude-sonnet-5 | 23.95% | 66.31% | 9.74% |
| deepseek-v4-flash-0731 | 8.22% | 90.29% | 1.49% |
| gemma-4-26B-A4B-it | 3.29% | 96.68% | 0.03% |
| gemini-3.5-flash-lite | 1.92% | 98.06% | 0.02% |
| gemma-4-31B-it | 0.98% | 98.98% | 0.04% |
| gemini-2.5-flash-lite | 0.46% | 99.32% | 0.22% |
| gpt-4.1-mini | 0.37% | 99.59% | 0.05% |

## Caveats

- Region suffixes are merged into one model. Private and customer-specific models are excluded.

## Cite as

**APA.** Requesty (2026). finish_reason mix per model, October 2026. Requesty Data. https://www.requesty.ai/data/finish-reason-mix-by-model-october-2026

```bibtex
@misc{requesty_finish_reason_mix_by_model_october_2026,
  author       = {{Requesty}},
  title        = {finish\_reason mix per model, October 2026},
  year         = {2026},
  howpublished = {\url{https://www.requesty.ai/data/finish-reason-mix-by-model-october-2026}},
  note         = {Requesty Data}
}
```

---

Downloads: [JSON](https://www.requesty.ai/data/finish-reason-mix-by-model-october-2026/data.json) · [CSV](https://www.requesty.ai/data/finish-reason-mix-by-model-october-2026/data.csv) · [Markdown](https://www.requesty.ai/data/finish-reason-mix-by-model-october-2026/data.md)