# Multi-Hop Question Answering on Bamboogle (F1, LasJ) Source: [Multi-Hop Question Answering on Bamboogle (F1, LasJ)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:42:47.522Z Evaluation of model performance on the Bamboogle dataset for Multi-Hop Question Answering, specifically reporting F1 and LasJ metrics. 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-Hop Question Answering | | Dataset (including any stated split) | Bamboogle | | Metric | F1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 25 of 25 | | 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 - [F1](): Higher is better; unit: PERCENT. - [LasJ](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 | Result date | Report paper | | --- | --- | --- | --- | | CARL | 61.6 | Not recorded | 69326712d6b0dd334293430e | | CARL-Lite | 61.1 | Not recorded | 69326712d6b0dd334293430e | | CARL | 60.7 | Not recorded | 69326712d6b0dd334293430e | | ARPO | 59.6 | Not recorded | 69326712d6b0dd334293430e | | GRPO | 59.5 | Not recorded | 69326712d6b0dd334293430e | | BranPO | 57.8 | Not recorded | 6982d2f6a8b01e76cc8e99ab | | TreeRL | 57.7 | Not recorded | 69326712d6b0dd334293430e | | TreeRPO | 55.7 | Not recorded | 69326712d6b0dd334293430e | | GRPO | 55.1 | Not recorded | 69326712d6b0dd334293430e | | GRPO | 52.9 | Not recorded | 6982d2f6a8b01e76cc8e99ab | | BranPO | 52 | Not recorded | 6982d2f6a8b01e76cc8e99ab | | Tree-GRPO | 51.2 | Not recorded | 6982d2f6a8b01e76cc8e99ab | | Tree-GRPO | 51 | Not recorded | 6982d2f6a8b01e76cc8e99ab | | GRPO | 50.1 | Not recorded | 6982d2f6a8b01e76cc8e99ab | | GiGPO | 49.7 | Not recorded | 6982d2f6a8b01e76cc8e99ab | | SFT | 49.1 | Not recorded | 6982d2f6a8b01e76cc8e99ab | | CARL | 48.6 | Not recorded | 69326712d6b0dd334293430e | | GiGPO | 48.1 | Not recorded | 6982d2f6a8b01e76cc8e99ab | | SFT | 44.2 | Not recorded | 6982d2f6a8b01e76cc8e99ab | | GRPO | 40.7 | Not recorded | 69326712d6b0dd334293430e | | Zero-Shot | 28.5 | Not recorded | 69326712d6b0dd334293430e | | CARL | 25.7 | Not recorded | 69326712d6b0dd334293430e | | GRPO | 24.5 | Not recorded | 69326712d6b0dd334293430e | | Zero-Shot | 19 | Not recorded | 69326712d6b0dd334293430e | | Zero-Shot | 16.5 | Not recorded | 69326712d6b0dd334293430e | ### CARL F1: 61.6. Result ID: 6999886d5698665ec4f9d209. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"4B Reasoning","Max actions":"32"}. This record does not assert independent reproduction. ### CARL-Lite F1: 61.1. Result ID: 6999886d5698665ec4f9d206. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"4B Reasoning","Max actions":"10"}. This record does not assert independent reproduction. ### CARL F1: 60.7. Result ID: 6999886d5698665ec4f9d207. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"4B Reasoning","Max actions":"10"}. This record does not assert independent reproduction. ### ARPO F1: 59.6. Result ID: 6999886d5698665ec4f9d205. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"4B Reasoning","Max actions":"10"}. This record does not assert independent reproduction. ### GRPO F1: 59.5. Result ID: 6999886d5698665ec4f9d208. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"4B Reasoning","Max actions":"32"}. This record does not assert independent reproduction. ### BranPO F1: 57.8. Result ID: 69964eba5698665ec4935ed3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B-Instruct-2507"}. This record does not assert independent reproduction. ### TreeRL F1: 57.7. Result ID: 6999886d5698665ec4f9d204. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"4B Reasoning","Max actions":"10"}. This record does not assert independent reproduction. ### TreeRPO F1: 55.7. Result ID: 6999886d5698665ec4f9d203. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"4B Reasoning","Max actions":"10"}. This record does not assert independent reproduction. ### GRPO F1: 55.1. Result ID: 6999886d5698665ec4f9d202. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"4B Reasoning","Max actions":"10"}. This record does not assert independent reproduction. ### GRPO F1: 52.9. Result ID: 69964eba5698665ec4935ed0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B-Instruct-2507"}. This record does not assert independent reproduction. ### BranPO F1: 52. Result ID: 69964eba5698665ec4935ece. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Tree-GRPO F1: 51.2. Result ID: 69964eba5698665ec4935ed2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B-Instruct-2507"}. This record does not assert independent reproduction. ### Tree-GRPO F1: 51. Result ID: 69964eba5698665ec4935ecd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### GRPO F1: 50.1. Result ID: 69964eba5698665ec4935ecb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### GiGPO F1: 49.7. Result ID: 69964eba5698665ec4935ed1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B-Instruct-2507"}. This record does not assert independent reproduction. ### SFT F1: 49.1. Result ID: 69964eba5698665ec4935ecf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B-Instruct-2507"}. This record does not assert independent reproduction. ### CARL F1: 48.6. Result ID: 6999886d5698665ec4f9d200. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"7B Non-Reasoning","Max actions":"32"}. This record does not assert independent reproduction. ### GiGPO F1: 48.1. Result ID: 69964eba5698665ec4935ecc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### SFT F1: 44.2. Result ID: 69964eba5698665ec4935eca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### GRPO F1: 40.7. Result ID: 6999886d5698665ec4f9d1ff. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"7B Non-Reasoning","Max actions":"32"}. This record does not assert independent reproduction. ### Zero-Shot F1: 28.5. Result ID: 6999886d5698665ec4f9d201. [Reporting paper]() Recorded evaluation configuration: {"Model":"4B Reasoning","Max actions":"10"}. This record does not assert independent reproduction. ### CARL F1: 25.7. Result ID: 6999886d5698665ec4f9d1fd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"3B Non-Reasoning","Max actions":"32"}. This record does not assert independent reproduction. ### GRPO F1: 24.5. Result ID: 6999886d5698665ec4f9d1fc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"3B Non-Reasoning","Max actions":"32"}. This record does not assert independent reproduction. ### Zero-Shot F1: 19. Result ID: 6999886d5698665ec4f9d1fb. [Reporting paper]() Recorded evaluation configuration: {"Model":"3B Non-Reasoning","Max actions":"32"}. This record does not assert independent reproduction. ### Zero-Shot F1: 16.5. Result ID: 6999886d5698665ec4f9d1fe. [Reporting paper]() Recorded evaluation configuration: {"Model":"7B Non-Reasoning","Max actions":"32"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.