Agentic
: 3.9 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)45.71sResponse Time (max)45.71sResponse Time (total)45.71s
Coding
: 4.6 A test is fully passed only if every run passed for that test.Wrong answer: 2Extra formatting: 1Response Time (avg)6.12sResponse Time (max)13.52sResponse Time (total)18.37s
Combined
: 3.0 A test is fully passed only if every run passed for that test.Invalid tool call: 1Wrong answer: 1Response Time (avg)14.81sResponse Time (max)24.48sResponse Time (total)29.63s
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)2.72sResponse Time (max)3.22sResponse Time (total)5.45s
Domain specific
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)1.10sResponse Time (max)1.44sResponse Time (total)3.30s
General Intelligence
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.63sResponse Time (max)1.63sResponse Time (total)1.63s
Puzzle Solving
: 3.3 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)1.50sResponse Time (max)2.39sResponse Time (total)4.49s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.04sResponse Time (max)4.04sResponse Time (total)4.04s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)961msResponse Time (max)961msResponse Time (total)961ms
Agentic
: 4.7 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)198.82sResponse Time (max)198.82sResponse Time (total)198.82s
Coding
: 5.7 A test is fully passed only if every run passed for that test.API error: 1No answer: 1Response Time (avg)101.89sResponse Time (max)196.21sResponse Time (total)305.67s
Combined
: 3.8 A test is fully passed only if every run passed for that test.Invalid tool call: 1No answer: 1Response Time (avg)72.12sResponse Time (max)103.21sResponse Time (total)144.25s
Data parsing and extraction
: 6.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)21.95sResponse Time (max)24.88sResponse Time (total)43.89s
Domain specific
: 3.0 A test is fully passed only if every run passed for that test.Timed out: 2Wrong answer: 1Response Time (avg)39.70sResponse Time (max)63.03sResponse Time (total)79.41s
Tool Calling
: 4.7 A test is fully passed only if every run passed for that test.Did not follow instructions: 1Response Time (avg)12.05sResponse Time (max)12.05sResponse Time (total)12.05s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)22.77sResponse Time (max)22.77sResponse Time (total)22.77s
Agentic
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)84.47sResponse Time (max)84.47sResponse Time (total)84.47s
Coding
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)972msResponse Time (max)1.02sResponse Time (total)2.92s
Combined
: 3.0 A test is fully passed only if every run passed for that test.No answer: 1Wrong answer: 1Response Time (avg)4.77sResponse Time (max)7.29sResponse Time (total)9.54s
Data parsing and extraction
: 6.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.12sResponse Time (max)1.54sResponse Time (total)2.24s
Domain specific
: 4.1 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)836msResponse Time (max)1.06sResponse Time (total)2.51s
Instructions following
: 6.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.60sResponse Time (max)2.42sResponse Time (total)3.20s
Puzzle Solving
: 8.2 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)710msResponse Time (max)792msResponse Time (total)2.13s
Tool Calling
: 2.8 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)1.57sResponse Time (max)1.57sResponse Time (total)1.57s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)591msResponse Time (max)591msResponse Time (total)591ms
Agentic
: 3.4 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)165.05sResponse Time (max)165.05sResponse Time (total)165.05s
Anti-AI Tricks
: 3.4 A test is fully passed only if every run passed for that test.Wrong answer: 3No answer: 1Response Time (avg)51.82sResponse Time (max)205.67sResponse Time (total)207.27s
Coding
: 5.3 A test is fully passed only if every run passed for that test.No answer: 1Wrong answer: 1Response Time (avg)158.98sResponse Time (max)441.13sResponse Time (total)476.95s
Combined
: 3.2 A test is fully passed only if every run passed for that test.Invalid tool call: 2Response Time (avg)284.71sResponse Time (max)560.31sResponse Time (total)569.43s
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)2.42sResponse Time (max)4.25sResponse Time (total)4.84s
Domain specific
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)2.68sResponse Time (max)7.28sResponse Time (total)8.03s
General Intelligence
: 4.6 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)739msResponse Time (max)739msResponse Time (total)739ms
Puzzle Solving
: 3.1 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)2.62sResponse Time (max)6.83sResponse Time (total)7.86s
Tool Calling
: 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)2.24sResponse Time (total)2.24s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)7.11sResponse Time (max)7.11sResponse Time (total)7.11s
Agentic
: 5.2 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)121.52sResponse Time (max)121.52sResponse Time (total)121.52s
Anti-AI Tricks
: 3.4 A test is fully passed only if every run passed for that test.Wrong answer: 4Response Time (avg)1.18sResponse Time (max)2.18sResponse Time (total)4.72s
Coding
: 3.8 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)1.13sResponse Time (max)1.68sResponse Time (total)3.39s
Combined
: 3.0 A test is fully passed only if every run passed for that test.Invalid tool call: 1Wrong answer: 1Response Time (avg)16.96sResponse Time (max)30.55sResponse Time (total)33.93s
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)1.13sResponse Time (max)1.31sResponse Time (total)2.27s
Domain specific
: 2.9 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)870msResponse Time (max)1.14sResponse Time (total)2.61s
General Intelligence
: 5.4 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.38sResponse Time (max)1.38sResponse Time (total)1.38s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.80sResponse Time (max)2.80sResponse Time (total)2.80s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)759msResponse Time (max)759msResponse Time (total)759ms
Agentic
: 3.9 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)49.61sResponse Time (max)49.61sResponse Time (total)49.61s
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)1.32sResponse Time (max)1.42sResponse Time (total)2.64s
Domain specific
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)1.79sResponse Time (max)3.59sResponse Time (total)5.36s
General Intelligence
: 4.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)2.58sResponse Time (max)2.58sResponse Time (total)2.58s
Instructions following
: 6.4 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.03sResponse Time (max)1.10sResponse Time (total)2.06s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)3.30sResponse Time (max)3.30sResponse Time (total)3.30s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.89sResponse Time (max)1.89sResponse Time (total)1.89s
Agentic
: 3.0 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)1.05sResponse Time (max)1.05sResponse Time (total)1.05s
Anti-AI Tricks
: 8.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)3.79sResponse Time (max)9.97sResponse Time (total)15.17s
Coding
: 3.6 A test is fully passed only if every run passed for that test.Wrong answer: 2Extra formatting: 1Response Time (avg)23.37sResponse Time (max)48.19sResponse Time (total)70.10s
Combined
: 6.5 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)19.56sResponse Time (max)27.68sResponse Time (total)39.11s
Data parsing and extraction
: 6.5 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)3.65sResponse Time (max)4.88sResponse Time (total)7.31s
Domain specific
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 2Timed out: 1Response Time (avg)6.58sResponse Time (max)7.90sResponse Time (total)19.73s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.50sResponse Time (max)1.88sResponse Time (total)3.00s
Puzzle Solving
: 3.6 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)1.87sResponse Time (max)2.41sResponse Time (total)5.61s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.77sResponse Time (max)4.77sResponse Time (total)4.77s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)15.74sResponse Time (max)15.74sResponse Time (total)15.74s
Agentic
: 5.0 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)47.06sResponse Time (max)47.06sResponse Time (total)47.06s
Anti-AI Tricks
: 6.9 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)799msResponse Time (max)1.05sResponse Time (total)3.20s
Coding
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)972msResponse Time (max)1.03sResponse Time (total)2.92s
Combined
: 3.0 A test is fully passed only if every run passed for that test.No answer: 1Wrong answer: 1Response Time (avg)5.16sResponse Time (max)7.48sResponse Time (total)10.32s
Data parsing and extraction
: 6.5 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.06sResponse Time (max)1.10sResponse Time (total)2.13s
Domain specific
: 3.6 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)846msResponse Time (max)1.03sResponse Time (total)2.54s
General Intelligence
: 4.4 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)819msResponse Time (max)819msResponse Time (total)819ms
Puzzle Solving
: 5.9 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)792msResponse Time (max)829msResponse Time (total)2.38s
Tool Calling
: 9.8 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.72sResponse Time (max)2.72sResponse Time (total)2.72s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)782msResponse Time (max)782msResponse Time (total)782ms
A test is fully passed only if every run passed for that test.Wrong answer: 17Did not follow instructions: 1Response Time (avg)3.12sResponse Time (max)45.46sResponse Time (total)71.87s…
Agentic
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)45.46sResponse Time (max)45.46sResponse Time (total)45.46s
Anti-AI Tricks
: 3.4 A test is fully passed only if every run passed for that test.Wrong answer: 4Response Time (avg)395msResponse Time (max)769msResponse Time (total)1.58s
Coding
: 3.7 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)901msResponse Time (max)1.28sResponse Time (total)2.70s
Combined
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)7.44sResponse Time (max)13.16sResponse Time (total)14.88s
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)822msResponse Time (max)1.08sResponse Time (total)1.64s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)377msResponse Time (max)418msResponse Time (total)1.13s
General Intelligence
: 4.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)729msResponse Time (max)729msResponse Time (total)729ms
Instructions following
: 6.5 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)380msResponse Time (max)380msResponse Time (total)759ms
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.40sResponse Time (max)1.40sResponse Time (total)1.40s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)397msResponse Time (max)397msResponse Time (total)397ms
Agentic
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)54.05sResponse Time (max)54.05sResponse Time (total)54.05s
Anti-AI Tricks
: 5.6 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)2.67sResponse Time (max)5.03sResponse Time (total)10.66s
Coding
: 4.4 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)39.98sResponse Time (max)59.15sResponse Time (total)119.95s
Combined
: 3.0 A test is fully passed only if every run passed for that test.No answer: 1Wrong answer: 1Response Time (avg)32.40sResponse Time (max)39.55sResponse Time (total)64.80s
Data parsing and extraction
: 7.3 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)1.23sResponse Time (max)1.96sResponse Time (total)2.46s
Domain specific
: 5.9 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)6.33sResponse Time (max)13.72sResponse Time (total)19.00s
Instructions following
: 7.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.38sResponse Time (max)1.61sResponse Time (total)2.75s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)3.50sResponse Time (max)3.50sResponse Time (total)3.50s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)5.92sResponse Time (max)5.92sResponse Time (total)5.92s
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
Anti-AI Tricks
: 8.1 A test is fully passed only if every run passed for that test.Extra formatting: 1Response Time (avg)15.85sResponse Time (max)20.83sResponse Time (total)47.55s
Coding
: 6.0 A test is fully passed only if every run passed for that test.Timed out: 1Wrong answer: 1Response Time (avg)10.71sResponse Time (max)17.72sResponse Time (total)32.13s
Combined
: 4.9 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)75.68sResponse Time (max)75.68sResponse Time (total)75.68s
Data parsing and extraction
: 6.5 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
Domain specific
: 5.9 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)96.01sResponse Time (max)96.01sResponse Time (total)96.01s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.28sResponse Time (max)7.37sResponse Time (total)8.55s
Puzzle Solving
: 7.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)3.87sResponse Time (max)5.26sResponse Time (total)7.74s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)27.78sResponse Time (max)27.78sResponse Time (total)27.78s
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
A test is fully passed only if every run passed for that test.Wrong answer: 9API error: 4Extra formatting: 3Response Time (avg)15.23sResponse Time (max)118.35sResponse Time (total)350.26s…
Agentic
: 3.0 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)1.10sResponse Time (max)1.10sResponse Time (total)1.10s
Anti-AI Tricks
: 6.9 A test is fully passed only if every run passed for that test.API error: 1Wrong answer: 1Response Time (avg)2.49sResponse Time (max)3.97sResponse Time (total)9.97s
Combined
: 6.5 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)74.48sResponse Time (max)118.35sResponse Time (total)148.95s
Data parsing and extraction
: 6.5 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)3.59sResponse Time (max)4.92sResponse Time (total)7.18s
General Intelligence
: 5.1 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)7.10sResponse Time (max)7.10sResponse Time (total)7.10s
Instructions following
: 9.8 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.51sResponse Time (max)1.91sResponse Time (total)3.01s
Puzzle Solving
: 3.5 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)2.47sResponse Time (max)2.86sResponse Time (total)7.40s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.77sResponse Time (max)4.77sResponse Time (total)4.77s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)21.72sResponse Time (max)21.72sResponse Time (total)21.72s
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
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.86sResponse Time (max)3.92sResponse Time (total)11.45s
Coding
: 6.0 A test is fully passed only if every run passed for that test.API error: 1Wrong answer: 1Response Time (avg)94.21sResponse Time (max)136.29sResponse Time (total)188.41s
Combined
: 2.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)64.71sResponse Time (max)64.71sResponse Time (total)64.71s
Data parsing and extraction
: 7.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)17.20sResponse Time (max)17.44sResponse Time (total)34.40s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.Timed out: 1Wrong answer: 1Response Time (avg)8.82sResponse Time (max)14.48sResponse Time (total)26.47s
General Intelligence
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.92sResponse Time (max)4.92sResponse Time (total)4.92s
Instructions following
: 9.9 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)3.36sResponse Time (max)4.35sResponse Time (total)6.72s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)8.19sResponse Time (max)8.19sResponse Time (total)8.19s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)82.71sResponse Time (max)82.71sResponse Time (total)82.71s
Agentic
: 3.0 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)35.39sResponse Time (max)35.39sResponse Time (total)35.39s
Anti-AI Tricks
: 6.4 A test is fully passed only if every run passed for that test.API error: 2Response Time (avg)10.82sResponse Time (max)15.85sResponse Time (total)43.29s
Coding
: 6.4 A test is fully passed only if every run passed for that test.API error: 2Response Time (avg)56.91sResponse Time (max)62.63sResponse Time (total)170.72s
Combined
: 5.1 A test is fully passed only if every run passed for that test.Invalid tool call: 1Wrong answer: 1Response Time (avg)177.43sResponse Time (max)229.67sResponse Time (total)354.87s
Data parsing and extraction
: 6.5 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)10.09sResponse Time (max)12.86sResponse Time (total)20.18s
Domain specific
: 3.0 A test is fully passed only if every run passed for that test.API error: 2Timed out: 1Response Time (avg)298.58sResponse Time (max)643.58sResponse Time (total)895.73s
General Intelligence
: 4.7 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)21.00sResponse Time (max)21.00sResponse Time (total)21.00s
Instructions following
: 2.8 A test is fully passed only if every run passed for that test.API error: 2Response Time (avg)9.52sResponse Time (max)9.76sResponse Time (total)19.03s
Puzzle Solving
: 5.3 A test is fully passed only if every run passed for that test.API error: 2Response Time (avg)31.07sResponse Time (max)72.76sResponse Time (total)93.21s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)17.26sResponse Time (max)17.26sResponse Time (total)17.26s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.No answer: 1Response Time (avg)183.84sResponse Time (max)183.84sResponse Time (total)183.84s
Agentic
: 3.5 A test is fully passed only if every run passed for that test.Timed out: 1Response Time (avg)490.99sResponse Time (max)490.99sResponse Time (total)490.99s
Anti-AI Tricks
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)10.29sResponse Time (max)17.68sResponse Time (total)41.16s
Coding
: 4.4 A test is fully passed only if every run passed for that test.Wrong answer: 2Extra formatting: 1Response Time (avg)168.41sResponse Time (max)280.94sResponse Time (total)505.22s
Combined
: 6.4 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)160.45sResponse Time (max)285.26sResponse Time (total)320.90s
Domain specific
: 2.9 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)88.61sResponse Time (max)226.92sResponse Time (total)265.83s
General Intelligence
: 3.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)7.58sResponse Time (max)7.58sResponse Time (total)7.58s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)6.92sResponse Time (max)6.92sResponse Time (total)6.92s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)77.98sResponse Time (max)77.98sResponse Time (total)77.98s
Agentic
: 3.0 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)26msResponse Time (max)26msResponse Time (total)26ms
Anti-AI Tricks
: 4.8 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)3.34sResponse Time (max)9.88sResponse Time (total)13.36s
Coding
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)6.39sResponse Time (max)17.51sResponse Time (total)19.16s
Combined
: 3.0 A test is fully passed only if every run passed for that test.Invalid tool call: 1Wrong answer: 1Response Time (avg)8.58sResponse Time (max)11.54sResponse Time (total)17.17s
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)1.10sResponse Time (max)1.23sResponse Time (total)2.21s
Domain specific
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 2API error: 1Response Time (avg)840msResponse Time (max)892msResponse Time (total)1.68s
General Intelligence
: 5.0 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
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)1.49sResponse Time (max)2.55sResponse Time (total)4.46s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.85sResponse Time (max)2.85sResponse Time (total)2.85s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)10.61sResponse Time (max)10.61sResponse Time (total)10.61s
Agentic
: 3.0 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)24msResponse Time (max)24msResponse Time (total)24ms
Anti-AI Tricks
: 9.2 A test is fully passed only if every run passed for that test.Did not follow instructions: 1Response Time (avg)1.81sResponse Time (max)3.73sResponse Time (total)7.25s
Coding
: 4.6 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)3.70sResponse Time (max)5.82sResponse Time (total)11.10s
Combined
: 3.0 A test is fully passed only if every run passed for that test.Invalid tool call: 1Wrong answer: 1Response Time (avg)4.08sResponse Time (max)4.59sResponse Time (total)8.15s
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)1.25sResponse Time (max)1.32sResponse Time (total)2.50s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)852msResponse Time (max)918msResponse Time (total)2.56s
Instructions following
: 9.9 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.89sResponse Time (max)2.18sResponse Time (total)3.78s
Puzzle Solving
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)1.56sResponse Time (max)2.38sResponse Time (total)4.68s
Tool Calling
: 3.0 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)2.21sResponse Time (max)2.21sResponse Time (total)2.21s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)2.00sResponse Time (max)2.00sResponse Time (total)2.00s
Agentic
: 5.2 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)65.61sResponse Time (max)65.61sResponse Time (total)65.61s
Anti-AI Tricks
: 3.6 A test is fully passed only if every run passed for that test.Wrong answer: 4Response Time (avg)2.10sResponse Time (max)6.15sResponse Time (total)8.41s
Coding
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)8.77sResponse Time (max)22.52sResponse Time (total)26.32s
Combined
: 3.8 A test is fully passed only if every run passed for that test.API error: 1No answer: 1Response Time (avg)39.54sResponse Time (max)39.54sResponse Time (total)39.54s
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)1.46sResponse Time (max)2.03sResponse Time (total)2.93s
Domain specific
: 2.9 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)7.76sResponse Time (max)12.46sResponse Time (total)23.27s
General Intelligence
: 4.4 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)3.51sResponse Time (max)3.51sResponse Time (total)3.51s
Instructions following
: 6.2 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.86sResponse Time (max)2.83sResponse Time (total)3.73s
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)414msResponse Time (max)414msResponse Time (total)414ms
Agentic
: 5.0 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)70.79sResponse Time (max)70.79sResponse Time (total)70.79s
Coding
: 4.3 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)623msResponse Time (max)1.34sResponse Time (total)1.87s
Combined
: 3.0 A test is fully passed only if every run passed for that test.Invalid tool call: 1Wrong answer: 1Response Time (avg)10.39sResponse Time (max)19.02sResponse Time (total)20.78s
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)768msResponse Time (max)824msResponse Time (total)1.54s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)303msResponse Time (max)379msResponse Time (total)910ms
General Intelligence
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)529msResponse Time (max)529msResponse Time (total)529ms
Puzzle Solving
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)1.01sResponse Time (max)1.92sResponse Time (total)3.02s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.36sResponse Time (max)1.36sResponse Time (total)1.36s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)254msResponse Time (max)254msResponse Time (total)254ms
A test is fully passed only if every run passed for that test.Wrong answer: 11Response Time (avg)7.82sResponse Time (max)102.62sResponse Time (total)172.04s…
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
Anti-AI Tricks
: 5.2 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)2.63sResponse Time (max)5.57sResponse Time (total)10.53s
Coding
: 3.8 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)3.12sResponse Time (max)3.45sResponse Time (total)9.35s
Combined
: 6.5 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)61.56sResponse Time (max)102.62sResponse Time (total)123.12s
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)2.87sResponse Time (max)3.54sResponse Time (total)5.74s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)1.23sResponse Time (max)1.27sResponse Time (total)3.70s
General Intelligence
: 4.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.62sResponse Time (max)1.62sResponse Time (total)1.62s
Instructions following
: 9.8 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.40sResponse Time (max)1.46sResponse Time (total)2.79s
Puzzle Solving
: 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)3.59sResponse Time (total)7.94s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)5.27sResponse Time (max)5.27sResponse Time (total)5.27s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.97sResponse Time (max)1.97sResponse Time (total)1.97s
A test is fully passed only if every run passed for that test.Wrong answer: 17No answer: 1Response Time (avg)35.86sResponse Time (max)321.19sResponse Time (total)609.61s…
Agentic
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)321.19sResponse Time (max)321.19sResponse Time (total)321.19s
Anti-AI Tricks
: 3.6 A test is fully passed only if every run passed for that test.Wrong answer: 4Response Time (avg)6.24sResponse Time (max)11.38sResponse Time (total)12.48s
Coding
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)24.56sResponse Time (max)38.78sResponse Time (total)73.69s
Combined
: 2.8 A test is fully passed only if every run passed for that test.No answer: 1Wrong answer: 1Response Time (avg)61.00sResponse Time (max)102.83sResponse Time (total)121.99s
Data parsing and extraction
: 7.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)42.13sResponse Time (max)42.13sResponse Time (total)42.13s
Domain specific
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)2.75sResponse Time (max)4.38sResponse Time (total)5.49s
General Intelligence
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.00sResponse Time (max)4.00sResponse Time (total)4.00s
Instructions following
: 6.5 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)2.67sResponse Time (max)2.67sResponse Time (total)2.67s
Puzzle Solving
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)4.04sResponse Time (max)7.81sResponse Time (total)8.08s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)13.99sResponse Time (max)13.99sResponse Time (total)13.99s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)3.90sResponse Time (max)3.90sResponse Time (total)3.90s
Agentic
: 6.1 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)142.68sResponse Time (max)142.68sResponse Time (total)142.68s
Anti-AI Tricks
: 8.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)11.68sResponse Time (max)40.72sResponse Time (total)46.73s
Coding
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)13.01sResponse Time (max)27.71sResponse Time (total)39.04s
Combined
: 3.0 A test is fully passed only if every run passed for that test.No answer: 1Timed out: 1Response Time (avg)298.21sResponse Time (max)566.80sResponse Time (total)596.42s
Data parsing and extraction
: 6.5 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.39sResponse Time (max)2.27sResponse Time (total)2.78s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)26.16sResponse Time (max)77.41sResponse Time (total)78.47s
Instructions following
: 3.0 A test is fully passed only if every run passed for that test.Timed out: 1Wrong answer: 1Response Time (avg)75.80sResponse Time (max)150.25sResponse Time (total)151.60s
Puzzle Solving
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 2Timed out: 1Response Time (avg)90.84sResponse Time (max)169.53sResponse Time (total)272.52s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.23sResponse Time (max)2.23sResponse Time (total)2.23s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)5.53sResponse Time (max)5.53sResponse Time (total)5.53s
Agentic
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)53.77sResponse Time (max)53.77sResponse Time (total)53.77s
Anti-AI Tricks
: 4.8 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)901msResponse Time (max)1.45sResponse Time (total)3.60s
Coding
: 3.8 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)980msResponse Time (max)1.57sResponse Time (total)2.94s
Combined
: 3.2 A test is fully passed only if every run passed for that test.Invalid tool call: 1Wrong answer: 1Response Time (avg)6.68sResponse Time (max)10.57sResponse Time (total)13.35s
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)758msResponse Time (max)803msResponse Time (total)1.52s
Domain specific
: 3.6 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)784msResponse Time (max)855msResponse Time (total)2.35s
General Intelligence
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.00sResponse Time (max)1.00sResponse Time (total)1.00s
Instructions following
: 7.1 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.23sResponse Time (max)1.66sResponse Time (total)2.47s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.80sResponse Time (max)2.80sResponse Time (total)2.80s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)651msResponse Time (max)651msResponse Time (total)651ms
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
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)6.59sResponse Time (max)10.20sResponse Time (total)26.37s
Coding
: 5.3 A test is fully passed only if every run passed for that test.API error: 2Response Time (avg)31.37sResponse Time (max)31.37sResponse Time (total)31.37s
Combined
: 5.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)46.04sResponse Time (max)46.04sResponse Time (total)46.04s
Data parsing and extraction
: 6.5 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)5.25sResponse Time (max)5.25sResponse Time (total)5.25s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)22.30sResponse Time (max)30.51sResponse Time (total)66.90s
General Intelligence
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)16.84sResponse Time (max)16.84sResponse Time (total)16.84s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)6.16sResponse Time (max)7.72sResponse Time (total)12.31s
Puzzle Solving
: 7.7 A test is fully passed only if every run passed for that test.Did not follow instructions: 1Response Time (avg)11.06sResponse Time (max)14.35sResponse Time (total)33.17s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)15.02sResponse Time (max)15.02sResponse Time (total)15.02s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)39.86sResponse Time (max)39.86sResponse Time (total)39.86s
A test is fully passed only if every run passed for that test.Wrong answer: 10API error: 5Response Time (avg)22.65sResponse Time (max)93.12sResponse Time (total)520.91s…
Agentic
: 6.1 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)92.87sResponse Time (max)92.87sResponse Time (total)92.87s
Anti-AI Tricks
: 5.2 A test is fully passed only if every run passed for that test.Wrong answer: 2API error: 1Response Time (avg)22.37sResponse Time (max)65.56sResponse Time (total)89.48s
Coding
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)1.94sResponse Time (max)3.25sResponse Time (total)5.81s
Combined
: 3.0 A test is fully passed only if every run passed for that test.API error: 1Wrong answer: 1Response Time (avg)49.01sResponse Time (max)93.12sResponse Time (total)98.01s
Data parsing and extraction
: 6.4 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)35.25sResponse Time (max)68.56sResponse Time (total)70.50s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)21.61sResponse Time (max)60.47sResponse Time (total)64.83s
General Intelligence
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)2.28sResponse Time (max)2.28sResponse Time (total)2.28s
Instructions following
: 6.4 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)31.00sResponse Time (max)59.73sResponse Time (total)62.01s
Puzzle Solving
: 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)4.51sResponse Time (total)7.63s
Tool Calling
: 3.0 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)26.44sResponse Time (max)26.44sResponse Time (total)26.44s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.05sResponse Time (max)1.05sResponse Time (total)1.05s
Global benchmark trends
See how current models trade score for cost, speed, output length, and category strength.