Agentic
: 7.4 A test is fully passed only if every run passed for that test.Did not follow instructions: 1Response Time (avg)126.80sResponse Time (max)126.80sResponse Time (total)126.80s
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)21.13sResponse Time (max)34.96sResponse Time (total)84.53s
Coding
: 5.9 A test is fully passed only if every run passed for that test.No answer: 1Wrong answer: 1Response Time (avg)206.65sResponse Time (max)409.98sResponse Time (total)619.94s
Combined
: 3.8 A test is fully passed only if every run passed for that test.Invalid tool call: 1No answer: 1Response Time (avg)512.79sResponse Time (max)950.25sResponse Time (total)1025.59s
Data parsing and extraction
: 7.3 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)59.33sResponse Time (max)97.12sResponse Time (total)118.65s
General Intelligence
: 2.8 A test is fully passed only if every run passed for that test.Timed out: 1Response Time (avg)30.30sResponse Time (max)30.30sResponse Time (total)30.30s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)24.45sResponse Time (max)43.36sResponse Time (total)48.89s
Puzzle Solving
: 8.2 A test is fully passed only if every run passed for that test.Timed out: 1Response Time (avg)33.13sResponse Time (max)64.81sResponse Time (total)99.38s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.65sResponse Time (max)4.65sResponse Time (total)4.65s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)177.35sResponse Time (max)177.35sResponse Time (total)177.35s
Agentic
: 6.1 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)81.77sResponse Time (max)81.77sResponse Time (total)81.77s
Anti-AI Tricks
: 4.8 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)2.87sResponse Time (max)5.35sResponse Time (total)11.47s
Coding
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)2.85sResponse Time (max)4.99sResponse Time (total)8.54s
Combined
: 6.5 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)28.45sResponse Time (max)48.38sResponse Time (total)56.89s
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)2.56sResponse 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)1.68sResponse Time (max)1.79sResponse Time (total)5.04s
General Intelligence
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)2.76sResponse Time (max)2.76sResponse Time (total)2.76s
Instructions following
: 6.5 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)2.82sResponse Time (max)3.85sResponse Time (total)5.64s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)6.64sResponse Time (max)6.64sResponse Time (total)6.64s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)3.92sResponse Time (max)3.92sResponse Time (total)3.92s
Agentic
: 6.1 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)129.13sResponse Time (max)129.13sResponse Time (total)129.13s
Anti-AI Tricks
: 8.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)6.97sResponse Time (max)13.43sResponse Time (total)27.87s
Coding
: 5.8 A test is fully passed only if every run passed for that test.No answer: 2Response Time (avg)306.23sResponse Time (max)480.52sResponse Time (total)918.70s
Combined
: 6.9 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)107.07sResponse Time (max)130.01sResponse Time (total)214.14s
Data parsing and extraction
: 7.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)12.67sResponse Time (max)16.38sResponse Time (total)25.35s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)69.36sResponse Time (max)127.05sResponse Time (total)208.09s
General Intelligence
: 3.4 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)19.56sResponse Time (max)19.56sResponse Time (total)19.56s
Puzzle Solving
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)12.75sResponse Time (max)17.95sResponse Time (total)38.24s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)6.96sResponse Time (max)6.96sResponse Time (total)6.96s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)17.29sResponse Time (max)17.29sResponse Time (total)17.29s
Agentic
: 6.1 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)161.24sResponse Time (max)161.24sResponse Time (total)161.24s
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)17.51sResponse Time (max)50.06sResponse Time (total)70.05s
Coding
: 5.9 A test is fully passed only if every run passed for that test.No answer: 2Response Time (avg)287.61sResponse Time (max)417.36sResponse Time (total)862.83s
Combined
: 6.9 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)85.20sResponse Time (max)131.55sResponse Time (total)170.40s
Data parsing and extraction
: 7.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)11.49sResponse Time (max)12.88sResponse Time (total)22.98s
Domain specific
: 3.6 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)49.50sResponse Time (max)79.61sResponse Time (total)148.51s
General Intelligence
: 4.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)27.55sResponse Time (max)27.55sResponse Time (total)27.55s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)7.36sResponse Time (max)7.36sResponse Time (total)7.36s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)8.80sResponse Time (max)8.80sResponse Time (total)8.80s
Agentic
: 4.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)233.51sResponse Time (max)233.51sResponse Time (total)233.51s
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)3.26sResponse Time (max)6.38sResponse Time (total)13.06s
Coding
: 6.2 A test is fully passed only if every run passed for that test.API error: 1Extra formatting: 1Response Time (avg)92.07sResponse Time (max)130.77sResponse Time (total)276.20s
Combined
: 6.9 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)125.45sResponse Time (max)197.54sResponse Time (total)250.89s
Data parsing and extraction
: 7.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)18.81sResponse Time (max)20.29sResponse Time (total)37.61s
Domain specific
: 2.9 A test is fully passed only if every run passed for that test.Extra formatting: 2No answer: 1Response Time (avg)146.15sResponse Time (max)333.34sResponse Time (total)438.44s
Instructions following
: 9.9 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.77sResponse Time (max)3.21sResponse Time (total)5.54s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)16.87sResponse Time (max)16.87sResponse Time (total)16.87s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)12.46sResponse Time (max)12.46sResponse Time (total)12.46s
A test is fully passed only if every run passed for that test.Wrong answer: 9API error: 1Timed out: 1Response Time (avg)7.74sResponse Time (max)107.89sResponse Time (total)178.07s…
Agentic
: 4.7 A test is fully passed only if every run passed for that test.Timed out: 1Response Time (avg)107.89sResponse Time (max)107.89sResponse Time (total)107.89s
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.28sResponse Time (max)2.09sResponse Time (total)5.12s
Coding
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)3.70sResponse Time (max)4.41sResponse Time (total)11.11s
Combined
: 6.5 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)9.23sResponse Time (max)9.87sResponse Time (total)18.46s
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)2.57sResponse Time (max)3.13sResponse Time (total)5.14s
Domain specific
: 3.6 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)4.39sResponse Time (max)4.72sResponse Time (total)13.17s
General Intelligence
: 4.4 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.60sResponse Time (max)1.60sResponse Time (total)1.60s
Instructions following
: 6.4 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)1.07sResponse Time (max)1.36sResponse Time (total)2.13s
Puzzle Solving
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.93sResponse Time (max)3.14sResponse Time (total)5.79s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)3.35sResponse Time (max)3.35sResponse Time (total)3.35s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)4.30sResponse Time (max)4.30sResponse Time (total)4.30s
Agentic
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)49.23sResponse Time (max)49.23sResponse Time (total)49.23s
Anti-AI Tricks
: 6.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)892msResponse Time (max)1.38sResponse Time (total)3.57s
Combined
: 3.0 A test is fully passed only if every run passed for that test.Invalid tool call: 2Response Time (avg)14.41sResponse Time (max)25.26sResponse Time (total)28.81s
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)1.66sResponse Time (max)2.11sResponse Time (total)3.32s
Domain specific
: 7.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)879msResponse Time (max)985msResponse Time (total)2.64s
General Intelligence
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)922msResponse Time (max)922msResponse Time (total)922ms
Instructions following
: 6.4 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)893msResponse Time (max)964msResponse Time (total)1.79s
Puzzle Solving
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.45sResponse Time (max)2.30sResponse Time (total)4.36s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.79sResponse Time (max)2.79sResponse Time (total)2.79s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.76sResponse Time (max)1.76sResponse Time (total)1.76s
Agentic
: 3.0 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)29.49sResponse Time (max)29.49sResponse Time (total)29.49s
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.61sResponse Time (max)3.91sResponse Time (total)6.43s
Coding
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)7.29sResponse Time (max)8.86sResponse Time (total)21.87s
Combined
: 3.0 A test is fully passed only if every run passed for that test.API error: 2Response Time (avg)2.22sResponse Time (max)2.78sResponse Time (total)4.44s
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)1.19sResponse Time (max)1.31sResponse Time (total)2.38s
Domain specific
: 2.9 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)8.45sResponse Time (max)11.63sResponse Time (total)25.36s
Puzzle Solving
: 6.1 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)3.42sResponse Time (max)4.30sResponse Time (total)10.26s
Tool Calling
: 3.0 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)1.83sResponse Time (max)1.83sResponse Time (total)1.83s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)5.93sResponse Time (max)5.93sResponse Time (total)5.93s
Agentic
: 3.9 A test is fully passed only if every run passed for that test.Timed out: 1Response Time (avg)566.79sResponse Time (max)566.79sResponse Time (total)566.79s
Anti-AI Tricks
: 7.3 A test is fully passed only if every run passed for that test.No answer: 1Wrong answer: 1Response Time (avg)51.38sResponse Time (max)85.28sResponse Time (total)102.75s
Coding
: 6.1 A test is fully passed only if every run passed for that test.No answer: 1Timed out: 1Response Time (avg)217.49sResponse Time (max)281.00sResponse Time (total)652.48s
Combined
: 6.7 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)89.19sResponse Time (max)107.01sResponse Time (total)178.38s
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)49.78sResponse Time (max)49.78sResponse Time (total)49.78s
Domain specific
: 2.9 A test is fully passed only if every run passed for that test.Wrong answer: 2Timed out: 1Response Time (avg)111.65sResponse Time (max)137.29sResponse Time (total)223.30s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)92.47sResponse Time (max)92.47sResponse Time (total)92.47s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)31.74sResponse Time (max)31.74sResponse Time (total)31.74s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)83.95sResponse Time (max)83.95sResponse Time (total)83.95s
Agentic
: 6.1 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)87.61sResponse Time (max)87.61sResponse Time (total)87.61s
Anti-AI Tricks
: 6.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)2.91sResponse Time (max)7.21sResponse Time (total)11.66s
Combined
: 7.3 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)34.36sResponse Time (max)61.86sResponse Time (total)68.72s
Data parsing and extraction
: 6.5 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)949msResponse Time (max)1.56sResponse Time (total)1.90s
Domain specific
: 7.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)50.99sResponse Time (max)76.87sResponse Time (total)152.96s
General Intelligence
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)6.26sResponse Time (max)6.26sResponse Time (total)6.26s
Puzzle Solving
: 7.8 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)10.22sResponse Time (max)26.01sResponse Time (total)30.66s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.78sResponse Time (max)2.78sResponse Time (total)2.78s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)72.27sResponse Time (max)72.27sResponse Time (total)72.27s
A test is fully passed only if every run passed for that test.Wrong answer: 4Extra formatting: 3Timed out: 1Response Time (avg)28.08sResponse Time (max)140.96sResponse Time (total)421.15s…
Agentic
: 0.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)0msResponse Time (max)0msResponse Time (total)0ms
Coding
: 5.7 A test is fully passed only if every run passed for that test.Extra formatting: 1Wrong answer: 1Response Time (avg)33.29sResponse Time (max)35.76sResponse Time (total)99.86s
Combined
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)93.65sResponse Time (max)140.96sResponse Time (total)187.31s
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)13.90sResponse Time (max)13.90sResponse Time (total)13.90s
General Intelligence
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.94sResponse Time (max)4.94sResponse Time (total)4.94s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.61sResponse Time (max)2.61sResponse Time (total)2.61s
Puzzle Solving
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)5.31sResponse Time (max)6.24sResponse 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)7.48sResponse Time (max)7.48sResponse Time (total)7.48s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)30.09sResponse Time (max)30.09sResponse Time (total)30.09s
Agentic
: 4.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)272.28sResponse Time (max)272.28sResponse Time (total)272.28s
Anti-AI Tricks
: 8.2 A test is fully passed only if every run passed for that test.No answer: 1Response Time (avg)53.37sResponse Time (max)74.40sResponse Time (total)213.47s
Coding
: 5.5 A test is fully passed only if every run passed for that test.Extra formatting: 1Wrong answer: 1Response Time (avg)310.39sResponse Time (max)518.33sResponse Time (total)931.17s
Combined
: 6.4 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)294.82sResponse Time (max)519.91sResponse Time (total)589.65s
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)43.08sResponse Time (max)47.23sResponse Time (total)86.16s
Domain specific
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)201.85sResponse Time (max)333.26sResponse Time (total)605.54s
Instructions following
: 9.8 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)40.08sResponse Time (max)56.63sResponse Time (total)80.15s
Puzzle Solving
: 9.0 A test is fully passed only if every run passed for that test.Did not follow instructions: 1Response Time (avg)45.83sResponse Time (max)74.11sResponse Time (total)137.48s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)7.86sResponse Time (max)7.86sResponse Time (total)7.86s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)108.62sResponse Time (max)108.62sResponse Time (total)108.62s
A test is fully passed only if every run passed for that test.Wrong answer: 9No answer: 1Response Time (avg)6.05sResponse Time (max)57.84sResponse Time (total)102.89s…
Agentic
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)57.84sResponse Time (max)57.84sResponse Time (total)57.84s
Anti-AI Tricks
: 8.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.25sResponse Time (max)1.59sResponse Time (total)2.49s
Coding
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)1.80sResponse Time (max)2.79sResponse Time (total)5.40s
Combined
: 3.8 A test is fully passed only if every run passed for that test.No answer: 1Wrong answer: 1Response Time (avg)12.38sResponse Time (max)21.19sResponse Time (total)24.75s
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)1.41sResponse Time (max)1.41sResponse Time (total)1.41s
Domain specific
: 7.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)879msResponse Time (max)963msResponse Time (total)1.76s
General Intelligence
: 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)1.13sResponse Time (total)1.13s
Instructions following
: 6.4 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.58sResponse Time (max)1.58sResponse Time (total)1.58s
Puzzle Solving
: 7.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.05sResponse Time (max)1.06sResponse Time (total)2.11s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)3.35sResponse Time (max)3.35sResponse Time (total)3.35s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.07sResponse Time (max)1.07sResponse Time (total)1.07s
Agentic
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)50.05sResponse Time (max)50.05sResponse Time (total)50.05s
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.42sResponse Time (max)2.72sResponse Time (total)5.66s
Coding
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)17.15sResponse Time (max)24.93sResponse Time (total)51.46s
Combined
: 3.0 A test is fully passed only if every run passed for that test.API error: 2Response Time (avg)3.04sResponse Time (max)4.53sResponse Time (total)6.08s
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)1.23sResponse Time (max)1.43sResponse Time (total)2.46s
Domain specific
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)31.89sResponse Time (max)54.48sResponse Time (total)95.68s
General Intelligence
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)3.63sResponse Time (max)3.63sResponse Time (total)3.63s
Puzzle Solving
: 7.8 A test is fully passed only if every run passed for that test.Did not follow instructions: 1Response Time (avg)3.94sResponse Time (max)5.76sResponse Time (total)11.82s
Tool Calling
: 3.0 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)2.15sResponse Time (max)2.15sResponse Time (total)2.15s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)24.53sResponse Time (max)24.53sResponse Time (total)24.53s
Agentic
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)55.86sResponse Time (max)55.86sResponse Time (total)55.86s
Anti-AI Tricks
: 4.8 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)1.59sResponse Time (max)3.60sResponse Time (total)6.38s
Coding
: 3.7 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)2.77sResponse Time (max)4.03sResponse Time (total)8.32s
Combined
: 5.2 A test is fully passed only if every run passed for that test.Invalid tool call: 1Wrong answer: 1Response Time (avg)129.31sResponse Time (max)212.63sResponse Time (total)258.63s
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)1.01sResponse Time (max)1.06sResponse Time (total)2.02s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)523msResponse Time (max)609msResponse Time (total)1.57s
Instructions following
: 6.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)513msResponse Time (max)570msResponse Time (total)1.03s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.04sResponse Time (max)2.04sResponse Time (total)2.04s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)295msResponse Time (max)295msResponse Time (total)295ms
Agentic
: 6.1 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)66.42sResponse Time (max)66.42sResponse Time (total)66.42s
Anti-AI Tricks
: 4.8 A test is fully passed only if every run passed for that test.Wrong answer: 2No answer: 1Response Time (avg)41.96sResponse Time (max)155.23sResponse Time (total)167.84s
Coding
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)70.35sResponse Time (max)105.98sResponse Time (total)211.04s
Combined
: 6.3 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)218.07sResponse Time (max)422.72sResponse Time (total)436.15s
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)4.50sResponse Time (max)5.55sResponse Time (total)9.00s
Domain specific
: 3.5 A test is fully passed only if every run passed for that test.Wrong answer: 2No answer: 1Response Time (avg)67.48sResponse Time (max)121.62sResponse Time (total)202.43s
General Intelligence
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)4.15sResponse Time (max)4.15sResponse Time (total)4.15s
Instructions following
: 9.8 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.57sResponse Time (max)2.61sResponse Time (total)5.15s
Puzzle Solving
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)3.43sResponse Time (max)4.37sResponse Time (total)10.29s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)3.01sResponse Time (max)3.01sResponse Time (total)3.01s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)10.88sResponse Time (max)10.88sResponse Time (total)10.88s
Agentic
: 3.9 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)51.61sResponse Time (max)51.61sResponse Time (total)51.61s
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)8.83sResponse Time (max)11.20sResponse Time (total)35.31s
Coding
: 5.9 A test is fully passed only if every run passed for that test.Extra formatting: 1Wrong answer: 1Response Time (avg)41.23sResponse Time (max)64.81sResponse Time (total)123.69s
Combined
: 6.5 A test is fully passed only if every run passed for that test.No answer: 1Response Time (avg)55.07sResponse Time (max)63.99sResponse Time (total)110.13s
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)18.97sResponse Time (max)26.99sResponse Time (total)37.93s
Domain specific
: 3.5 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)158.01sResponse Time (max)216.69sResponse Time (total)474.02s
Instructions following
: 9.8 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)18.58sResponse Time (max)31.48sResponse Time (total)37.15s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)17.66sResponse Time (max)17.66sResponse Time (total)17.66s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)44.47sResponse Time (max)44.47sResponse Time (total)44.47s
Agentic
: 3.0 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)1.52sResponse Time (max)1.52sResponse Time (total)1.52s
Anti-AI Tricks
: 7.0 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)3.17sResponse Time (max)4.99sResponse Time (total)12.67s
Coding
: 6.4 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)22.00sResponse Time (max)35.74sResponse Time (total)65.99s
Combined
: 7.3 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)106.70sResponse Time (max)199.97sResponse Time (total)213.41s
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)4.13sResponse Time (max)4.56sResponse Time (total)8.26s
Domain specific
: 2.9 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)44.66sResponse Time (max)95.65sResponse Time (total)133.99s
General Intelligence
: 5.1 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)3.27sResponse Time (max)3.27sResponse Time (total)3.27s
Instructions following
: 9.9 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.67sResponse Time (max)2.87sResponse Time (total)5.33s
Puzzle Solving
: 8.2 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)3.38sResponse Time (max)4.30sResponse Time (total)10.13s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)28.04sResponse Time (max)28.04sResponse Time (total)28.04s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)5.22sResponse Time (max)5.22sResponse Time (total)5.22s
Agentic
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)107.19sResponse Time (max)107.19sResponse Time (total)107.19s
Anti-AI Tricks
: 4.0 A test is fully passed only if every run passed for that test.Wrong answer: 4Response Time (avg)2.11sResponse Time (max)3.94sResponse Time (total)8.46s
Coding
: 3.9 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)4.96sResponse Time (max)9.79sResponse Time (total)14.89s
Combined
: 2.8 A test is fully passed only if every run passed for that test.Invalid tool call: 1No answer: 1Response Time (avg)46.88sResponse Time (max)61.20sResponse Time (total)93.77s
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)1.08sResponse Time (max)1.62sResponse Time (total)2.15s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)2.27sResponse Time (max)3.99sResponse Time (total)6.80s
General Intelligence
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)790msResponse Time (max)790msResponse Time (total)790ms
Instructions following
: 9.8 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.98sResponse Time (max)2.28sResponse Time (total)3.97s
Puzzle Solving
: 7.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.45sResponse Time (max)2.09sResponse Time (total)4.36s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)10.68sResponse Time (max)10.68sResponse Time (total)10.68s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)2.34sResponse Time (max)2.34sResponse Time (total)2.34s
Agentic
: 5.2 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)48.84sResponse Time (max)48.84sResponse Time (total)48.84s
Anti-AI Tricks
: 6.9 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)4.16sResponse Time (max)6.41sResponse Time (total)16.65s
Coding
: 6.2 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)21.02sResponse Time (max)44.29sResponse Time (total)63.06s
Combined
: 3.8 A test is fully passed only if every run passed for that test.Invalid tool call: 1Wrong answer: 1Response Time (avg)53.02sResponse Time (max)83.60sResponse Time (total)106.04s
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)3.42sResponse Time (max)4.01sResponse Time (total)6.84s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)19.23sResponse Time (max)30.42sResponse Time (total)57.69s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)3.40sResponse Time (max)3.57sResponse Time (total)6.79s
Puzzle Solving
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.20sResponse Time (max)4.53sResponse Time (total)12.59s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)18.45sResponse Time (max)18.45sResponse Time (total)18.45s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)7.42sResponse Time (max)7.42sResponse Time (total)7.42s
A test is fully passed only if every run passed for that test.Wrong answer: 8API error: 3Response Time (avg)9.18sResponse Time (max)44.64sResponse Time (total)211.12s…
Agentic
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)44.64sResponse Time (max)44.64sResponse Time (total)44.64s
Anti-AI Tricks
: 9.2 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.52sResponse Time (max)2.98sResponse Time (total)6.08s
Coding
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)20.68sResponse Time (max)33.46sResponse Time (total)62.05s
Combined
: 3.0 A test is fully passed only if every run passed for that test.API error: 2Response Time (avg)2.68sResponse Time (max)3.43sResponse Time (total)5.37s
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)1.60sResponse Time (max)1.93sResponse Time (total)3.20s
Domain specific
: 5.9 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)20.22sResponse Time (max)24.34sResponse Time (total)60.66s
General Intelligence
: 5.1 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)2.50sResponse Time (max)2.50sResponse Time (total)2.50s
Instructions following
: 9.8 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.15sResponse Time (max)1.41sResponse Time (total)2.30s
Puzzle Solving
: 5.8 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)4.46sResponse Time (max)7.42sResponse Time (total)13.38s
Tool Calling
: 3.0 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)1.84sResponse Time (max)1.84sResponse Time (total)1.84s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)9.10sResponse Time (max)9.10sResponse Time (total)9.10s
A test is fully passed only if every run passed for that test.Wrong answer: 9API error: 1No answer: 1Response Time (avg)7.62sResponse Time (max)80.30sResponse Time (total)175.36s…
Agentic
: 3.9 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)80.30sResponse Time (max)80.30sResponse Time (total)80.30s
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.33sResponse Time (max)2.12sResponse Time (total)5.33s
Coding
: 6.4 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)6.58sResponse Time (max)8.12sResponse Time (total)19.74s
Combined
: 6.4 A test is fully passed only if every run passed for that test.No answer: 1Response Time (avg)16.00sResponse Time (max)23.63sResponse Time (total)32.00s
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)3.08sResponse Time (max)4.24sResponse Time (total)6.16s
Domain specific
: 2.9 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)4.86sResponse Time (max)7.32sResponse Time (total)14.58s
General Intelligence
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)2.69sResponse Time (max)2.69sResponse Time (total)2.69s
Instructions following
: 6.5 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)934msResponse Time (max)1.13sResponse Time (total)1.87s
Puzzle Solving
: 8.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.39sResponse Time (max)1.86sResponse Time (total)4.17s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)3.06sResponse Time (max)3.06sResponse Time (total)3.06s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)5.48sResponse Time (max)5.48sResponse Time (total)5.48s
Agentic
: 6.1 A test is fully passed only if every run passed for that test.Timed out: 1Response Time (avg)86.84sResponse Time (max)86.84sResponse Time (total)86.84s
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.09sResponse Time (max)1.54sResponse Time (total)4.35s
Combined
: 3.8 A test is fully passed only if every run passed for that test.Invalid tool call: 1Wrong answer: 1Response Time (avg)14.36sResponse Time (max)17.71sResponse Time (total)28.71s
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)2.24sResponse Time (max)2.62sResponse Time (total)4.49s
Domain specific
: 2.9 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)5.68sResponse Time (max)9.06sResponse Time (total)17.04s
Instructions following
: 9.8 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.05sResponse Time (max)1.15sResponse Time (total)2.09s
Puzzle Solving
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.21sResponse Time (max)1.54sResponse Time (total)3.64s
Tool Calling
: 3.0 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)2.25sResponse Time (max)2.25sResponse Time (total)2.25s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)5.41sResponse Time (max)5.41sResponse Time (total)5.41s
Agentic
: 6.1 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)88.48sResponse Time (max)88.48sResponse Time (total)88.48s
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)6.02sResponse Time (max)8.79sResponse Time (total)24.07s
Coding
: 7.7 A test is fully passed only if every run passed for that test.No answer: 1Response Time (avg)50.55sResponse Time (max)86.11sResponse Time (total)151.65s
Combined
: 3.0 A test is fully passed only if every run passed for that test.API error: 1Invalid tool call: 1Response Time (avg)817.57sResponse Time (max)817.57sResponse Time (total)817.57s
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)12.99sResponse Time (max)13.75sResponse Time (total)25.99s
Domain specific
: 2.9 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)25.39sResponse Time (max)45.02sResponse Time (total)76.16s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)7.50sResponse Time (max)10.22sResponse Time (total)15.00s
Puzzle Solving
: 8.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)5.95sResponse Time (max)8.42sResponse Time (total)17.84s
Tool Calling
: 3.0 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)0msResponse Time (max)0msResponse Time (total)0ms
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)32.90sResponse Time (max)32.90sResponse Time (total)32.90s
Agentic
: 6.1 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)70.45sResponse Time (max)70.45sResponse Time (total)70.45s
Anti-AI Tricks
: 6.4 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)2.71sResponse Time (max)6.72sResponse Time (total)10.82s
Combined
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)34.77sResponse Time (max)62.84sResponse Time (total)69.55s
Data parsing and extraction
: 6.5 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)1.00sResponse Time (max)1.67sResponse Time (total)2.00s
Domain specific
: 5.9 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)134.49sResponse Time (max)280.72sResponse Time (total)403.47s
General Intelligence
: 4.6 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)5.16sResponse Time (max)5.16sResponse Time (total)5.16s
Puzzle Solving
: 6.0 A test is fully passed only if every run passed for that test.Did not follow instructions: 2Response Time (avg)3.48sResponse Time (max)5.27sResponse Time (total)10.43s
Tool Calling
: 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)3.38sResponse Time (total)3.38s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)93.01sResponse Time (max)93.01sResponse Time (total)93.01s
Global benchmark trends
See how current models trade score for cost, speed, output length, and category strength.