{"id":"model.alibaba.qwen.qwen3-235b-a22b-instruct-2507","name":"Qwen3-235B-A22B-Instruct-2507","family":"Qwen3","type":"instruct","modalities":["text"],"capabilities":[],"openness":{"weights":"open_weights","code":"not_disclosed","data":"not_disclosed","license":null,"deployment":"self_hostable","api":null},"keySpecs":{"contextWindowTokens":null,"extendedContextWindowTokens":null,"totalParameters":null,"activeParameters":null,"architectureType":null,"baseModel":null,"inputPriceUsdPerMtok":null,"outputPriceUsdPerMtok":null,"concurrencyLimitRequests":null},"organization":{"id":"org.alibaba-qwen","name":"阿里千问 / Qwen","websiteUrl":"https://qwen.ai/"},"brand":{"id":"brand.alibaba-qwen","name":"Qwen","websiteUrl":"https://qwen.ai"},"product":{"id":"product.alibaba-qwen.models","name":"Qwen Models","websiteUrl":"https://qwen.readthedocs.io/en/latest/"},"origin":"domestic","versions":[{"id":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","name":"Qwen3-235B-A22B-Instruct-2507","externalModelId":"Qwen/Qwen3-235B-A22B-Instruct-2507","kind":"date","releaseDate":"2025-07-21","datePrecision":"day","publicAvailableAt":null,"lifecycleStatus":"active","knowledgeCutoff":null,"claims":[{"id":"claim.version.alibaba.qwen.qwen3-instruct-2507.max-output","fieldKey":"max_output_tokens","value":{"unit":"tokens","value":16384},"rawValue":"16,384 maximum assistant message length for instruct models","ingestionOrigin":"curated_official","unit":"tokens","condition":"Qwen3-2507 instruct mode","status":"approved","confidence":"high","reviewedBy":"system:curated_official","reviewedAt":"2026-08-03 22:13:04.249287+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.alibaba.qwen.docs","title":"Qwen documentation","url":"https://qwen.readthedocs.io/en/latest/","accessedAt":"2026-09-17 15:20:45.271+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-09-17 15:17:00.621+08"},"evidence":{"id":"evidence.alibaba.qwen.docs.context","locator":"Key Concepts and Qwen3-2507 documentation","excerpt":"Qwen documents 119 languages and dialects for Qwen3. For Qwen3-2507, the maximum assistant message length is 81,920 tokens for thinking models and 16,384 tokens for instruct models; Qwen3-2507 supports 256K context and can be extended to 1M tokens."}},{"id":"claim.version.alibaba.qwen.qwen3-instruct-2507.release-date","fieldKey":"release_date","value":{"value":"2025-07-21","precision":"day"},"rawValue":"2025-07-21","ingestionOrigin":"curated_official","unit":null,"condition":"Official Qwen3 README News entry.","status":"approved","confidence":"high","reviewedBy":"system:curated_official","reviewedAt":"2026-08-05 23:43:29.286214+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.alibaba.qwen.qwen3.github","title":"QwenLM/Qwen3","url":"https://github.com/QwenLM/Qwen3","accessedAt":"2026-09-17 15:20:54.923+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-09-17 15:17:04.998+08"},"evidence":{"id":"evidence.alibaba.qwen.qwen3-2507.release-dates","locator":"README News entries dated 2025.07.21 and 2025.07.25","excerpt":"Qwen states that Qwen3-235B-A22B-Instruct-2507 was released on 2025-07-21 and Qwen3-235B-A22B-Thinking-2507 was released on 2025-07-25."}}],"benchmarks":[{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.aime25","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"AIME25","scoreNumeric":70.3,"scoreText":"70.3%","testSet":"AIME25","promptSettings":"Official Qwen3-2507 model-card comparison table; shot count, prompt template, sampling configuration, harness, and evaluation date are not specified.","evaluationDate":null,"evaluator":"Qwen Team","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.arc-agi","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"ARC-AGI","scoreNumeric":41.8,"scoreText":"41.8%","testSet":"ARC-AGI","promptSettings":"Official Qwen3-2507 model-card comparison table; shot count, prompt template, sampling configuration, harness, and evaluation date are not specified.","evaluationDate":null,"evaluator":"Qwen Team","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.aider-polyglot","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"Aider-Polyglot","scoreNumeric":57.3,"scoreText":"57.3%","testSet":"Aider-Polyglot","promptSettings":"Official Qwen3-2507 model-card comparison table; shot count, prompt template, sampling configuration, harness, and evaluation date are not specified.","evaluationDate":null,"evaluator":"Qwen Team","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.arena-hard-v2","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"Arena-Hard v2","scoreNumeric":79.2,"scoreText":"79.2%","testSet":"Arena-Hard v2","promptSettings":"Win rate evaluated by GPT-4.1; prompt and harness details are not specified in the table.","evaluationDate":null,"evaluator":"GPT-4.1","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.bfcl-v3","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"BFCL-v3","scoreNumeric":70.9,"scoreText":"70.9%","testSet":"BFCL-v3","promptSettings":"Official Qwen3-2507 model-card comparison table; shot count, prompt template, sampling configuration, harness, and evaluation date are not specified.","evaluationDate":null,"evaluator":"Qwen Team","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.csimpleqa","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"CSimpleQA","scoreNumeric":84.3,"scoreText":"84.3%","testSet":"CSimpleQA","promptSettings":"Official Qwen3-2507 model-card comparison table; shot count, prompt template, sampling configuration, harness, and evaluation date are not specified.","evaluationDate":null,"evaluator":"Qwen Team","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.creative-writing-v3","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"Creative Writing v3","scoreNumeric":87.5,"scoreText":"87.5%","testSet":"Creative Writing v3","promptSettings":"Official Qwen3-2507 model-card comparison table; shot count, prompt template, sampling configuration, harness, and evaluation date are not specified.","evaluationDate":null,"evaluator":"Qwen Team","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.gpqa","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"GPQA","scoreNumeric":77.5,"scoreText":"77.5%","testSet":"GPQA","promptSettings":"Official Qwen3-2507 model-card comparison table; shot count, prompt template, sampling configuration, harness, and evaluation date are not specified.","evaluationDate":null,"evaluator":"Qwen Team","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.hmmt25","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"HMMT25","scoreNumeric":55.4,"scoreText":"55.4%","testSet":"HMMT25","promptSettings":"Official Qwen3-2507 model-card comparison table; shot count, prompt template, sampling configuration, harness, and evaluation date are not specified.","evaluationDate":null,"evaluator":"Qwen Team","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.ifeval","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"IFEval","scoreNumeric":88.7,"scoreText":"88.7%","testSet":"IFEval","promptSettings":"Official Qwen3-2507 model-card comparison table; shot count, prompt template, sampling configuration, harness, and evaluation date are not specified.","evaluationDate":null,"evaluator":"Qwen Team","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.include","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"INCLUDE","scoreNumeric":79.5,"scoreText":"79.5%","testSet":"INCLUDE","promptSettings":"Official Qwen3-2507 model-card comparison table; shot count, prompt template, sampling configuration, harness, and evaluation date are not specified.","evaluationDate":null,"evaluator":"Qwen Team","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.livebench-20241125","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"LiveBench 20241125","scoreNumeric":75.4,"scoreText":"75.4%","testSet":"LiveBench 20241125","promptSettings":"Official Qwen3-2507 model-card comparison table; shot count, prompt template, sampling configuration, harness, and evaluation date are not specified.","evaluationDate":null,"evaluator":"Qwen Team","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.livecodebench-v6","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"LiveCodeBench v6 (25.02-25.05)","scoreNumeric":51.8,"scoreText":"51.8%","testSet":"LiveCodeBench v6 (25.02-25.05)","promptSettings":"Official Qwen3-2507 model-card comparison table; benchmark window is part of the test-set name; other harness details are not specified.","evaluationDate":null,"evaluator":"Qwen Team","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.mmlu-pro","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"MMLU-Pro","scoreNumeric":83,"scoreText":"83.0%","testSet":"MMLU-Pro","promptSettings":"Official Qwen3-2507 model-card comparison table; shot count, prompt template, sampling configuration, harness, and evaluation date are not specified.","evaluationDate":null,"evaluator":"Qwen Team","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.mmlu-prox","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"MMLU-ProX","scoreNumeric":79.4,"scoreText":"79.4%","testSet":"MMLU-ProX","promptSettings":"Official Qwen3-2507 model-card comparison table; shot count, prompt template, sampling configuration, harness, and evaluation date are not specified.","evaluationDate":null,"evaluator":"Qwen Team","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.mmlu-redux","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"MMLU-Redux","scoreNumeric":93.1,"scoreText":"93.1%","testSet":"MMLU-Redux","promptSettings":"Official Qwen3-2507 model-card comparison table; shot count, prompt template, sampling configuration, harness, and evaluation date are not specified.","evaluationDate":null,"evaluator":"Qwen Team","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.multiif","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"MultiIF","scoreNumeric":77.5,"scoreText":"77.5%","testSet":"MultiIF","promptSettings":"Official Qwen3-2507 model-card comparison table; shot count, prompt template, sampling configuration, harness, and evaluation date are not specified.","evaluationDate":null,"evaluator":"Qwen Team","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.multipl-e","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"MultiPL-E","scoreNumeric":87.9,"scoreText":"87.9%","testSet":"MultiPL-E","promptSettings":"Official Qwen3-2507 model-card comparison table; shot count, prompt template, sampling configuration, harness, and evaluation date are not specified.","evaluationDate":null,"evaluator":"Qwen Team","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.polymath","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"PolyMATH","scoreNumeric":50.2,"scoreText":"50.2%","testSet":"PolyMATH","promptSettings":"Official Qwen3-2507 model-card comparison table; shot count, prompt template, sampling configuration, harness, and evaluation date are not specified.","evaluationDate":null,"evaluator":"Qwen Team","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.ruler-1m-full-attention","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"RULER 1M (Full Attention)","scoreNumeric":92.5,"scoreText":"92.5%","testSet":"RULER 1M","promptSettings":"Full Attention; Dual Chunk Attention enabled; 260 samples per length across 13 sub-tasks (20 samples per sub-task); per-length scores are preserved in evidence.","evaluationDate":null,"evaluator":"Qwen Team","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.ruler-1m-sparse-attention","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"RULER 1M (Sparse Attention)","scoreNumeric":91.7,"scoreText":"91.7%","testSet":"RULER 1M","promptSettings":"Sparse Attention; Dual Chunk Attention enabled; 260 samples per length across 13 sub-tasks (20 samples per sub-task); per-length scores are preserved in evidence.","evaluationDate":null,"evaluator":"Qwen Team","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.simpleqa","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"SimpleQA","scoreNumeric":54.3,"scoreText":"54.3%","testSet":"SimpleQA","promptSettings":"Official Qwen3-2507 model-card comparison table; shot count, prompt template, sampling configuration, harness, and evaluation date are not specified.","evaluationDate":null,"evaluator":"Qwen Team","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.supergpqa","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"SuperGPQA","scoreNumeric":62.6,"scoreText":"62.6%","testSet":"SuperGPQA","promptSettings":"Official Qwen3-2507 model-card comparison table; shot count, prompt template, sampling configuration, harness, and evaluation date are not specified.","evaluationDate":null,"evaluator":"Qwen Team","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.tau1-airline","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"TAU1-Airline","scoreNumeric":44,"scoreText":"44.0%","testSet":"TAU1-Airline","promptSettings":"Results generated using GPT-4o-20241120 because native GPT-4o-0327 function calling was unavailable; other prompt and harness details are not specified.","evaluationDate":null,"evaluator":"GPT-4o-20241120","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.tau1-retail","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"TAU1-Retail","scoreNumeric":71.3,"scoreText":"71.3%","testSet":"TAU1-Retail","promptSettings":"Results generated using GPT-4o-20241120 because native GPT-4o-0327 function calling was unavailable; other prompt and harness details are not specified.","evaluationDate":null,"evaluator":"GPT-4o-20241120","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.tau2-airline","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"TAU2-Airline","scoreNumeric":50,"scoreText":"50.0%","testSet":"TAU2-Airline","promptSettings":"Results generated using GPT-4o-20241120 because native GPT-4o-0327 function calling was unavailable; other prompt and harness details are not specified.","evaluationDate":null,"evaluator":"GPT-4o-20241120","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.tau2-retail","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"TAU2-Retail","scoreNumeric":74.6,"scoreText":"74.6%","testSet":"TAU2-Retail","promptSettings":"Results generated using GPT-4o-20241120 because native GPT-4o-0327 function calling was unavailable; other prompt and harness details are not specified.","evaluationDate":null,"evaluator":"GPT-4o-20241120","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.tau2-telecom","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"TAU2-Telecom","scoreNumeric":32.5,"scoreText":"32.5%","testSet":"TAU2-Telecom","promptSettings":"Results generated using GPT-4o-20241120 because native GPT-4o-0327 function calling was unavailable; other prompt and harness details are not specified.","evaluationDate":null,"evaluator":"GPT-4o-20241120","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.writingbench","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"WritingBench","scoreNumeric":85.2,"scoreText":"85.2%","testSet":"WritingBench","promptSettings":"Official Qwen3-2507 model-card comparison table; shot count, prompt template, sampling configuration, harness, and evaluation date are not specified.","evaluationDate":null,"evaluator":"Qwen Team","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}},{"id":"benchmark.alibaba.qwen.qwen3-instruct-2507.zebralogic","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","benchmarkName":"ZebraLogic","scoreNumeric":95,"scoreText":"95.0%","testSet":"ZebraLogic","promptSettings":"Official Qwen3-2507 model-card comparison table; shot count, prompt template, sampling configuration, harness, and evaluation date are not specified.","evaluationDate":null,"evaluator":"Qwen Team","comparabilityStatus":"partially_comparable","source":{"id":"source.alibaba.qwen.qwen3-instruct-2507","title":"Qwen3-235B-A22B-Instruct-2507 model card","url":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"}}]}],"dataUpdatedAt":"2026-08-05 23:43:29.286214+08","latestVersion":{"id":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","name":"Qwen3-235B-A22B-Instruct-2507","externalModelId":"Qwen/Qwen3-235B-A22B-Instruct-2507","status":"active"},"dataQuality":{"approved":2,"pending":0,"stale":45,"conflicted":0},"availabilityRegions":[],"availabilityChannels":[],"availabilityScopes":[],"decisionReadiness":{"overall":"incomplete","evaluatedAt":"2026-11-01T12:51:30.089Z","tracks":[{"key":"api","applicable":false,"grade":"incomplete","verifiedAt":null,"satisfiedFields":[],"missingFields":[],"missingEvidenceFields":[],"staleFields":[],"conflictedFields":[],"ineligibleSourceFields":[],"reasons":[],"fields":[]},{"key":"self_hosted","applicable":false,"grade":"incomplete","verifiedAt":null,"satisfiedFields":[],"missingFields":[],"missingEvidenceFields":[],"staleFields":[],"conflictedFields":[],"ineligibleSourceFields":[],"reasons":[],"fields":[]}]},"timeline":[{"id":"timeline.version.version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","kind":"version","subjectId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","date":"2025-07-21","datePrecision":"day","title":"Qwen3-235B-A22B-Instruct-2507","summary":"模型版本 · active","eventType":"version","lifecycleStatus":"active","source":null},{"id":"event.alibaba.qwen.qwen3-instruct-2507.release","kind":"event","subjectId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","date":"2025-07-21","datePrecision":"day","title":"Qwen3-235B-A22B-Instruct-2507 发布","summary":"Qwen 官方仓库记录 235B 非思考模式 2507 更新于 2025-07-21 发布。","eventType":"release","lifecycleStatus":null,"source":{"id":"source.alibaba.qwen.qwen3.github","title":"QwenLM/Qwen3","url":"https://github.com/QwenLM/Qwen3"}}],"availability":[],"enterpriseCases":[],"useCases":[],"deploymentProfiles":[],"learningResources":[],"trainingProfiles":[{"id":"training-profile.llamafactory.qwen3-235b-instruct-2507.887b850","modelId":"model.alibaba.qwen.qwen3-235b-a22b-instruct-2507","modelName":"Qwen3-235B-A22B-Instruct-2507","versionId":"version.alibaba.qwen.qwen3-235b-a22b-instruct-2507","versionName":"Qwen3-235B-A22B-Instruct-2507","tool":"llamafactory","toolRef":"887b850813d80a8d893ec56703d5b3a0eec46de6","supportStatus":"supported","template":"qwen3_nothink","trainingStages":["sft","dpo","kto","orpo","simpo"],"tuningMethods":["full","freeze","lora","qlora"],"modalities":["text"],"modelLocator":"YOUR_QWEN3_235B_INSTRUCT_2507_MODEL_PATH","notes":"README 的 Qwen3 模板说明思考与非思考模式需选择对应 template；本档案使用 qwen3_nothink，不推断其他运行参数。","verifiedAt":"2026-08-09 00:00:00+08","source":{"id":"source.llamafactory.readme.2026-08-09","title":"LlamaFactory README（固定 887b850 工具快照）","url":"https://github.com/hiyouga/LlamaFactory/blob/887b850813d80a8d893ec56703d5b3a0eec46de6/README_zh.md"},"evidence":{"id":"evidence.llamafactory.readme.models.2026-08-09","locator":"README：模型表、模板说明与训练方法","excerpt":"LlamaFactory README names DeepSeek 3-3.2 with template deepseek3, Llama 4 with template llama4, Qwen3 with templates qwen3/qwen3_nothink, and lists pretraining, SFT, reward-model, PPO, DPO, KTO, ORPO and SimPO training methods. It states that instruct/chat models must use their corresponding template."}}],"publication":{"approvedClaimsOnly":true,"note":"页面只展示已审核 Claim；待审核数据不会被当作公开事实。"}}