# Self-Affirmation Success Rate on MT-Bench-101 Source: [Self-Affirmation Success Rate on MT-Bench-101]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:05:10.607Z Evaluation of model performance on the MT-Bench-101 dataset specifically measuring the success rate of self-affirmation responses. 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 | self-affirmation | | Dataset (including any stated split) | MT-Bench-101 | | Metric | Success Rate | | 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 - [Success Rate](): Higher is better; unit: PERCENT. ## Recorded results | Method | Success Rate | Result date | Report paper | | --- | --- | --- | --- | | EMBER (Single) | 0.58 | Not recorded | 69535c8c53fdd5c36173d9ee | | EMBER (Single) | 0.516 | Not recorded | 69535c8c53fdd5c36173d9ee | | EMBER (Multi) | 0.516 | Not recorded | 69535c8c53fdd5c36173d9ee | | EMBER (Single) | 0.461 | Not recorded | 69535c8c53fdd5c36173d9ee | | EMBER (Multi) | 0.438 | Not recorded | 69535c8c53fdd5c36173d9ee | | EMBER (Multi) | 0.42 | Not recorded | 69535c8c53fdd5c36173d9ee | | EMBER (Multi) | 0.356 | Not recorded | 69535c8c53fdd5c36173d9ee | | EMBER (Single) | 0.352 | Not recorded | 69535c8c53fdd5c36173d9ee | | SFT | 0.233 | Not recorded | 69535c8c53fdd5c36173d9ee | | Prior Knowledge (Bench) | 0.206 | Not recorded | 69535c8c53fdd5c36173d9ee | | EMBER (Multi) | 0.206 | Not recorded | 69535c8c53fdd5c36173d9ee | | EMBER (Single) | 0.183 | Not recorded | 69535c8c53fdd5c36173d9ee | | SFT | 0.142 | Not recorded | 69535c8c53fdd5c36173d9ee | | SFT | 0.069 | Not recorded | 69535c8c53fdd5c36173d9ee | | SFT | 0.065 | Not recorded | 69535c8c53fdd5c36173d9ee | | Prior Knowledge (Prompt) | 0.027 | Not recorded | 69535c8c53fdd5c36173d9ee | | Prior Knowledge (Prompt) | 0.027 | Not recorded | 69535c8c53fdd5c36173d9ee | | Prior Knowledge (Bench) | 0.014 | Not recorded | 69535c8c53fdd5c36173d9ee | | Prior Knowledge (Prompt) | 0.014 | Not recorded | 69535c8c53fdd5c36173d9ee | | Prior Knowledge (Prompt) | 0.014 | Not recorded | 69535c8c53fdd5c36173d9ee | | Prior Knowledge (Prompt) | 0.014 | Not recorded | 69535c8c53fdd5c36173d9ee | | SFT | 0.009 | Not recorded | 69535c8c53fdd5c36173d9ee | | Prior Knowledge (Bench) | 0 | Not recorded | 69535c8c53fdd5c36173d9ee | | Prior Knowledge (Bench) | 0 | Not recorded | 69535c8c53fdd5c36173d9ee | | Prior Knowledge (Bench) | 0 | Not recorded | 69535c8c53fdd5c36173d9ee | ### EMBER (Single) Success Rate: 0.58. Result ID: 6996abc55698665ec4f5cff2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Mistral 0.3-7B"}. This record does not assert independent reproduction. ### EMBER (Single) Success Rate: 0.516. Result ID: 6996abc55698665ec4f5cff4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen 3-8B"}. This record does not assert independent reproduction. ### EMBER (Multi) Success Rate: 0.516. Result ID: 6996abc55698665ec4f5cff8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Llama 3.1-8B"}. This record does not assert independent reproduction. ### EMBER (Single) Success Rate: 0.461. Result ID: 6996abc55698665ec4f5cff3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Llama 3.1-8B"}. This record does not assert independent reproduction. ### EMBER (Multi) Success Rate: 0.438. Result ID: 6996abc55698665ec4f5cffa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen 3-14B"}. This record does not assert independent reproduction. ### EMBER (Multi) Success Rate: 0.42. Result ID: 6996abc55698665ec4f5cff9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen 3-8B"}. This record does not assert independent reproduction. ### EMBER (Multi) Success Rate: 0.356. Result ID: 6996abc55698665ec4f5cff7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Mistral 0.3-7B"}. This record does not assert independent reproduction. ### EMBER (Single) Success Rate: 0.352. Result ID: 6996abc55698665ec4f5cff5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen 3-14B"}. This record does not assert independent reproduction. ### SFT Success Rate: 0.233. Result ID: 6996abc55698665ec4f5cfed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Mistral 0.3-7B"}. This record does not assert independent reproduction. ### Prior Knowledge (Bench) Success Rate: 0.206. Result ID: 6996abc55698665ec4f5cfe3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Mistral 0.3-7B"}. This record does not assert independent reproduction. ### EMBER (Multi) Success Rate: 0.206. Result ID: 6996abc55698665ec4f5cffb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen 3-32B"}. This record does not assert independent reproduction. ### EMBER (Single) Success Rate: 0.183. Result ID: 6996abc55698665ec4f5cff6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen 3-32B"}. This record does not assert independent reproduction. ### SFT Success Rate: 0.142. Result ID: 6996abc55698665ec4f5cff0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen 3-14B"}. This record does not assert independent reproduction. ### SFT Success Rate: 0.069. Result ID: 6996abc55698665ec4f5cff1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen 3-32B"}. This record does not assert independent reproduction. ### SFT Success Rate: 0.065. Result ID: 6996abc55698665ec4f5cfef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen 3-8B"}. This record does not assert independent reproduction. ### Prior Knowledge (Prompt) Success Rate: 0.027. Result ID: 6996abc55698665ec4f5cfe8. [Reporting paper]() Recorded evaluation configuration: {"Target Model":"Mistral 0.3-7B"}. This record does not assert independent reproduction. ### Prior Knowledge (Prompt) Success Rate: 0.027. Result ID: 6996abc55698665ec4f5cfea. [Reporting paper]() Recorded evaluation configuration: {"Target Model":"Qwen 3-8B"}. This record does not assert independent reproduction. ### Prior Knowledge (Bench) Success Rate: 0.014. Result ID: 6996abc55698665ec4f5cfe7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen 3-32B"}. This record does not assert independent reproduction. ### Prior Knowledge (Prompt) Success Rate: 0.014. Result ID: 6996abc55698665ec4f5cfe9. [Reporting paper]() Recorded evaluation configuration: {"Target Model":"Llama 3.1-8B"}. This record does not assert independent reproduction. ### Prior Knowledge (Prompt) Success Rate: 0.014. Result ID: 6996abc55698665ec4f5cfeb. [Reporting paper]() Recorded evaluation configuration: {"Target Model":"Qwen 3-14B"}. This record does not assert independent reproduction. ### Prior Knowledge (Prompt) Success Rate: 0.014. Result ID: 6996abc55698665ec4f5cfec. [Reporting paper]() Recorded evaluation configuration: {"Target Model":"Qwen 3-32B"}. This record does not assert independent reproduction. ### SFT Success Rate: 0.009. Result ID: 6996abc55698665ec4f5cfee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Llama 3.1-8B"}. This record does not assert independent reproduction. ### Prior Knowledge (Bench) Success Rate: 0. Result ID: 6996abc55698665ec4f5cfe4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Llama 3.1-8B"}. This record does not assert independent reproduction. ### Prior Knowledge (Bench) Success Rate: 0. Result ID: 6996abc55698665ec4f5cfe5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen 3-8B"}. This record does not assert independent reproduction. ### Prior Knowledge (Bench) Success Rate: 0. Result ID: 6996abc55698665ec4f5cfe6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen 3-14B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.