# Terminal Task Execution on Terminal-Bench 1.0 (test)

Source: [Terminal Task Execution on Terminal-Bench 1.0 (test)](<https://www.sota2.com/research/sota/terminal-task-execution-on-terminal-bench-1-0-test>)

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

Data updated: 2026-03-31T06:53:40.286Z

Evaluation of model performance on completing tasks within the Terminal-Bench 1.0 environment, specifically using the test split, measured by average pass rate.

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 | Terminal Task Execution |
| Dataset (including any stated split) | Terminal-Bench 1.0 (test) |
| Metric | Avg Pass Rate |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Avg Pass Rate](<https://www.sota2.com/research/sota/terminal-task-execution-on-terminal-bench-1-0-test.md?metric=Avg%20Pass%20Rate>): Higher is better; unit: PERCENT.

- [Avg Steps per Task](<https://www.sota2.com/research/sota/terminal-task-execution-on-terminal-bench-1-0-test.md?metric=Avg%20Steps%20per%20Task>): Lower is better; unit: SCALAR.

- [Avg Cost per Task ($)](<https://www.sota2.com/research/sota/terminal-task-execution-on-terminal-bench-1-0-test.md?metric=Avg%20Cost%20per%20Task%20(%24)>): Lower is better; unit: OTHER.

## Recorded results

| Method | Avg Pass Rate | Result date | Report paper |
| --- | --- | --- | --- |
| SkillFlow-specific | 34.9 | Not recorded | 68fa77dc1e209131cea759e1 |
| No Skills | 34.8 | Not recorded | 68fa77dc1e209131cea759e1 |
| Vercel | 32.6 | Not recorded | 68fa77dc1e209131cea759e1 |
| SkillFlow | 31.8 | Not recorded | 68fa77dc1e209131cea759e1 |
| Reptile | 18.9 | Not recorded | 698abb65c97a0b3e3b5dddfa |
| Terminus 2 | 18.8 | Not recorded | 698abb65c97a0b3e3b5dddfa |

### SkillFlow-specific

Avg Pass Rate: 34.9. Result ID: 69cb6f5747f34ce924b3329f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77dc1e209131cea759e1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77dc1e209131cea759e1.md>)

Recorded evaluation configuration: {"Skillset":"SkillFlow-specific"}. This record does not assert independent reproduction.

### No Skills

Avg Pass Rate: 34.8. Result ID: 69cb6f5747f34ce924b3329c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77dc1e209131cea759e1.md>)

Recorded evaluation configuration: {"Skillset":"No Skills"}. This record does not assert independent reproduction.

### Vercel

Avg Pass Rate: 32.6. Result ID: 69cb6f5747f34ce924b3329d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77dc1e209131cea759e1.md>)

Recorded evaluation configuration: {"Skillset":"Vercel"}. This record does not assert independent reproduction.

### SkillFlow

Avg Pass Rate: 31.8. Result ID: 69cb6f5747f34ce924b3329e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77dc1e209131cea759e1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77dc1e209131cea759e1.md>)

Recorded evaluation configuration: {"Skillset":"SkillFlow"}. This record does not assert independent reproduction.

### Reptile

Avg Pass Rate: 18.9. Result ID: 6995fe785698665ec4342e74.

[Reporting paper](<https://www.sota2.com/research/paper/698abb65c97a0b3e3b5dddfa.md>)

Recorded evaluation configuration: {"Base Model":"Devstral-2505-22B","Category":"Fine-tuned Models"}. This record does not assert independent reproduction.

### Terminus 2

Avg Pass Rate: 18.8. Result ID: 6995fe785698665ec4342e75.

[Reporting paper](<https://www.sota2.com/research/paper/698abb65c97a0b3e3b5dddfa.md>)

Recorded evaluation configuration: {"Base Model":"LiteCoder-30a3b","Category":"Fine-tuned Models"}. This record does not assert independent reproduction.

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