# Science Question Answering on ARC-C French (test) Source: [Science Question Answering on ARC-C French (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:32:59.329Z Evaluation of model performance on the French subset (test split) of the ARC-C dataset for Science Question Answering. 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 | Science Question Answering | | Dataset (including any stated split) | ARC-C French (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Trinity Large (MoE) | 90 | Not recorded | 6995476c09c33900fcd6d4aa | | Qwen3 8B | 87 | Not recorded | 6995476c09c33900fcd6d4aa | | Qwen3 4B | 84 | Not recorded | 6995476c09c33900fcd6d4aa | | Datology 8B | 74 | Not recorded | 6995476c09c33900fcd6d4aa | | Granite-4.0 Micro | 70 | Not recorded | 6995476c09c33900fcd6d4aa | | Llama-3.1 8B | 68 | Not recorded | 6995476c09c33900fcd6d4aa | | SmolLM3 3B | 68 | Not recorded | 6995476c09c33900fcd6d4aa | | LFM2.5 1.2B | 65 | Not recorded | 6995476c09c33900fcd6d4aa | | Datology 3B | 58 | Not recorded | 6995476c09c33900fcd6d4aa | | Llama-3.2 3B | 54 | Not recorded | 6995476c09c33900fcd6d4aa | | Llama-3.2 1B | 31 | Not recorded | 6995476c09c33900fcd6d4aa | | Arrow | 27.51 | Not recorded | 68fa7a661e209131cea82edb | | Phi-2 | 26.84 | Not recorded | 68fa7a661e209131cea82edb | | GenKnowSub | 25.5 | Not recorded | 68fa7a661e209131cea82edb | | GenKnowSub | 24.16 | Not recorded | 68fa7a661e209131cea82edb | ### Trinity Large (MoE) Accuracy: 90. Result ID: 699ab0c55698665ec43e332f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Architecture":"MoE","Evaluation":"zero-shot"}. This record does not assert independent reproduction. ### Qwen3 8B Accuracy: 87. Result ID: 699ab0c55698665ec43e332b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model size":"8B","Evaluation":"zero-shot"}. This record does not assert independent reproduction. ### Qwen3 4B Accuracy: 84. Result ID: 699ab0c55698665ec43e332a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model size":"4B","Evaluation":"zero-shot"}. This record does not assert independent reproduction. ### Datology 8B Accuracy: 74. Result ID: 699ab0c55698665ec43e3326. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model size":"8B","Evaluation":"zero-shot"}. This record does not assert independent reproduction. ### Granite-4.0 Micro Accuracy: 70. Result ID: 699ab0c55698665ec43e332d. [Reporting paper]() Recorded evaluation configuration: {"Evaluation":"zero-shot"}. This record does not assert independent reproduction. ### Llama-3.1 8B Accuracy: 68. Result ID: 699ab0c55698665ec43e3329. [Reporting paper]() Recorded evaluation configuration: {"Model size":"8B","Evaluation":"zero-shot"}. This record does not assert independent reproduction. ### SmolLM3 3B Accuracy: 68. Result ID: 699ab0c55698665ec43e332c. [Reporting paper]() Recorded evaluation configuration: {"Model size":"3B","Evaluation":"zero-shot"}. This record does not assert independent reproduction. ### LFM2.5 1.2B Accuracy: 65. Result ID: 699ab0c55698665ec43e332e. [Reporting paper]() Recorded evaluation configuration: {"Model size":"1.2B","Evaluation":"zero-shot"}. This record does not assert independent reproduction. ### Datology 3B Accuracy: 58. Result ID: 699ab0c55698665ec43e3325. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model size":"3B","Evaluation":"zero-shot"}. This record does not assert independent reproduction. ### Llama-3.2 3B Accuracy: 54. Result ID: 699ab0c55698665ec43e3328. [Reporting paper]() Recorded evaluation configuration: {"Model size":"3B","Evaluation":"zero-shot"}. This record does not assert independent reproduction. ### Llama-3.2 1B Accuracy: 31. Result ID: 699ab0c55698665ec43e3327. [Reporting paper]() Recorded evaluation configuration: {"Model size":"1B","Evaluation":"zero-shot"}. This record does not assert independent reproduction. ### Arrow Accuracy: 27.51. Result ID: 698b76e27a967eddb76ecd35. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Phi-2","Evaluation Setting":"Zero-shot"}. This record does not assert independent reproduction. ### Phi-2 Accuracy: 26.84. Result ID: 698b76e27a967eddb76ecd34. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Phi-2","Evaluation Setting":"Zero-shot"}. This record does not assert independent reproduction. ### GenKnowSub Accuracy: 25.5. Result ID: 698b76e27a967eddb76ecd36. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Phi-2","Evaluation Setting":"Zero-shot","Setting":"En"}. This record does not assert independent reproduction. ### GenKnowSub Accuracy: 24.16. Result ID: 698b76e27a967eddb76ecd37. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Phi-2","Evaluation Setting":"Zero-shot","Setting":"Avg"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.