# Is Gemini 3.1 Pro SOTA?

Best current rank: #34 in Coding › Agentic, as of Nov 22, 2026.

As of Nov 22, 2026, Gemini 3.1 Pro is ranked #34 in Coding › Agentic (since Nov 22, 2026; sources Terminal-Bench 4.0; methodology v1.0). Ranked #34 in Coding › Agentic.

Canonical: https://isitsota.com/m/gemini-3-1-pro/coding
Last updated: 2026-11-22
Methodology v1.0. Computed automatically.

- Coding: #43 in Coding — Ranked #43 in Coding.
- Coding › Agentic: #34 in Coding › Agentic — Ranked #34 in Coding › Agentic.

## Coding

https://isitsota.com/c/coding

### Primary benchmarks

- Terminal-Bench 4.0: 2.7 (CI 105.0%–4.4) on Nov 18, 2026 (#40 of 44).

On the category's weighted score it is 89.0 points behind #1 Claude Sonnet 5.5 and 2.2 behind the next model up, Muse Spark Open.

### Nearby on the board

| # | Model | Category score |
| ---: | --- | ---: |
| 40 | [Minimax M3](https://isitsota.com/m/minimax-m3.md) | 14.1 |
| 41 | [Beam 1.0](https://isitsota.com/m/beam-1-0.md) | 11.6 |
| 42 | [Muse Spark Open](https://isitsota.com/m/muse-spark-open.md) | 11.5 |
| 43 | **Gemini 3.1 Pro** | 9.3 |
| 44 | [GPT-5.4 Mini](https://isitsota.com/m/gpt-5-4-mini.md) | 7.0 |
| 45 | [Inkling Small](https://isitsota.com/m/inkling-small-thinking-machines-lab.md) | 4.7 |
| 46 | [Inkling Small](https://isitsota.com/m/inkling-small.md) | 3.8 |

## Related

- Model page: https://isitsota.com/m/gemini-3-1-pro.md
- Lab: [Google DeepMind](https://isitsota.com/labs/google.md)
- Category: [Coding](https://isitsota.com/c/coding.md)
- Category: [Coding › Agentic](https://isitsota.com/c/coding-agentic.md)
- JSON: https://api.isitsota.com/v1/models/gemini-3-1-pro
