# Dialogue on IFEval Source: [Dialogue on IFEval]() Collection index: [llms.txt]() Data updated: 2026-05-22T08:30:02.892Z Evaluation of dialogue system performance using the IFEval dataset, measured by the IFEval metric. 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 | Dialogue | | Dataset (including any stated split) | IFEval | | Metric | IFEval | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 34 of 34 | | 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 - [IFEval](): Higher is better; unit: PERCENT. ## Recorded results | Method | IFEval | Result date | Report paper | | --- | --- | --- | --- | | FuseChat3.0 | 80.2 | Not recorded | 6a0fe2fdf984739ed6739c8c | | SKillWeave (Ours) | 79.1 | Not recorded | 6a0fe2fdf984739ed6739c8c | | SkillWeave (Delta-Come replacement) | 79 | Not recorded | 6a0fe2fdf984739ed6739c8c | | SkillWeave (Self-Rewarding replacement) | 78.8 | Not recorded | 6a0fe2fdf984739ed6739c8c | | Sequentially MTL | 78.6 | Not recorded | 6a0fe2fdf984739ed6739c8c | | Twin-Merging r1024 | 78.4 | Not recorded | 6a0fe2fdf984739ed6739c8c | | SkillWeave (ASVD replacement) | 78.3 | Not recorded | 6a0fe2fdf984739ed6739c8c | | Self-Align | 78.2 | Not recorded | 6a0fe2fdf984739ed6739c8c | | SkillWeave (PEFT replacement) | 78.1 | Not recorded | 6a0fe2fdf984739ed6739c8c | | Qwen2-57BA14B-it | 78 | Not recorded | 6a0fe2fdf984739ed6739c8c | | Self-MoE | 77.9 | Not recorded | 6a0fe2fdf984739ed6739c8c | | EMR-Merging | 77.9 | Not recorded | 6a0fe2fdf984739ed6739c8c | | Self-Rewarding | 77.9 | Not recorded | 6a0fe2fdf984739ed6739c8c | | TALL-Mask | 77.8 | Not recorded | 6a0fe2fdf984739ed6739c8c | | Jointly MTL | 77.8 | Not recorded | 6a0fe2fdf984739ed6739c8c | | Twin-Merging r512 | 77.7 | Not recorded | 6a0fe2fdf984739ed6739c8c | | Routed LoRA r1024 | 77.6 | Not recorded | 6a0fe2fdf984739ed6739c8c | | PCB-Merge+DARE | 77.2 | Not recorded | 6a0fe2fdf984739ed6739c8c | | Qwen1.5-72B-Chat | 77.1 | Not recorded | 6a0fe2fdf984739ed6739c8c | | Gemma2-27B-it | 77.1 | Not recorded | 6a0fe2fdf984739ed6739c8c | | PCB-Merging | 76.9 | Not recorded | 6a0fe2fdf984739ed6739c8c | | FuseLLM | 76.9 | Not recorded | 6a0fe2fdf984739ed6739c8c | | Ties-Merging | 76.7 | Not recorded | 6a0fe2fdf984739ed6739c8c | | Routed LoRA r512 | 76.7 | Not recorded | 6a0fe2fdf984739ed6739c8c | | SkillWeave (Self-Specialize replacement) | 76.6 | Not recorded | 6a0fe2fdf984739ed6739c8c | | Task Arithmetic | 76.2 | Not recorded | 6a0fe2fdf984739ed6739c8c | | Llama3.1-8B-Instruct | 75.9 | Not recorded | 6a0fe2fdf984739ed6739c8c | | FuseChat3.0 | 72.5 | Not recorded | 6a0fe2fdf984739ed6739c8c | | SkillWeave | 64.1 | Not recorded | 6a0fe2fdf984739ed6739c8c | | self-rewarding | 63.2 | Not recorded | 6a0fe2fdf984739ed6739c8c | | PEFT | 62.7 | Not recorded | 6a0fe2fdf984739ed6739c8c | | Twin-merging | 61.9 | Not recorded | 6a0fe2fdf984739ed6739c8c | | Qwen2.5-14B | 59.9 | Not recorded | 6a0fe2fdf984739ed6739c8c | | Llama3.2-1B-Instruct | 58.4 | Not recorded | 6a0fe2fdf984739ed6739c8c | ### FuseChat3.0 IFEval: 80.2. Result ID: 6a101405fbc373592c090e2f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"8B"}. This record does not assert independent reproduction. ### SKillWeave (Ours) IFEval: 79.1. Result ID: 6a101405fbc373592c090e34. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"10B"}. This record does not assert independent reproduction. ### SkillWeave (Delta-Come replacement) IFEval: 79. Result ID: 6a101405fbc373592c090e39. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"10B"}. This record does not assert independent reproduction. ### SkillWeave (Self-Rewarding replacement) IFEval: 78.8. Result ID: 6a101405fbc373592c090e35. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"10B"}. This record does not assert independent reproduction. ### Sequentially MTL IFEval: 78.6. Result ID: 6a101405fbc373592c090e33. [Reporting paper]() Recorded evaluation configuration: {"#Params":"8B"}. This record does not assert independent reproduction. ### Twin-Merging r1024 IFEval: 78.4. Result ID: 6a101405fbc373592c090e2d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"21B"}. This record does not assert independent reproduction. ### SkillWeave (ASVD replacement) IFEval: 78.3. Result ID: 6a101405fbc373592c090e38. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"10B"}. This record does not assert independent reproduction. ### Self-Align IFEval: 78.2. Result ID: 6a101405fbc373592c090e31. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#Params":"8B"}. This record does not assert independent reproduction. ### SkillWeave (PEFT replacement) IFEval: 78.1. Result ID: 6a101405fbc373592c090e37. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"10B"}. This record does not assert independent reproduction. ### Qwen2-57BA14B-it IFEval: 78. Result ID: 6a101405fbc373592c090e22. [Reporting paper]() Recorded evaluation configuration: {"#Params":"52B"}. This record does not assert independent reproduction. ### Self-MoE IFEval: 77.9. Result ID: 6a101405fbc373592c090e27. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"9B"}. This record does not assert independent reproduction. ### EMR-Merging IFEval: 77.9. Result ID: 6a101405fbc373592c090e2b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#Params":"16.7B"}. This record does not assert independent reproduction. ### Self-Rewarding IFEval: 77.9. Result ID: 6a101405fbc373592c090e30. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"8B"}. This record does not assert independent reproduction. ### TALL-Mask IFEval: 77.8. Result ID: 6a101405fbc373592c090e2a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"16.7B"}. This record does not assert independent reproduction. ### Jointly MTL IFEval: 77.8. Result ID: 6a101405fbc373592c090e32. [Reporting paper]() Recorded evaluation configuration: {"#Params":"8B"}. This record does not assert independent reproduction. ### Twin-Merging r512 IFEval: 77.7. Result ID: 6a101405fbc373592c090e2c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"14.1B"}. This record does not assert independent reproduction. ### Routed LoRA r1024 IFEval: 77.6. Result ID: 6a101405fbc373592c090e29. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"21B"}. This record does not assert independent reproduction. ### PCB-Merge+DARE IFEval: 77.2. Result ID: 6a101405fbc373592c090e26. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"8B"}. This record does not assert independent reproduction. ### Qwen1.5-72B-Chat IFEval: 77.1. Result ID: 6a101405fbc373592c090e1f. [Reporting paper]() Recorded evaluation configuration: {"#Params":"72B"}. This record does not assert independent reproduction. ### Gemma2-27B-it IFEval: 77.1. Result ID: 6a101405fbc373592c090e20. [Reporting paper]() Recorded evaluation configuration: {"#Params":"27B"}. This record does not assert independent reproduction. ### PCB-Merging IFEval: 76.9. Result ID: 6a101405fbc373592c090e25. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"8B"}. This record does not assert independent reproduction. ### FuseLLM IFEval: 76.9. Result ID: 6a101405fbc373592c090e2e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"8B"}. This record does not assert independent reproduction. ### Ties-Merging IFEval: 76.7. Result ID: 6a101405fbc373592c090e24. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"8B"}. This record does not assert independent reproduction. ### Routed LoRA r512 IFEval: 76.7. Result ID: 6a101405fbc373592c090e28. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"14.1B"}. This record does not assert independent reproduction. ### SkillWeave (Self-Specialize replacement) IFEval: 76.6. Result ID: 6a101405fbc373592c090e36. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"10B"}. This record does not assert independent reproduction. ### Task Arithmetic IFEval: 76.2. Result ID: 6a101405fbc373592c090e23. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"8B"}. This record does not assert independent reproduction. ### Llama3.1-8B-Instruct IFEval: 75.9. Result ID: 6a101405fbc373592c090e1e. [Reporting paper]() Recorded evaluation configuration: {"#Params":"8B"}. This record does not assert independent reproduction. ### FuseChat3.0 IFEval: 72.5. Result ID: 6a101405fbc373592c090e8d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"1.48B","Backbone":"Llama-3.2-1B-Instruct"}. This record does not assert independent reproduction. ### SkillWeave IFEval: 64.1. Result ID: 6a101405fbc373592c090e8e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"1.42B","Backbone":"Llama-3.2-1B-Instruct"}. This record does not assert independent reproduction. ### self-rewarding IFEval: 63.2. Result ID: 6a101405fbc373592c090e8b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"1.15B","Backbone":"Llama-3.2-1B-Instruct"}. This record does not assert independent reproduction. ### PEFT IFEval: 62.7. Result ID: 6a101405fbc373592c090e8f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#Params":"1.42B","Backbone":"Llama-3.2-1B-Instruct"}. This record does not assert independent reproduction. ### Twin-merging IFEval: 61.9. Result ID: 6a101405fbc373592c090e8c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"1.48B","Backbone":"Llama-3.2-1B-Instruct"}. This record does not assert independent reproduction. ### Qwen2.5-14B IFEval: 59.9. Result ID: 6a101405fbc373592c090e21. [Reporting paper]() Recorded evaluation configuration: {"#Params":"14B"}. This record does not assert independent reproduction. ### Llama3.2-1B-Instruct IFEval: 58.4. Result ID: 6a101405fbc373592c090e8a. [Reporting paper]() Recorded evaluation configuration: {"#Params":"1.15B","Backbone":"Llama-3.2-1B-Instruct"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.