List your company

Robustness Evaluation on LLMBar

83.07AccuracyQwen3-30B-A3B-Thinking-2507
58.297264.728671.1677.5914Jan 7, 2026

Evaluation results

MethodLinks
Qwen3-30B-A3B-Thinking-2507variant=Thinking2026.0183.07
QwQ-32B2026.0179.31
DeepSeek-R12026.0179
Qwen3-Next-80B-A3B-Thinkingvariant=Thinking2026.0177.55
DeepSeek-V32026.0176.49
Qwen2.5-32B-Instructvariant=Instruct2026.0167.71
Qwen3-Next-80B-A3B-Instructvariant=Instruct2026.0164.55
Qwen3-30B-A3B-Instruct-2507variant=Instruct2026.0159.25