# General AI Assistant tasks on GAIA (Pass@1, Pass@3)

Source: [General AI Assistant tasks on GAIA (Pass@1, Pass@3)](<https://www.sota2.com/research/sota/general-ai-assistant-tasks-on-gaia-pass-at-1-pass-at-3>)

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

Data updated: 2026-05-19T10:30:34.968Z

Evaluation of general AI assistant capabilities on the GAIA dataset, measured using Pass@1 and Pass@3 scores.

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 |
| Metric | Pass@1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 38 of 38 |
| 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

- [Pass@1 Score](<https://www.sota2.com/research/sota/general-ai-assistant-tasks-on-gaia-pass-at-1-pass-at-3.md?metric=Pass%401%20Score>): Higher is better; unit: PERCENT.

- [Pass@3 Score](<https://www.sota2.com/research/sota/general-ai-assistant-tasks-on-gaia-pass-at-1-pass-at-3.md?metric=Pass%403%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Pass@1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| AgentOrchestra | 83.4 | Not recorded | 69fc1c945497b3b670c88565 |
| Uno-Orchestra | 82 | Not recorded | 69fc1c945497b3b670c88565 |
| Tongyi DeepResearch | 70.9 | Not recorded | 69019f853ef7ccd74e5e3b7f |
| OpenAI-o3 | 70.5 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| AOrchestra | 69.4 | Not recorded | 69fc1c945497b3b670c88565 |
| Claude-4 | 68.3 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| Claude-4-Sonnet | 68.3 | Not recorded | 69019f853ef7ccd74e5e3b7f |
| OpenAI DeepResearch | 67.4 | Not recorded | 69019f853ef7ccd74e5e3b7f |
| GLM 4.5 | 66 | Not recorded | 69019f853ef7ccd74e5e3b7f |
| DeepSeek-v3.1 | 63.1 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| DeepSeek-V3.1 | 63.1 | Not recorded | 69019f853ef7ccd74e5e3b7f |
| OpenAI o4-mini | 60 | Not recorded | 69019f853ef7ccd74e5e3b7f |
| Kimi-K2 | 57.7 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| Kimi K2 | 57.7 | Not recorded | 69019f853ef7ccd74e5e3b7f |
| WebSailor-30B | 51.5 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-30B | 49.2 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-30B | 47.3 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-30B | 46.9 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-30B | 45.6 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-30B | 45 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-7B | 43.4 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-7B | 42.4 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-7B | 41.1 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-3B | 40.5 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-7B | 40.5 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-30B | 40.1 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-3B | 39.2 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-3B | 35.3 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-7B | 34.6 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-30B | 33.3 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-7B | 33 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-3B | 32.4 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-7B | 31.7 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-3B | 27.5 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-3B | 27.2 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-3B | 25.6 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| xRouter | 24.8 | Not recorded | 69fc1c945497b3b670c88565 |
| ColdStart-LLM | 17.2 | Not recorded | 69fc1c945497b3b670c88565 |

### AgentOrchestra

Pass@1 Score: 83.4. Result ID: 69fc5cd547f34ce924df6e57.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1c945497b3b670c88565.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Uno-Orchestra

Pass@1 Score: 82. Result ID: 69fc5cd547f34ce924df6e58.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1c945497b3b670c88565.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fc1c945497b3b670c88565.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Tongyi DeepResearch

Pass@1 Score: 70.9. Result ID: 6a0c3bb2fbc373592c02fbba.

[Reporting paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b7f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b7f.md>)

Recorded evaluation configuration: {"Agent Type":"DeepResearch Agent","Configuration":"30B-A3B"}. This record does not assert independent reproduction.

### OpenAI-o3

Pass@1 Score: 70.5. Result ID: 69c68cf347f34ce924b0c433.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"Paradigm":"ReAct","Summary Tool":"-"}. This record does not assert independent reproduction.

### AOrchestra

Pass@1 Score: 69.4. Result ID: 69fc5cd547f34ce924df6e56.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1c945497b3b670c88565.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6982d2fba8b01e76cc8e9a12.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Claude-4

Pass@1 Score: 68.3. Result ID: 69c68cf347f34ce924b0c432.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba71e209131cea89abb.md>)

Recorded evaluation configuration: {"Paradigm":"ReAct","Summary Tool":"-"}. This record does not assert independent reproduction.

### Claude-4-Sonnet

Pass@1 Score: 68.3. Result ID: 6a0c3bb2fbc373592c02fbb7.

[Reporting paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b7f.md>)

Recorded evaluation configuration: {"Agent Type":"LLM-based ReAct Agent"}. This record does not assert independent reproduction.

### OpenAI DeepResearch

Pass@1 Score: 67.4. Result ID: 6a0c3bb2fbc373592c02fbb9.

[Reporting paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b7f.md>)

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

### GLM 4.5

Pass@1 Score: 66. Result ID: 6a0c3bb2fbc373592c02fbb4.

[Reporting paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b7f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a891e209131cea83c41.md>)

Recorded evaluation configuration: {"Agent Type":"LLM-based ReAct Agent"}. This record does not assert independent reproduction.

### DeepSeek-v3.1

Pass@1 Score: 63.1. Result ID: 69c68cf347f34ce924b0c435.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba71e209131cea89abb.md>)

Recorded evaluation configuration: {"Paradigm":"ReAct","Summary Tool":"-"}. This record does not assert independent reproduction.

### DeepSeek-V3.1

Pass@1 Score: 63.1. Result ID: 6a0c3bb2fbc373592c02fbb6.

[Reporting paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b7f.md>)

Recorded evaluation configuration: {"Agent Type":"LLM-based ReAct Agent"}. This record does not assert independent reproduction.

### OpenAI o4-mini

Pass@1 Score: 60. Result ID: 6a0c3bb2fbc373592c02fbb8.

[Reporting paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b7f.md>)

Recorded evaluation configuration: {"Agent Type":"LLM-based ReAct Agent"}. This record does not assert independent reproduction.

### Kimi-K2

Pass@1 Score: 57.7. Result ID: 69c68cf347f34ce924b0c434.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a1.md>)

Recorded evaluation configuration: {"Paradigm":"ReAct","Summary Tool":"-"}. This record does not assert independent reproduction.

### Kimi K2

Pass@1 Score: 57.7. Result ID: 6a0c3bb2fbc373592c02fbb5.

[Reporting paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b7f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a1.md>)

Recorded evaluation configuration: {"Agent Type":"LLM-based ReAct Agent"}. This record does not assert independent reproduction.

### WebSailor-30B

Pass@1 Score: 51.5. Result ID: 69c68cf347f34ce924b0c449.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"Paradigm":"ReSum","Summary Tool":"GPT-OSS-120B"}. This record does not assert independent reproduction.

### WebSailor-30B

Pass@1 Score: 49.2. Result ID: 69c68cf347f34ce924b0c44b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"Paradigm":"ReSum","Summary Tool":"DeepSeek-R1-671B"}. This record does not assert independent reproduction.

### WebSailor-30B

Pass@1 Score: 47.3. Result ID: 69c68cf347f34ce924b0c448.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"Paradigm":"ReSum","Summary Tool":"ReSumTool-30B"}. This record does not assert independent reproduction.

### WebSailor-30B

Pass@1 Score: 46.9. Result ID: 69c68cf347f34ce924b0c44a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"Paradigm":"ReSum","Summary Tool":"Qwen3-235B"}. This record does not assert independent reproduction.

### WebSailor-30B

Pass@1 Score: 45.6. Result ID: 69c68cf347f34ce924b0c447.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"Paradigm":"ReSum","Summary Tool":"Qwen3-30B"}. This record does not assert independent reproduction.

### WebSailor-30B

Pass@1 Score: 45. Result ID: 69c68cf347f34ce924b0c444.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"Paradigm":"ReAct","Summary Tool":"-"}. This record does not assert independent reproduction.

### WebSailor-7B

Pass@1 Score: 43.4. Result ID: 69c68cf347f34ce924b0c442.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"Paradigm":"ReSum","Summary Tool":"Qwen3-235B"}. This record does not assert independent reproduction.

### WebSailor-7B

Pass@1 Score: 42.4. Result ID: 69c68cf347f34ce924b0c441.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"Paradigm":"ReSum","Summary Tool":"GPT-OSS-120B"}. This record does not assert independent reproduction.

### WebSailor-7B

Pass@1 Score: 41.1. Result ID: 69c68cf347f34ce924b0c443.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"Paradigm":"ReSum","Summary Tool":"DeepSeek-R1-671B"}. This record does not assert independent reproduction.

### WebSailor-3B

Pass@1 Score: 40.5. Result ID: 69c68cf347f34ce924b0c43a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"Paradigm":"ReSum","Summary Tool":"GPT-OSS-120B"}. This record does not assert independent reproduction.

### WebSailor-7B

Pass@1 Score: 40.5. Result ID: 69c68cf347f34ce924b0c440.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"Paradigm":"ReSum","Summary Tool":"ReSumTool-30B"}. This record does not assert independent reproduction.

### WebSailor-30B

Pass@1 Score: 40.1. Result ID: 69c68cf347f34ce924b0c445.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"Paradigm":"Recent History","Summary Tool":"-"}. This record does not assert independent reproduction.

### WebSailor-3B

Pass@1 Score: 39.2. Result ID: 69c68cf347f34ce924b0c43c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"Paradigm":"ReSum","Summary Tool":"DeepSeek-R1-671B"}. This record does not assert independent reproduction.

### WebSailor-3B

Pass@1 Score: 35.3. Result ID: 69c68cf347f34ce924b0c439.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"Paradigm":"ReSum","Summary Tool":"ReSumTool-30B"}. This record does not assert independent reproduction.

### WebSailor-7B

Pass@1 Score: 34.6. Result ID: 69c68cf347f34ce924b0c43f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"Paradigm":"ReSum","Summary Tool":"Qwen3-30B"}. This record does not assert independent reproduction.

### WebSailor-30B

Pass@1 Score: 33.3. Result ID: 69c68cf347f34ce924b0c446.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"Paradigm":"MEM1","Summary Tool":"-"}. This record does not assert independent reproduction.

### WebSailor-7B

Pass@1 Score: 33. Result ID: 69c68cf347f34ce924b0c43e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"Paradigm":"Recent History","Summary Tool":"-"}. This record does not assert independent reproduction.

### WebSailor-3B

Pass@1 Score: 32.4. Result ID: 69c68cf347f34ce924b0c43b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"Paradigm":"ReSum","Summary Tool":"Qwen3-235B"}. This record does not assert independent reproduction.

### WebSailor-7B

Pass@1 Score: 31.7. Result ID: 69c68cf347f34ce924b0c43d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"Paradigm":"ReAct","Summary Tool":"-"}. This record does not assert independent reproduction.

### WebSailor-3B

Pass@1 Score: 27.5. Result ID: 69c68cf347f34ce924b0c438.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"Paradigm":"ReSum","Summary Tool":"Qwen3-30B"}. This record does not assert independent reproduction.

### WebSailor-3B

Pass@1 Score: 27.2. Result ID: 69c68cf347f34ce924b0c437.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"Paradigm":"Recent History","Summary Tool":"-"}. This record does not assert independent reproduction.

### WebSailor-3B

Pass@1 Score: 25.6. Result ID: 69c68cf347f34ce924b0c436.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"Paradigm":"ReAct","Summary Tool":"-"}. This record does not assert independent reproduction.

### xRouter

Pass@1 Score: 24.8. Result ID: 69fc5cd547f34ce924df6e55.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1c945497b3b670c88565.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bfb1e209131cea8b94e.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ColdStart-LLM

Pass@1 Score: 17.2. Result ID: 69fc5cd547f34ce924df6e54.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1c945497b3b670c88565.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69dc789f7d0172140ec78bc2.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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