# End-to-end terminal tasks on Terminal-Bench 2

Source: [End-to-end terminal tasks on Terminal-Bench 2](<https://www.sota2.com/research/sota/end-to-end-terminal-tasks-on-terminal-bench-2>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T06:03:54.188Z

Evaluation of model performance on the Terminal-Bench 2 dataset for general end-to-end terminal task execution, measured by Score.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | End-to-end terminal tasks |
| Dataset (including any stated split) | Terminal-Bench 2 |
| Metric | Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 13 of 13 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Score](<https://www.sota2.com/research/sota/end-to-end-terminal-tasks-on-terminal-bench-2.md?metric=Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Score | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-5 | 49.6 | Not recorded | 69326715d6b0dd3342934334 |
| Claude-Sonnet-4.5 | 42.8 | Not recorded | 69326715d6b0dd3342934334 |
| Kimi-K2-thinking | 35.7 | Not recorded | 69326715d6b0dd3342934334 |
| Gemini-2.5-pro | 32.6 | Not recorded | 69326715d6b0dd3342934334 |
| DeepSeek-V3.1-Nex-N1 | 31.8 | Not recorded | 69326715d6b0dd3342934334 |
| Minimax-M2 | 30 | Not recorded | 69326715d6b0dd3342934334 |
| GLM-4.6 | 24.5 | Not recorded | 69326715d6b0dd3342934334 |
| DeepSeek-V3.1 | 22.2 | Not recorded | 69326715d6b0dd3342934334 |
| Qwen3-32B-Nex-N1 | 16.7 | Not recorded | 69326715d6b0dd3342934334 |
| Qwen3-30B-A3B-Nex-N1 | 8.3 | Not recorded | 69326715d6b0dd3342934334 |
| Qwen3-32B | 7.9 | Not recorded | 69326715d6b0dd3342934334 |
| Qwen3-30B-A3B | 6 | Not recorded | 69326715d6b0dd3342934334 |
| InternLM3-8B-Nex-N1 | 0 | Not recorded | 69326715d6b0dd3342934334 |

### GPT-5

Score: 49.6. Result ID: 6996cc315698665ec4180b60.

[Reporting paper](<https://www.sota2.com/research/paper/69326715d6b0dd3342934334.md>)

Recorded evaluation configuration: {"Model Type":"Proprietary"}. This record does not assert independent reproduction.

### Claude-Sonnet-4.5

Score: 42.8. Result ID: 6996cc315698665ec4180b5f.

[Reporting paper](<https://www.sota2.com/research/paper/69326715d6b0dd3342934334.md>)

Recorded evaluation configuration: {"Model Type":"Proprietary"}. This record does not assert independent reproduction.

### Kimi-K2-thinking

Score: 35.7. Result ID: 6996cc315698665ec4180b64.

[Reporting paper](<https://www.sota2.com/research/paper/69326715d6b0dd3342934334.md>)

Recorded evaluation configuration: {"Model Type":"Open Source","Parameter Scale":"\> 100B"}. This record does not assert independent reproduction.

### Gemini-2.5-pro

Score: 32.6. Result ID: 6996cc315698665ec4180b61.

[Reporting paper](<https://www.sota2.com/research/paper/69326715d6b0dd3342934334.md>)

Recorded evaluation configuration: {"Model Type":"Proprietary"}. This record does not assert independent reproduction.

### DeepSeek-V3.1-Nex-N1

Score: 31.8. Result ID: 6996cc315698665ec4180b66.

[Reporting paper](<https://www.sota2.com/research/paper/69326715d6b0dd3342934334.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69326715d6b0dd3342934334.md>)

[Implementation](<https://github.com/nex-agi/Nex-N1>)

Recorded evaluation configuration: {"Model Type":"Open Source","Parameter Scale":"\> 100B"}. This record does not assert independent reproduction.

### Minimax-M2

Score: 30. Result ID: 6996cc315698665ec4180b63.

[Reporting paper](<https://www.sota2.com/research/paper/69326715d6b0dd3342934334.md>)

Recorded evaluation configuration: {"Model Type":"Open Source","Parameter Scale":"\> 100B"}. This record does not assert independent reproduction.

### GLM-4.6

Score: 24.5. Result ID: 6996cc315698665ec4180b62.

[Reporting paper](<https://www.sota2.com/research/paper/69326715d6b0dd3342934334.md>)

Recorded evaluation configuration: {"Model Type":"Open Source","Parameter Scale":"\> 100B"}. This record does not assert independent reproduction.

### DeepSeek-V3.1

Score: 22.2. Result ID: 6996cc315698665ec4180b65.

[Reporting paper](<https://www.sota2.com/research/paper/69326715d6b0dd3342934334.md>)

Recorded evaluation configuration: {"Model Type":"Open Source","Parameter Scale":"\> 100B"}. This record does not assert independent reproduction.

### Qwen3-32B-Nex-N1

Score: 16.7. Result ID: 6996cc315698665ec4180b68.

[Reporting paper](<https://www.sota2.com/research/paper/69326715d6b0dd3342934334.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69326715d6b0dd3342934334.md>)

[Implementation](<https://github.com/nex-agi/Nex-N1>)

Recorded evaluation configuration: {"Model Type":"Open Source","Parameter Scale":"\< 100B"}. This record does not assert independent reproduction.

### Qwen3-30B-A3B-Nex-N1

Score: 8.3. Result ID: 6996cc315698665ec4180b6a.

[Reporting paper](<https://www.sota2.com/research/paper/69326715d6b0dd3342934334.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69326715d6b0dd3342934334.md>)

[Implementation](<https://github.com/nex-agi/Nex-N1>)

Recorded evaluation configuration: {"Model Type":"Open Source","Parameter Scale":"\< 100B"}. This record does not assert independent reproduction.

### Qwen3-32B

Score: 7.9. Result ID: 6996cc315698665ec4180b67.

[Reporting paper](<https://www.sota2.com/research/paper/69326715d6b0dd3342934334.md>)

Recorded evaluation configuration: {"Model Type":"Open Source","Parameter Scale":"\< 100B"}. This record does not assert independent reproduction.

### Qwen3-30B-A3B

Score: 6. Result ID: 6996cc315698665ec4180b69.

[Reporting paper](<https://www.sota2.com/research/paper/69326715d6b0dd3342934334.md>)

Recorded evaluation configuration: {"Model Type":"Open Source","Parameter Scale":"\< 100B"}. This record does not assert independent reproduction.

### InternLM3-8B-Nex-N1

Score: 0. Result ID: 6996cc315698665ec4180b6b.

[Reporting paper](<https://www.sota2.com/research/paper/69326715d6b0dd3342934334.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69326715d6b0dd3342934334.md>)

[Implementation](<https://github.com/nex-agi/Nex-N1>)

Recorded evaluation configuration: {"Model Type":"Open Source","Parameter Scale":"\< 100B"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
