# General AI Assistant Tasks on GAIA Level 1 original (test)

Source: [General AI Assistant Tasks on GAIA Level 1 original (test)](<https://www.sota2.com/research/sota/general-ai-assistant-tasks-on-gaia-level-1-original-test>)

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

Data updated: 2026-02-26T05:57:49.206Z

Evaluation of general AI assistant capabilities on the original test split of GAIA Level 1, reporting performance, cost, and latency.

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 | General AI Assistant Tasks |
| Dataset (including any stated split) | GAIA Level 1 original (test) |
| Metric | Performance (%) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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

- [Performance (%)](<https://www.sota2.com/research/sota/general-ai-assistant-tasks-on-gaia-level-1-original-test.md?metric=Performance%20(%25)>): Higher is better; unit: PERCENT.

- [Cost ($)](<https://www.sota2.com/research/sota/general-ai-assistant-tasks-on-gaia-level-1-original-test.md?metric=Cost%20(%24)>): Lower is better; unit: SCALAR.

- [Delay (h)](<https://www.sota2.com/research/sota/general-ai-assistant-tasks-on-gaia-level-1-original-test.md?metric=Delay%20(h)>): Lower is better; unit: TIME.

## Recorded results

| Method | Performance (%) | Result date | Report paper |
| --- | --- | --- | --- |
| EvoRoute | 83.02 | Not recorded | 695de87753fdd5c361743c7c |
| EvoRoute | 73.91 | Not recorded | 695de87753fdd5c361743c7c |
| Claude-4 | 67.92 | Not recorded | 695de87753fdd5c361743c7c |
| MasRouter | 67.92 | Not recorded | 695de87753fdd5c361743c7c |
| GPT-4o | 59.91 | Not recorded | 695de87753fdd5c361743c7c |
| PromptLLM | 58.91 | Not recorded | 695de87753fdd5c361743c7c |
| GraphRouter | 58.13 | Not recorded | 695de87753fdd5c361743c7c |
| GPT-4.1 | 56.29 | Not recorded | 695de87753fdd5c361743c7c |
| Claude-4 | 56.26 | Not recorded | 695de87753fdd5c361743c7c |
| GPT-4.1 | 55 | Not recorded | 695de87753fdd5c361743c7c |
| MasRouter | 49.82 | Not recorded | 695de87753fdd5c361743c7c |
| PromptLLM | 49.8 | Not recorded | 695de87753fdd5c361743c7c |
| GraphRouter | 47.95 | Not recorded | 695de87753fdd5c361743c7c |
| Qwen3-14b | 16.77 | Not recorded | 695de87753fdd5c361743c7c |
| Qwen3-14b | 15.35 | Not recorded | 695de87753fdd5c361743c7c |

### EvoRoute

Performance (%): 83.02. Result ID: 6996a2e35698665ec4ec70b2.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

Recorded evaluation configuration: {"Framework":"CK-Pro","Setting":"Ours"}. This record does not assert independent reproduction.

### EvoRoute

Performance (%): 73.91. Result ID: 6996a2e35698665ec4ec70b9.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

Recorded evaluation configuration: {"Framework":"Smolagent","Setting":"Ours"}. This record does not assert independent reproduction.

### Claude-4

Performance (%): 67.92. Result ID: 6996a2e35698665ec4ec70ac.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

Recorded evaluation configuration: {"Framework":"CK-Pro","Setting":"Manual"}. This record does not assert independent reproduction.

### MasRouter

Performance (%): 67.92. Result ID: 6996a2e35698665ec4ec70b1.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76fd1e209131cea7049b.md>)

Recorded evaluation configuration: {"Framework":"CK-Pro","Setting":"Routing"}. This record does not assert independent reproduction.

### GPT-4o

Performance (%): 59.91. Result ID: 6996a2e35698665ec4ec70ad.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

Recorded evaluation configuration: {"Framework":"CK-Pro","Setting":"Manual"}. This record does not assert independent reproduction.

### PromptLLM

Performance (%): 58.91. Result ID: 6996a2e35698665ec4ec70af.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa777b1e209131cea737d1.md>)

Recorded evaluation configuration: {"Framework":"CK-Pro","Setting":"Routing"}. This record does not assert independent reproduction.

### GraphRouter

Performance (%): 58.13. Result ID: 6996a2e35698665ec4ec70b0.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa777b1e209131cea737d1.md>)

Recorded evaluation configuration: {"Framework":"CK-Pro","Setting":"Routing"}. This record does not assert independent reproduction.

### GPT-4.1

Performance (%): 56.29. Result ID: 6996a2e35698665ec4ec70ae.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

Recorded evaluation configuration: {"Framework":"CK-Pro","Setting":"Manual"}. This record does not assert independent reproduction.

### Claude-4

Performance (%): 56.26. Result ID: 6996a2e35698665ec4ec70b4.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

Recorded evaluation configuration: {"Framework":"Smolagent","Setting":"Manual"}. This record does not assert independent reproduction.

### GPT-4.1

Performance (%): 55. Result ID: 6996a2e35698665ec4ec70b5.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

Recorded evaluation configuration: {"Framework":"Smolagent","Setting":"Manual"}. This record does not assert independent reproduction.

### MasRouter

Performance (%): 49.82. Result ID: 6996a2e35698665ec4ec70b8.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76fd1e209131cea7049b.md>)

Recorded evaluation configuration: {"Framework":"Smolagent","Setting":"Routing"}. This record does not assert independent reproduction.

### PromptLLM

Performance (%): 49.8. Result ID: 6996a2e35698665ec4ec70b6.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa777b1e209131cea737d1.md>)

Recorded evaluation configuration: {"Framework":"Smolagent","Setting":"Routing"}. This record does not assert independent reproduction.

### GraphRouter

Performance (%): 47.95. Result ID: 6996a2e35698665ec4ec70b7.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa777b1e209131cea737d1.md>)

Recorded evaluation configuration: {"Framework":"Smolagent","Setting":"Routing"}. This record does not assert independent reproduction.

### Qwen3-14b

Performance (%): 16.77. Result ID: 6996a2e35698665ec4ec70ab.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

Recorded evaluation configuration: {"Framework":"CK-Pro","Setting":"Manual"}. This record does not assert independent reproduction.

### Qwen3-14b

Performance (%): 15.35. Result ID: 6996a2e35698665ec4ec70b3.

[Reporting paper](<https://www.sota2.com/research/paper/695de87753fdd5c361743c7c.md>)

Recorded evaluation configuration: {"Framework":"Smolagent","Setting":"Manual"}. This record does not assert independent reproduction.

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