Benchmarks

13 results across 11 benchmarks

Benchmark results for Qwen3.6-35B-A3B
BenchmarkScoreSource
AI2D TEST92.7%alibabacloud.com for Qwen3.6-35B-A3B on AI2D TEST (opens in a new tab)AccuracyReported Launch postAlibaba Cloud CommunitySelf-reportedQwen TeamRecord for Qwen3.6-35B-A3B on AI2D TEST
CharXiv Reasoning — No toolsConfiguration: No tools78.0%huggingface.co for Qwen3.6-35B-A3B on CharXiv Reasoning — No tools (opens in a new tab)CharXiv AccuracyReported Model cardQwenSelf-reportedQwen TeamRecord for Qwen3.6-35B-A3B on CharXiv Reasoning — No tools
GPQA Diamond — Epoch AI harnessEffort: NoneConfiguration: Epoch AI harness84.8%epoch.ai for Qwen3.6-35B-A3B (none) on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)GPQA Diamond AccuracyReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Qwen3.6-35B-A3B on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness
GPQA Diamond — Epoch AI harnessConfiguration: Epoch AI harness83.8%epoch.ai for Qwen3.6-35B-A3B on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness (opens in a new tab)Archived copy (opens in a new tab)GPQA Diamond AccuracyReported Evaluated Benchmark leaderboardEpoch AIIndependentRecord for Qwen3.6-35B-A3B on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness
HallusionBench Original69.8%alibabacloud.com for Qwen3.6-35B-A3B on HallusionBench Original (opens in a new tab)AccuracyReported Launch postAlibaba Cloud CommunitySelf-reportedQwen TeamRecord for Qwen3.6-35B-A3B on HallusionBench Original
MMMU81.7%alibabacloud.com for Qwen3.6-35B-A3B on Massive Multi-discipline Multimodal Understanding MMMU (opens in a new tab)MMMU AccuracyReported Launch postAlibaba Cloud CommunitySelf-reportedQwen TeamRecord for Qwen3.6-35B-A3B on Massive Multi-discipline Multimodal Understanding MMMU
MathVista MINI86.4%alibabacloud.com for Qwen3.6-35B-A3B on MathVista MINI (opens in a new tab)AccuracyReported Launch postAlibaba Cloud CommunitySelf-reportedQwen TeamRecord for Qwen3.6-35B-A3B on MathVista MINI
MMLU-Pro Original85.2%alibabacloud.com for Qwen3.6-35B-A3B on MMLU-Pro Original (opens in a new tab)AccuracyReported Launch postAlibaba Cloud CommunitySelf-reportedQwen TeamRecord for Qwen3.6-35B-A3B on MMLU-Pro Original
MMMU-Pro No toolsConfiguration: No tools75.3%huggingface.co for Qwen3.6-35B-A3B on MMMU-Pro No tools (opens in a new tab)MMMU-Pro accuracySetting: Not statedReported Model cardQwenSelf-reportedQwen TeamRecord for Qwen3.6-35B-A3B on MMMU-Pro No tools
NL2Repo Bench Original29.4%huggingface.co for Qwen3.6-35B-A3B on NL2Repo Bench Original (opens in a new tab)Average test pass rateReported Model cardQwenSelf-reportedQwen TeamRecord for Qwen3.6-35B-A3B on NL2Repo Bench Original
SWE-bench Multilingual67.2%alibabacloud.com for Qwen3.6-35B-A3B on SWE-bench Multilingual (opens in a new tab)Resolved TasksReported Launch postAlibaba Cloud CommunitySelf-reportedQwen TeamRecord for Qwen3.6-35B-A3B on SWE-bench Multilingual
SWE-bench Verified73.4%alibabacloud.com for Qwen3.6-35B-A3B on SWE-bench Verified (opens in a new tab)Resolved TasksReported Launch postAlibaba Cloud CommunitySelf-reportedQwen TeamRecord for Qwen3.6-35B-A3B on SWE-bench Verified
Terminal-Bench 2.0 — Qwen3.6 Harbor/Terminus-2Configuration: Qwen3.6 Harbor/Terminus-2 harness51.5%alibabacloud.com for Qwen3.6-35B-A3B on Terminal-Bench 2.0 — Qwen3.6 Harbor/Terminus-2 (opens in a new tab)Terminal-Bench AccuracyReported Launch postAlibaba Cloud CommunitySelf-reportedQwen TeamRecord for Qwen3.6-35B-A3B on Terminal-Bench 2.0 — Qwen3.6 Harbor/Terminus-2