Agentic
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)60.87sResponse Time (max)60.87sResponse Time (total)60.87s
Anti-AI Tricks
: 8.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.92sResponse Time (max)2.74sResponse Time (total)7.66s
Coding
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.25sResponse Time (max)2.79sResponse Time (total)6.76s
Combined
: 3.8 A test is fully passed only if every run passed for that test.API error: 1Wrong answer: 1Response Time (avg)11.93sResponse Time (max)15.38sResponse Time (total)23.85s
Data parsing and extraction
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.36sResponse Time (max)2.47sResponse Time (total)4.72s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)1.94sResponse Time (max)2.22sResponse Time (total)5.81s
General Intelligence
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.11sResponse Time (max)2.11sResponse Time (total)2.11s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.40sResponse Time (max)3.17sResponse Time (total)4.80s
Puzzle Solving
: 8.7 A test is fully passed only if every run passed for that test.Did not follow instructions: 1Response Time (avg)2.18sResponse Time (max)2.42sResponse Time (total)6.55s
Tool Calling
: 4.7 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)6.57sResponse Time (max)6.57sResponse Time (total)6.57s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.96sResponse Time (max)1.96sResponse Time (total)1.96s
Agentic
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)45.58sResponse Time (max)45.58sResponse Time (total)45.58s
Anti-AI Tricks
: 8.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)4.16sResponse Time (max)11.32sResponse Time (total)16.65s
Coding
: 5.6 A test is fully passed only if every run passed for that test.Did not follow instructions: 1No answer: 1Response Time (avg)199.23sResponse Time (max)301.09sResponse Time (total)597.69s
Combined
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)104.92sResponse Time (max)201.92sResponse Time (total)209.84s
Data parsing and extraction
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.99sResponse Time (max)2.42sResponse Time (total)3.97s
Domain specific
: 5.9 A test is fully passed only if every run passed for that test.No answer: 1Wrong answer: 1Response Time (avg)260.29sResponse Time (max)605.14sResponse Time (total)780.87s
General Intelligence
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)3.52sResponse Time (max)3.52sResponse Time (total)3.52s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.73sResponse Time (max)1.91sResponse Time (total)3.45s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.43sResponse Time (max)2.43sResponse Time (total)2.43s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)97.77sResponse Time (max)97.77sResponse Time (total)97.77s
Agentic
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)76.95sResponse Time (max)76.95sResponse Time (total)76.95s
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)5.67sResponse Time (max)7.12sResponse Time (total)22.67s
Coding
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)155.16sResponse Time (max)236.14sResponse Time (total)465.48s
Combined
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)35.56sResponse Time (max)51.56sResponse Time (total)71.11s
Data parsing and extraction
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)7.63sResponse Time (max)8.37sResponse Time (total)15.26s
Domain specific
: 4.1 A test is fully passed only if every run passed for that test.Wrong answer: 2No answer: 1Response Time (avg)301.27sResponse Time (max)676.83sResponse Time (total)903.82s
Instructions following
: 9.8 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)6.23sResponse Time (max)8.15sResponse Time (total)12.47s
Puzzle Solving
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)7.88sResponse Time (max)14.72sResponse Time (total)23.65s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)5.71sResponse Time (max)5.71sResponse Time (total)5.71s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.No answer: 1Response Time (avg)60.58sResponse Time (max)60.58sResponse Time (total)60.58s
A test is fully passed only if every run passed for that test.Wrong answer: 3No answer: 2Timed out: 1Response Time (avg)26.88sResponse Time (max)102.40sResponse Time (total)591.34s…
Agentic
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)102.40sResponse Time (max)102.40sResponse Time (total)102.40s
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)5.89sResponse Time (max)7.10sResponse Time (total)23.56s
Coding
: 8.2 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)40.96sResponse Time (max)60.28sResponse Time (total)122.88s
Combined
: 5.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)51.96sResponse Time (max)51.96sResponse Time (total)51.96s
Data parsing and extraction
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)13.44sResponse Time (max)16.02sResponse Time (total)26.88s
General Intelligence
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)17.39sResponse Time (max)17.39sResponse Time (total)17.39s
Instructions following
: 9.9 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)7.90sResponse Time (max)10.13sResponse Time (total)15.80s
Puzzle Solving
: 8.2 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)13.13sResponse Time (max)25.90sResponse Time (total)39.40s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)20.41sResponse Time (max)20.41sResponse Time (total)20.41s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.No answer: 1Response Time (avg)34.25sResponse Time (max)34.25sResponse Time (total)34.25s
A test is fully passed only if every run passed for that test.Wrong answer: 8Response Time (avg)8.93sResponse Time (max)54.74sResponse Time (total)205.39s…
Agentic
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)54.74sResponse Time (max)54.74sResponse Time (total)54.74s
Anti-AI Tricks
: 8.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)2.22sResponse Time (max)3.03sResponse Time (total)8.87s
Coding
: 6.1 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)7.19sResponse Time (max)9.73sResponse Time (total)21.57s
Combined
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)11.10sResponse Time (max)15.93sResponse Time (total)22.19s
Data parsing and extraction
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)872msResponse Time (max)920msResponse Time (total)1.74s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)21.52sResponse Time (max)41.68sResponse Time (total)64.57s
General Intelligence
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)2.37sResponse Time (max)2.37sResponse Time (total)2.37s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.43sResponse Time (max)1.84sResponse Time (total)2.87s
Puzzle Solving
: 8.4 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)3.78sResponse Time (max)6.96sResponse Time (total)11.33s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)5.09sResponse Time (max)5.09sResponse Time (total)5.09s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)10.05sResponse Time (max)10.05sResponse Time (total)10.05s
Agentic
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)69.33sResponse Time (max)69.33sResponse Time (total)69.33s
Anti-AI Tricks
: 8.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)17.99sResponse Time (max)48.33sResponse Time (total)71.98s
Coding
: 8.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)156.74sResponse Time (max)254.92sResponse Time (total)470.22s
Combined
: 6.4 A test is fully passed only if every run passed for that test.No answer: 1Response Time (avg)58.52sResponse Time (max)79.36sResponse Time (total)117.04s
Data parsing and extraction
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)9.07sResponse Time (max)12.19sResponse Time (total)18.14s
Domain specific
: 3.6 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)84.35sResponse Time (max)168.71sResponse Time (total)253.05s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)7.26sResponse Time (max)9.02sResponse Time (total)14.52s
Puzzle Solving
: 9.0 A test is fully passed only if every run passed for that test.Did not follow instructions: 1Response Time (avg)10.23sResponse Time (max)11.54sResponse Time (total)30.68s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)12.38sResponse Time (max)12.38sResponse Time (total)12.38s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)48.32sResponse Time (max)48.32sResponse Time (total)48.32s
A test is fully passed only if every run passed for that test.Wrong answer: 5Invalid tool call: 2Response Time (avg)54.31sResponse Time (max)601.80sResponse Time (total)1249.02s…
Agentic
: 7.4 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)93.37sResponse Time (max)93.37sResponse Time (total)93.37s
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)6.91sResponse Time (max)11.38sResponse Time (total)27.65s
Coding
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)24.94sResponse Time (max)38.41sResponse Time (total)74.83s
Combined
: 4.6 A test is fully passed only if every run passed for that test.Invalid tool call: 1Wrong answer: 1Response Time (avg)36.74sResponse Time (max)54.74sResponse Time (total)73.47s
Data parsing and extraction
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.83sResponse Time (max)5.38sResponse Time (total)9.65s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)274.56sResponse Time (max)601.80sResponse Time (total)823.68s
General Intelligence
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)8.92sResponse Time (max)8.92sResponse Time (total)8.92s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)5.71sResponse Time (max)6.71sResponse Time (total)11.41s
Puzzle Solving
: 8.2 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)8.23sResponse Time (max)9.84sResponse Time (total)24.70s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)11.68sResponse Time (max)11.68sResponse Time (total)11.68s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)89.65sResponse Time (max)89.65sResponse Time (total)89.65s
Agentic
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)90.18sResponse Time (max)90.18sResponse Time (total)90.18s
Anti-AI Tricks
: 8.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)39.56sResponse Time (max)120.09sResponse Time (total)158.26s
Coding
: 7.0 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)109.70sResponse Time (max)141.71sResponse Time (total)329.11s
Combined
: 7.3 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)99.12sResponse Time (max)173.03sResponse Time (total)198.23s
Data parsing and extraction
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)24.88sResponse Time (max)30.28sResponse Time (total)49.75s
Domain specific
: 4.1 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)238.45sResponse Time (max)485.92sResponse Time (total)715.34s
Instructions following
: 9.8 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)12.20sResponse Time (max)21.22sResponse Time (total)24.41s
Puzzle Solving
: 9.9 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)12.50sResponse Time (max)20.68sResponse Time (total)37.50s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)55.56sResponse Time (max)55.56sResponse Time (total)55.56s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)10.02sResponse Time (max)10.02sResponse Time (total)10.02s
Agentic
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)64.54sResponse Time (max)64.54sResponse Time (total)64.54s
Anti-AI Tricks
: 5.7 A test is fully passed only if every run passed for that test.Wrong answer: 2No answer: 1Response Time (avg)25.70sResponse Time (max)48.19sResponse Time (total)102.80s
Coding
: 6.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)243.00sResponse Time (max)416.76sResponse Time (total)729.00s
Combined
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)78.99sResponse Time (max)119.80sResponse Time (total)157.97s
Data parsing and extraction
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)25.03sResponse Time (max)27.49sResponse Time (total)50.06s
Domain specific
: 3.6 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)249.47sResponse Time (max)387.23sResponse Time (total)748.42s
General Intelligence
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)8.83sResponse Time (max)8.83sResponse Time (total)8.83s
Tool Calling
: 9.8 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)15.92sResponse Time (max)15.92sResponse Time (total)15.92s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)34.01sResponse Time (max)34.01sResponse Time (total)34.01s
A test is fully passed only if every run passed for that test.Wrong answer: 3Invalid tool call: 1Timed out: 1Response Time (avg)14.12sResponse Time (max)150.60sResponse Time (total)310.55s…
Agentic
: 5.2 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)150.60sResponse Time (max)150.60sResponse Time (total)150.60s
Anti-AI Tricks
: 8.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.85sResponse Time (max)2.71sResponse Time (total)7.38s
Coding
: 7.6 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)12.96sResponse Time (max)23.18sResponse Time (total)38.89s
Combined
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)43.42sResponse Time (max)65.40sResponse Time (total)86.85s
Data parsing and extraction
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.37sResponse Time (max)3.30sResponse Time (total)4.74s
Domain specific
: 7.7 A test is fully passed only if every run passed for that test.Timed out: 1Response Time (avg)1.19sResponse Time (max)1.43sResponse Time (total)2.38s
General Intelligence
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.87sResponse Time (max)2.87sResponse Time (total)2.87s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.57sResponse Time (max)1.66sResponse Time (total)3.14s
Puzzle Solving
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.43sResponse Time (max)2.89sResponse Time (total)7.28s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.17sResponse Time (max)4.17sResponse Time (total)4.17s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)2.25sResponse Time (max)2.25sResponse Time (total)2.25s
Agentic
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)148.13sResponse Time (max)148.13sResponse Time (total)148.13s
Anti-AI Tricks
: 8.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)28.51sResponse Time (max)39.73sResponse Time (total)114.05s
Coding
: 7.8 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)50.60sResponse Time (max)62.48sResponse Time (total)151.79s
Combined
: 6.4 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)104.10sResponse Time (max)131.63sResponse Time (total)208.20s
Data parsing and extraction
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)28.03sResponse Time (max)30.49sResponse Time (total)56.07s
Domain specific
: 3.6 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)115.42sResponse Time (max)218.13sResponse Time (total)346.26s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)15.36sResponse Time (max)19.53sResponse Time (total)30.73s
Puzzle Solving
: 8.2 A test is fully passed only if every run passed for that test.Did not follow instructions: 1Response Time (avg)26.11sResponse Time (max)32.37sResponse Time (total)78.32s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)74.73sResponse Time (max)74.73sResponse Time (total)74.73s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)54.46sResponse Time (max)54.46sResponse Time (total)54.46s
A test is fully passed only if every run passed for that test.Wrong answer: 7API error: 1Response Time (avg)28.04sResponse Time (max)149.84sResponse Time (total)645.03s…
Agentic
: 6.1 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)56.02sResponse Time (max)56.02sResponse Time (total)56.02s
Anti-AI Tricks
: 8.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)3.32sResponse Time (max)5.98sResponse Time (total)13.28s
Coding
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)40.66sResponse Time (max)56.87sResponse Time (total)121.97s
Combined
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)24.73sResponse Time (max)34.30sResponse Time (total)49.47s
Data parsing and extraction
: 6.5 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)3.80sResponse Time (max)7.39sResponse Time (total)7.61s
Domain specific
: 3.5 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)95.58sResponse Time (max)149.84sResponse Time (total)286.75s
General Intelligence
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.34sResponse Time (max)4.34sResponse Time (total)4.34s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)8.38sResponse Time (max)14.30sResponse Time (total)16.75s
Puzzle Solving
: 8.2 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)9.39sResponse Time (max)20.40sResponse Time (total)28.16s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)13.83sResponse Time (max)13.83sResponse Time (total)13.83s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)46.86sResponse Time (max)46.86sResponse Time (total)46.86s
A test is fully passed only if every run passed for that test.Wrong answer: 8Response Time (avg)18.39sResponse Time (max)111.09sResponse Time (total)422.93s…
Agentic
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)60.15sResponse Time (max)60.15sResponse Time (total)60.15s
Anti-AI Tricks
: 8.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)2.99sResponse Time (max)4.94sResponse Time (total)11.95s
Coding
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)15.63sResponse Time (max)32.41sResponse Time (total)46.88s
Combined
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)19.05sResponse Time (max)24.81sResponse Time (total)38.10s
Data parsing and extraction
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.18sResponse Time (max)2.64sResponse Time (total)4.36s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)62.87sResponse Time (max)111.09sResponse Time (total)188.61s
General Intelligence
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)3.65sResponse Time (max)3.65sResponse Time (total)3.65s
Instructions following
: 9.9 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.79sResponse Time (max)1.96sResponse Time (total)3.58s
Puzzle Solving
: 7.6 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)14.55sResponse Time (max)38.14sResponse Time (total)43.66s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.98sResponse Time (max)4.98sResponse Time (total)4.98s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)17.00sResponse Time (max)17.00sResponse Time (total)17.00s
A test is fully passed only if every run passed for that test.Wrong answer: 7API error: 1Invalid tool call: 1Response Time (avg)40.33sResponse Time (max)392.56sResponse Time (total)927.65s…
Agentic
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)188.06sResponse Time (max)188.06sResponse Time (total)188.06s
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)8.62sResponse Time (max)16.86sResponse Time (total)34.49s
Coding
: 8.4 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)26.53sResponse Time (max)31.91sResponse Time (total)79.58s
Combined
: 6.3 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)218.25sResponse Time (max)392.56sResponse Time (total)436.49s
Data parsing and extraction
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)5.68sResponse Time (max)7.94sResponse Time (total)11.36s
Domain specific
: 3.6 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)35.22sResponse Time (max)49.56sResponse Time (total)105.65s
General Intelligence
: 3.7 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)2.52sResponse Time (max)2.52sResponse Time (total)2.52s
Instructions following
: 9.8 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)6.35sResponse Time (max)9.38sResponse Time (total)12.69s
Puzzle Solving
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)3.54sResponse Time (max)6.03sResponse Time (total)10.62s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)7.72sResponse Time (max)7.72sResponse Time (total)7.72s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)38.47sResponse Time (max)38.47sResponse Time (total)38.47s
A test is fully passed only if every run passed for that test.Wrong answer: 8Did not follow instructions: 2Response Time (avg)15.95sResponse Time (max)94.06sResponse Time (total)366.93s…
Agentic
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)73.96sResponse Time (max)73.96sResponse Time (total)73.96s
Anti-AI Tricks
: 8.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)4.52sResponse Time (max)7.74sResponse Time (total)18.10s
Coding
: 6.1 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)19.12sResponse Time (max)28.80sResponse Time (total)57.37s
Combined
: 9.9 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)32.24sResponse Time (max)40.36sResponse Time (total)64.49s
Data parsing and extraction
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.54sResponse Time (max)3.33sResponse Time (total)5.08s
Domain specific
: 5.9 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)38.72sResponse Time (max)94.06sResponse Time (total)116.16s
Instructions following
: 9.8 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.88sResponse Time (max)2.61sResponse Time (total)3.75s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)7.71sResponse Time (max)7.71sResponse Time (total)7.71s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)4.81sResponse Time (max)4.81sResponse Time (total)4.81s
A test is fully passed only if every run passed for that test.Wrong answer: 2Invalid tool call: 1Timed out: 1Response Time (avg)16.64sResponse Time (max)108.60sResponse Time (total)382.64s…
Agentic
: 2.8 A test is fully passed only if every run passed for that test.Timed out: 1Response Time (avg)63.72sResponse Time (max)63.72sResponse Time (total)63.72s
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.66sResponse Time (max)3.54sResponse Time (total)10.63s
Coding
: 8.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)11.69sResponse Time (max)17.73sResponse Time (total)35.06s
Combined
: 8.7 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)60.28sResponse Time (max)108.60sResponse Time (total)120.55s
Data parsing and extraction
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)5.74sResponse Time (max)6.78sResponse Time (total)11.49s
Domain specific
: 8.2 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)31.77sResponse Time (max)47.10sResponse Time (total)95.31s
General Intelligence
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)3.65sResponse Time (max)3.65sResponse Time (total)3.65s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.81sResponse Time (max)5.24sResponse Time (total)9.62s
Puzzle Solving
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.73sResponse Time (max)3.39sResponse Time (total)8.19s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)18.47sResponse Time (max)18.47sResponse Time (total)18.47s
Trivia
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)5.94sResponse Time (max)5.94sResponse Time (total)5.94s
Agentic
: 6.1 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)137.50sResponse Time (max)137.50sResponse Time (total)137.50s
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.03sResponse Time (max)2.72sResponse Time (total)8.13s
Coding
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)29.46sResponse Time (max)49.90sResponse Time (total)88.39s
Combined
: 6.9 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)98.91sResponse Time (max)166.72sResponse Time (total)197.82s
Data parsing and extraction
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)6.20sResponse Time (max)6.23sResponse Time (total)12.40s
Domain specific
: 4.1 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)23.34sResponse Time (max)42.75sResponse Time (total)70.03s
General Intelligence
: 4.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)5.00sResponse Time (max)5.00sResponse Time (total)5.00s
Instructions following
: 9.8 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.32sResponse Time (max)3.23sResponse Time (total)4.64s
Puzzle Solving
: 8.7 A test is fully passed only if every run passed for that test.Did not follow instructions: 1Response Time (avg)1.72sResponse Time (max)2.26sResponse Time (total)5.15s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)5.85sResponse Time (max)5.85sResponse Time (total)5.85s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)9.26sResponse Time (max)9.26sResponse Time (total)9.26s
A test is fully passed only if every run passed for that test.Wrong answer: 8Invalid tool call: 1Response Time (avg)7.58sResponse Time (max)54.57sResponse Time (total)174.39s…
Agentic
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)54.57sResponse Time (max)54.57sResponse Time (total)54.57s
Anti-AI Tricks
: 8.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)2.36sResponse Time (max)3.09sResponse Time (total)9.46s
Coding
: 6.6 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)9.56sResponse Time (max)19.85sResponse Time (total)28.67s
Combined
: 8.7 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)9.68sResponse Time (max)14.29sResponse Time (total)19.36s
Data parsing and extraction
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)919msResponse Time (max)931msResponse Time (total)1.84s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)9.34sResponse Time (max)11.03sResponse Time (total)28.02s
General Intelligence
: 4.8 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)3.52sResponse Time (max)3.52sResponse Time (total)3.52s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.48sResponse Time (max)1.80sResponse Time (total)2.96s
Puzzle Solving
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.46sResponse Time (max)8.85sResponse Time (total)13.37s
Tool Calling
: 4.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)6.69sResponse Time (max)6.69sResponse Time (total)6.69s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)5.95sResponse Time (max)5.95sResponse Time (total)5.95s
Agentic
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)146.48sResponse Time (max)146.48sResponse Time (total)146.48s
Anti-AI Tricks
: 8.7 A test is fully passed only if every run passed for that test.Extra formatting: 1Response Time (avg)19.75sResponse Time (max)49.95sResponse Time (total)79.01s
Coding
: 6.2 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)160.69sResponse Time (max)234.36sResponse Time (total)482.07s
Combined
: 7.3 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)595.19sResponse Time (max)1026.43sResponse Time (total)1190.39s
Data parsing and extraction
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)30.26sResponse Time (max)32.03sResponse Time (total)60.52s
Domain specific
: 5.9 A test is fully passed only if every run passed for that test.Timed out: 1Wrong answer: 1Response Time (avg)89.39sResponse Time (max)95.52sResponse Time (total)268.18s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)19.66sResponse Time (max)32.25sResponse Time (total)39.32s
Puzzle Solving
: 8.2 A test is fully passed only if every run passed for that test.Did not follow instructions: 1Response Time (avg)59.60sResponse Time (max)123.57sResponse Time (total)178.80s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)7.45sResponse Time (max)7.45sResponse Time (total)7.45s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)85.11sResponse Time (max)85.11sResponse Time (total)85.11s
Agentic
: 6.1 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)104.77sResponse Time (max)104.77sResponse Time (total)104.77s
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.65sResponse Time (max)4.90sResponse Time (total)10.60s
Coding
: 8.2 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)24.61sResponse Time (max)30.05sResponse Time (total)73.83s
Combined
: 8.2 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)45.23sResponse Time (max)71.40sResponse Time (total)90.46s
Data parsing and extraction
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)3.38sResponse Time (max)3.44sResponse Time (total)6.75s
General Intelligence
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)5.01sResponse Time (max)5.01sResponse Time (total)5.01s
Instructions following
: 9.9 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.23sResponse Time (max)2.24sResponse Time (total)4.45s
Puzzle Solving
: 8.2 A test is fully passed only if every run passed for that test.Did not follow instructions: 1Response Time (avg)3.88sResponse Time (max)6.30sResponse Time (total)11.63s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)9.39sResponse Time (max)9.39sResponse Time (total)9.39s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.No answer: 1Response Time (avg)22.41sResponse Time (max)22.41sResponse Time (total)22.41s
A test is fully passed only if every run passed for that test.Wrong answer: 3API error: 1Response Time (avg)13.30sResponse Time (max)40.17sResponse Time (total)305.83s…
Agentic
: 3.0 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)6.93sResponse Time (max)6.93sResponse Time (total)6.93s
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)5.90sResponse Time (max)6.70sResponse Time (total)23.59s
Coding
: 8.4 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)13.91sResponse Time (max)19.46sResponse Time (total)41.74s
Combined
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)34.59sResponse Time (max)40.17sResponse Time (total)69.18s
Data parsing and extraction
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)6.30sResponse Time (max)7.96sResponse Time (total)12.59s
Domain specific
: 7.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)24.34sResponse Time (max)29.92sResponse Time (total)73.01s
General Intelligence
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)5.40sResponse Time (max)5.40sResponse Time (total)5.40s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)5.60sResponse Time (max)5.76sResponse Time (total)11.20s
Puzzle Solving
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)6.11sResponse Time (max)6.93sResponse Time (total)18.32s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)13.30sResponse Time (max)13.30sResponse Time (total)13.30s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)30.58sResponse Time (max)30.58sResponse Time (total)30.58s
Agentic
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)100.66sResponse Time (max)100.66sResponse Time (total)100.66s
Anti-AI Tricks
: 8.6 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)4.05sResponse Time (max)6.69sResponse Time (total)16.20s
Coding
: 8.4 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)57.87sResponse Time (max)138.75sResponse Time (total)173.61s
Combined
: 6.9 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)59.64sResponse Time (max)101.47sResponse Time (total)119.27s
Data parsing and extraction
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.43sResponse Time (max)3.39sResponse Time (total)4.87s
Domain specific
: 3.6 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)71.05sResponse Time (max)102.91sResponse Time (total)213.16s
Instructions following
: 9.8 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.13sResponse Time (max)2.45sResponse Time (total)4.25s
Puzzle Solving
: 7.8 A test is fully passed only if every run passed for that test.Did not follow instructions: 1Response Time (avg)4.37sResponse Time (max)7.27sResponse Time (total)13.11s
Tool Calling
: 4.7 A test is fully passed only if every run passed for that test.Did not follow instructions: 1Response Time (avg)9.62sResponse Time (max)9.62sResponse Time (total)9.62s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)30.10sResponse Time (max)30.10sResponse Time (total)30.10s
A test is fully passed only if every run passed for that test.Wrong answer: 7Response Time (avg)7.85sResponse Time (max)80.34sResponse Time (total)180.65s…
Agentic
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)80.34sResponse Time (max)80.34sResponse Time (total)80.34s
Anti-AI Tricks
: 6.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)1.08sResponse Time (max)1.39sResponse Time (total)4.30s
Coding
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)1.35sResponse Time (max)1.63sResponse Time (total)4.04s
Combined
: 6.5 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)37.23sResponse Time (max)72.30sResponse Time (total)74.47s
Data parsing and extraction
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.35sResponse Time (max)1.43sResponse Time (total)2.69s
Domain specific
: 7.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.24sResponse Time (max)1.87sResponse Time (total)3.71s
General Intelligence
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.04sResponse Time (max)1.04sResponse Time (total)1.04s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)943msResponse Time (max)974msResponse Time (total)1.89s
Puzzle Solving
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.13sResponse Time (max)1.29sResponse Time (total)3.40s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)3.92sResponse Time (max)3.92sResponse Time (total)3.92s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)856msResponse Time (max)856msResponse Time (total)856ms
Agentic
: 2.8 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)84.47sResponse Time (max)84.47sResponse Time (total)84.47s
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.09sResponse Time (max)2.56sResponse Time (total)8.35s
Coding
: 7.9 A test is fully passed only if every run passed for that test.Did not follow instructions: 1Response Time (avg)12.63sResponse Time (max)18.07sResponse Time (total)37.89s
Combined
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)44.36sResponse Time (max)76.68sResponse Time (total)88.72s
Data parsing and extraction
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.07sResponse Time (max)5.60sResponse Time (total)8.14s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)7.28sResponse Time (max)10.39sResponse Time (total)21.83s
General Intelligence
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.52sResponse Time (max)2.52sResponse Time (total)2.52s
Instructions following
: 9.9 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.70sResponse Time (max)3.07sResponse Time (total)5.40s
Puzzle Solving
: 7.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)2.38sResponse Time (max)2.55sResponse Time (total)7.15s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)3.81sResponse Time (max)3.81sResponse Time (total)3.81s
Trivia
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.75sResponse Time (max)2.75sResponse Time (total)2.75s
Agentic
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)127.11sResponse Time (max)127.11sResponse Time (total)127.11s
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)24.22sResponse Time (max)63.59sResponse Time (total)96.87s
Coding
: 5.9 A test is fully passed only if every run passed for that test.Did not follow instructions: 1No answer: 1Response Time (avg)160.52sResponse Time (max)311.89sResponse Time (total)481.57s
Combined
: 6.9 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)266.12sResponse Time (max)328.22sResponse Time (total)532.25s
Data parsing and extraction
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)13.67sResponse Time (max)19.13sResponse Time (total)27.34s
Domain specific
: 4.1 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)301.08sResponse Time (max)532.28sResponse Time (total)903.25s
Instructions following
: 9.8 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)11.45sResponse Time (max)15.77sResponse Time (total)22.90s
Puzzle Solving
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)65.54sResponse Time (max)156.63sResponse Time (total)196.61s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)32.93sResponse Time (max)32.93sResponse Time (total)32.93s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)347.95sResponse Time (max)347.95sResponse Time (total)347.95s
Global benchmark trends
See how current models trade score for cost, speed, output length, and category strength.