Q1 How strong is it across many tests combined? AA Intelligence Index · Bottom 19%#96 Q1 How strong is it across many tests combined? AA Intelligence Index · Bottom 19%#96 Q2 Which AI gives the answers people prefer most? Arena Text · Bottom 41%#59 Q3 Does it have broad knowledge across expert fields? MMLU-Pro · Bottom 47%#16
Q1 Bottom 19%#96 of 117 14.3 Q2 1446 Q3 83.0% About AA Intelligence Index More about AA Intelligence Index
Q Can it handle customer service by the rules? TAU2 · Bottom 42%#47
Q Can it handle customer service by the rules? TAU2 · Bottom 42%#47
Bottom 42%#47 of 79 83.9% About TAU2 More about TAU2
Q1 Can it pull scattered facts from several long documents into one answer? Long Context Reasoning · Bottom 1%#116 Q1 Can it pull scattered facts from several long documents into one answer? Long Context Reasoning · Bottom 1%#116 Q2 Which AI gives the business answers people prefer most? Arena Business, Management & Finance · Bottom 37%#63
Q1 Bottom 1%#116 of 116 7.0% Q2 1441 About Long Context Reasoning More about Long Context Reasoning
Q Which AI gives answers people prefer most, without false claims? Arena Text Factuality · Bottom 42%#54
Q Which AI gives answers people prefer most, without false claims? Arena Text Factuality · Bottom 42%#54
Bottom 42%#54 of 90 1445 About Arena Text Factuality More about Arena Text Factuality
Q1 Which AI gives the coding answers people prefer most? Arena Coding · Bottom 33%#66 Q1 Which AI gives the coding answers people prefer most? Arena Coding · Bottom 33%#66 Q2 Can it operate a computer itself to crack the toughest development jobs? TerminalBench Hard · Bottom 28%#58 Q3 How strong is its overall coding? AA Coding Index · Bottom 18%#83 Q1 Bottom 33%#66 of 97 1490 Q2 25.0% Q3 29.2 Q4 81.2% Q5 37.5% Q6 1484 About Arena Coding More about Arena Coding
Q1 Which AI gives the writing and literature answers people prefer most? Arena Writing, Literature & Language · Bottom 33%#66 Q1 Which AI gives the writing and literature answers people prefer most? Arena Writing, Literature & Language · Bottom 33%#66 Q2 Which AI do people prefer most in long conversations? Arena Multi-turn · Bottom 32%#67 Q3 Does it follow tricky rules like format and length without missing any? IFBench · Bottom 5%#78 Q1 Bottom 33%#66 of 97 1419 Q2 1442 Q3 41.4% Q4 1422 Q5 1425 Q6 1412 About Arena Writing, Literature & Language More about Arena Writing, Literature & Language
Q1 Can it solve problems that stump experts across fields? Humanity's Last Exam · Bottom 18%#97 Q1 Can it solve problems that stump experts across fields? Humanity's Last Exam · Bottom 18%#97 Q2 Which AI gives the math answers people prefer most? Arena Math · Bottom 32%#65 Q3 Can it solve graduate-level science problems? GPQA Diamond · Bottom 20%#84 Q1 Bottom 18%#97 of 117 13.3% Q2 1435 Q3 77.7% Q4 85.0 Q5 85.0% Q6 1458 Q7 1435 About Humanity's Last Exam More about Humanity's Last Exam
Q1 Can it read charts and answer accurately? CharXiv · Bottom 4%#31 Q1 Can it read charts and answer accurately? CharXiv · Bottom 4%#31 Q2 Can it solve college-level problems with images and diagrams? MMMU-Pro · Bottom 22%#30
Q1 Bottom 4%#31 of 31 67.1% Self-reported by developer Q2 68.6% About CharXiv More about CharXiv
Q1 Which AI do people prefer most when asking in Korean? Arena Korean · Bottom 42%#47 Q1 Which AI do people prefer most when asking in Korean? Arena Korean · Bottom 42%#47 Q2 Which AI do people prefer most when asking in Japanese? Arena Japanese · Bottom 26%#57 Q3 Which AI do people prefer most on tough questions? Arena Hard Prompts · Bottom 39%#61 Q1 Bottom 42%#47 of 79 1402 Q2 1383 Q3 1464 Q4 1447 Q5 1471 Q6 1439 About Arena Korean More about Arena Korean