# Multi-step Reasoning and Factuality on FRAMES (Pass@1)

Source: [Multi-step Reasoning and Factuality on FRAMES (Pass@1)](<https://www.sota2.com/research/sota/multi-step-reasoning-and-factuality-on-frames-pass-at-1>)

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

Data updated: 2026-05-19T10:32:17.869Z

Evaluation of model performance on the FRAMES dataset focusing on multi-step reasoning and factuality verification, measured using Pass@1 success 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 | Multi-step Reasoning and Factuality |
| Dataset (including any stated split) | FRAMES |
| Metric | Pass@1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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](<https://www.sota2.com/research/sota/multi-step-reasoning-and-factuality-on-frames-pass-at-1.md?metric=Pass%401>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Pass@1 | Result date | Report paper |
| --- | --- | --- | --- |
| Tongyi DeepResearch | 90.6 | Not recorded | 69019f853ef7ccd74e5e3b7f |
| OpenAI o3 | 84 | Not recorded | 69019f853ef7ccd74e5e3b7f |
| DeepSeek-V3.1 | 83.7 | Not recorded | 69019f853ef7ccd74e5e3b7f |
| Claude-4-Sonnet | 80.7 | Not recorded | 69019f853ef7ccd74e5e3b7f |
| GLM 4.5 | 78.9 | Not recorded | 69019f853ef7ccd74e5e3b7f |
| Kimi Researcher | 78.8 | Not recorded | 69019f853ef7ccd74e5e3b7f |
| Kimi K2 | 72 | Not recorded | 69019f853ef7ccd74e5e3b7f |

### Tongyi DeepResearch

Pass@1: 90.6. Result ID: 6a0c3bb2fbc373592c02fbce.

[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: 84. Result ID: 6a0c3bb2fbc373592c02fbcc.

[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.

### DeepSeek-V3.1

Pass@1: 83.7. Result ID: 6a0c3bb2fbc373592c02fbca.

[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.

### Claude-4-Sonnet

Pass@1: 80.7. Result ID: 6a0c3bb2fbc373592c02fbcb.

[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.

### GLM 4.5

Pass@1: 78.9. Result ID: 6a0c3bb2fbc373592c02fbc8.

[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.

### Kimi Researcher

Pass@1: 78.8. Result ID: 6a0c3bb2fbc373592c02fbcd.

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

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

### Kimi K2

Pass@1: 72. Result ID: 6a0c3bb2fbc373592c02fbc9.

[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.

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