Qwen3-235B-A22B-Thinking-2507

Home/Models/Qwen/Qwen3-235B-A22B-Thinking-2507

Qwen/Qwen3-235B-A22B-Thinking-2507

kind: original
quant: bf16 (16-bit)
family: qwen
modality: text-generation
root model: Qwen/Qwen3-235B-A22B-Thinking-2507
provider: Qwen
license: apache-2.0
language: —
context: 262,144
library: transformers
vRAM (GB): —
size on disk: —
downloads: 20,387
likes: 408
created: —
last modified: 2025-08-17T08:20:17+00:00 (2025)
huggingface: https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507
tags: transformerssafetensorsqwen3_moetext-generationconversationalarxiv:2402.17463arxiv:2407.02490arxiv:2501.15383arxiv:2404.06654arxiv:2505.09388license:apache-2.0eval-resultsendpoints_compatibledeploy:azureregion:us

benchmark	category	score	context	conf	evidence
MMLU	knowledge	93.4	MMLU-Redux	medium	`\| MMLU-Redux \| 93.4 \| 92.8 \| 94.9 \| 94.4 \| 94.6 \| 92.7 \| 93.8 \|`
AIME 2025	math	87.5	AIME25	medium	`\| AIME25 \| 87.5 \| 92.7* \| 88.9* \| 88.0 \| 75.5 \| 81.5 \| 92.3 \|`
MMLU-Pro	knowledge	85.0	MMLU-Pro	medium	`\| MMLU-Pro \| 85.0 \| 81.9 \| 85.9 \| 85.6 \| - \| 82.8 \| 84.4 \|`
GPQA	reasoning	81.0	GPQA	medium	`\| GPQA \| 81.0 \| 81.4* \| 83.3* \| 86.4 \| 79.6 \| 71.1 \| 81.1 \|`
MMLU-Pro	knowledge	80.6	MMLU-ProX	medium	`\| MMLU-ProX \| 80.6 \| 79.0 \| 83.3 \| 84.7 \| - \| 80.0 \| 81.0 \|`
IFEval	instruction-following	79.1	IFEval	medium	`\| IFEval \| 79.1 \| 92.4 \| 92.1 \| 90.8 \| 89.7 \| 83.4 \| 87.8 \|`
Chatbot Arena	chat	72.2	Arena-Hard v2$	medium	`\| Arena-Hard v2$ \| 72.2 \| 59.3 \| 80.8 \| 72.5 \| 59.1 \| 61.5 \| 79.7 \|`
LiveCodeBench	coding	68.7	LiveCodeBench v6 (25.02-25.05)	medium	`\| LiveCodeBench v6 (25.02-25.05) \| 68.7 \| 71.8 \| 58.6 \| 72.5 \| 48.9 \| 55.7 \| 74.1 \|`
BFCL (function calling)	agentic	63.8	BFCL-v3	medium	`\| BFCL-v3 \| 63.8 \| 67.2 \| 72.4 \| 67.2 \| 61.8 \| 70.8 \| 71.9 \|`
Humanity's Last Exam	knowledge	18.1	HLE	medium	`\| HLE \| 17.7# \| 18.1* \| 20.3 \| 21.6 \| 10.7 \| 11.8# \| 18.2# \|`

none scraped.