Agentic
: 4.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)94.09sResponse Time (max)94.09sResponse Time (total)94.09s
Anti-AI Tricks
: 6.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)25.50sResponse Time (max)37.73sResponse Time (total)51.00s
Coding
: 7.0 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)41.62sResponse Time (max)54.86sResponse Time (total)124.86s
Combined
: 6.4 A test is fully passed only if every run passed for that test.No answer: 1Response Time (avg)146.93sResponse Time (max)227.89sResponse Time (total)293.85s
Data parsing and extraction
: 3.7 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)21.42sResponse Time (max)21.42sResponse Time (total)21.42s
Domain specific
: 3.4 A test is fully passed only if every run passed for that test.Wrong answer: 2Timed out: 1Response Time (avg)124.13sResponse Time (max)204.02sResponse Time (total)248.27s
Instructions following
: 9.8 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)15.64sResponse Time (max)15.64sResponse Time (total)15.64s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)33.30sResponse Time (max)33.30sResponse Time (total)33.30s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)20.13sResponse Time (max)20.13sResponse Time (total)20.13s
Agentic
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)44.97sResponse Time (max)44.97sResponse Time (total)44.97s
Anti-AI Tricks
: 6.7 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)4.13sResponse Time (max)8.33sResponse Time (total)16.53s
Combined
: 3.0 A test is fully passed only if every run passed for that test.Invalid tool call: 2Response Time (avg)262.39sResponse Time (max)419.41sResponse Time (total)524.77s
Data parsing and extraction
: 6.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)13.98sResponse Time (max)20.06sResponse Time (total)27.96s
Domain specific
: 2.9 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)66.94sResponse Time (max)118.63sResponse Time (total)200.81s
Instructions following
: 6.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)4.12sResponse Time (max)4.57sResponse Time (total)8.24s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)5.96sResponse Time (max)5.96sResponse Time (total)5.96s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)125.13sResponse Time (max)125.13sResponse Time (total)125.13s
Agentic
: 3.0 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)21msResponse Time (max)21msResponse Time (total)21ms
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)42.21sResponse Time (max)89.34sResponse Time (total)168.84s
Coding
: 5.3 A test is fully passed only if every run passed for that test.API error: 2Response Time (avg)59.65sResponse Time (max)59.65sResponse Time (total)59.65s
Combined
: 7.3 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)257.28sResponse Time (max)304.19sResponse Time (total)514.55s
Data parsing and extraction
: 6.5 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)37.36sResponse Time (max)54.24sResponse Time (total)74.71s
Domain specific
: 3.6 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)65.30sResponse Time (max)150.55sResponse Time (total)195.89s
Instructions following
: 9.8 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)11.78sResponse Time (max)17.75sResponse Time (total)23.55s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)104.44sResponse Time (max)104.44sResponse Time (total)104.44s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)113.91sResponse Time (max)113.91sResponse Time (total)113.91s
A test is fully passed only if every run passed for that test.Wrong answer: 7API error: 2Invalid tool call: 2Response Time (avg)13.08sResponse Time (max)75.27sResponse Time (total)287.79s…
Agentic
: 3.0 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)42msResponse Time (max)42msResponse Time (total)42ms
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.26sResponse Time (max)10.43sResponse Time (total)17.02s
Coding
: 6.7 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)14.85sResponse Time (max)23.25sResponse Time (total)44.56s
Combined
: 2.9 A test is fully passed only if every run passed for that test.Invalid tool call: 2Response Time (avg)50.41sResponse Time (max)75.27sResponse Time (total)100.82s
Data parsing and extraction
: 7.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)7.15sResponse Time (max)11.16sResponse Time (total)14.31s
Domain specific
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 2API error: 1Response Time (avg)30.29sResponse Time (max)40.12sResponse Time (total)60.58s
General Intelligence
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)2.98sResponse Time (max)2.98sResponse Time (total)2.98s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.85sResponse Time (max)1.99sResponse Time (total)3.70s
Puzzle Solving
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.33sResponse Time (max)6.40sResponse Time (total)12.98s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)6.47sResponse Time (max)6.47sResponse Time (total)6.47s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)24.35sResponse Time (max)24.35sResponse Time (total)24.35s
Agentic
: 7.4 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)55.81sResponse Time (max)55.81sResponse Time (total)55.81s
Anti-AI Tricks
: 3.7 A test is fully passed only if every run passed for that test.Wrong answer: 4Response Time (avg)1.90sResponse Time (max)2.99sResponse Time (total)7.61s
Combined
: 3.0 A test is fully passed only if every run passed for that test.No answer: 1Wrong answer: 1Response Time (avg)10.37sResponse Time (max)14.56sResponse Time (total)20.73s
Data parsing and extraction
: 6.5 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)3.09sResponse Time (max)5.97sResponse Time (total)6.19s
Domain specific
: 7.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)5.46sResponse Time (max)13.30sResponse Time (total)16.37s
Instructions following
: 6.5 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)6.81sResponse Time (max)12.42sResponse Time (total)13.61s
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)1.83sResponse 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)3.76sResponse Time (max)3.76sResponse Time (total)3.76s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.32sResponse Time (max)1.32sResponse Time (total)1.32s
Agentic
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)57.98sResponse Time (max)57.98sResponse Time (total)57.98s
Anti-AI Tricks
: 4.8 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)942msResponse Time (max)1.09sResponse Time (total)3.77s
Coding
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)1.00sResponse Time (max)1.14sResponse Time (total)3.01s
Combined
: 2.9 A test is fully passed only if every run passed for that test.Invalid tool call: 1No answer: 1Response Time (avg)7.02sResponse Time (max)10.07sResponse Time (total)14.05s
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)1.27sResponse Time (total)2.26s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)843msResponse Time (max)923msResponse Time (total)2.53s
General Intelligence
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.03sResponse Time (max)1.03sResponse Time (total)1.03s
Puzzle Solving
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)1.23sResponse Time (max)2.02sResponse Time (total)3.70s
Tool Calling
: 9.6 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)3.10sResponse Time (max)3.10sResponse Time (total)3.10s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)787msResponse Time (max)787msResponse Time (total)787ms
A test is fully passed only if every run passed for that test.Wrong answer: 14Did not follow instructions: 1Response Time (avg)3.46sResponse Time (max)43.95sResponse Time (total)79.48s…
Agentic
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)43.95sResponse Time (max)43.95sResponse Time (total)43.95s
Anti-AI Tricks
: 3.6 A test is fully passed only if every run passed for that test.Wrong answer: 4Response Time (avg)1.14sResponse Time (max)2.84sResponse Time (total)4.55s
Coding
: 5.6 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)2.38sResponse Time (max)5.85sResponse Time (total)7.15s
Combined
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)7.51sResponse Time (max)13.15sResponse Time (total)15.02s
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)544msResponse Time (max)612msResponse Time (total)1.09s
Domain specific
: 7.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)463msResponse Time (max)614msResponse Time (total)1.39s
Instructions following
: 6.5 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)608msResponse Time (max)738msResponse Time (total)1.22s
Puzzle Solving
: 5.4 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)750msResponse Time (max)1.21sResponse Time (total)2.25s
Tool Calling
: 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)1.60sResponse Time (total)1.60s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)655msResponse Time (max)655msResponse Time (total)655ms
~$0.011Estimated GPU electricity cost only. It excludes the rest of the computer and hardware ownership. NVIDIA GeForce RTX 3090: 0.1095 h × 0.300 kW × €0.2896/kWh × 1.138 USD/EUR = ~$0.010823.
5.71s…
A test is fully passed only if every run passed for that test.Wrong answer: 14No answer: 1Response Time (avg)5.71sResponse Time (max)65.25sResponse Time (total)131.36s…
Agentic
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)65.25sResponse Time (max)65.25sResponse Time (total)65.25s
Anti-AI Tricks
: 6.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)1.70sResponse Time (max)4.03sResponse Time (total)6.82s
Coding
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)1.64sResponse Time (max)2.70sResponse Time (total)4.91s
Combined
: 3.0 A test is fully passed only if every run passed for that test.No answer: 1Wrong answer: 1Response Time (avg)11.98sResponse Time (max)16.02sResponse Time (total)23.95s
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)1.71sResponse Time (total)3.19s
Domain specific
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)5.38sResponse Time (max)15.16sResponse Time (total)16.15s
General Intelligence
: 6.1 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.09sResponse Time (max)1.09sResponse Time (total)1.09s
Instructions following
: 7.1 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)612msResponse Time (max)637msResponse Time (total)1.22s
Puzzle Solving
: 6.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)1.30sResponse Time (max)2.37sResponse Time (total)3.89s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.35sResponse Time (max)4.35sResponse Time (total)4.35s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)540msResponse Time (max)540msResponse Time (total)540ms
Agentic
: 4.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)117.01sResponse Time (max)117.01sResponse Time (total)117.01s
Anti-AI Tricks
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 4Response Time (avg)2.55sResponse Time (max)6.80sResponse Time (total)10.19s
Coding
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)1.55sResponse Time (max)2.70sResponse Time (total)4.65s
Combined
: 3.8 A test is fully passed only if every run passed for that test.Invalid tool call: 1Wrong answer: 1Response Time (avg)94.59sResponse Time (max)186.24sResponse Time (total)189.18s
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)2.09sResponse Time (max)3.22sResponse Time (total)4.18s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)814msResponse Time (max)979msResponse Time (total)2.44s
General Intelligence
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)963msResponse Time (max)963msResponse Time (total)963ms
Instructions following
: 6.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)892msResponse Time (max)990msResponse Time (total)1.78s
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)766msResponse Time (max)766msResponse Time (total)766ms
Agentic
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)70.17sResponse Time (max)70.17sResponse Time (total)70.17s
Anti-AI Tricks
: 3.5 A test is fully passed only if every run passed for that test.Wrong answer: 4Response Time (avg)2.35sResponse Time (max)6.55sResponse Time (total)9.42s
Coding
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)1.02sResponse Time (max)1.83sResponse Time (total)3.07s
Combined
: 3.0 A test is fully passed only if every run passed for that test.API error: 1Wrong answer: 1Response Time (avg)21.14sResponse Time (max)37.50sResponse Time (total)42.28s
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)1.94sResponse Time (max)2.86sResponse Time (total)3.89s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.API error: 1Wrong answer: 1Response Time (avg)758msResponse Time (max)1.00sResponse Time (total)2.28s
General Intelligence
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)13.49sResponse Time (max)13.49sResponse Time (total)13.49s
Instructions following
: 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)1.72sResponse Time (total)2.92s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.99sResponse Time (max)2.99sResponse Time (total)2.99s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.83sResponse Time (max)1.83sResponse Time (total)1.83s
Agentic
: 4.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)64.73sResponse Time (max)64.73sResponse Time (total)64.73s
Anti-AI Tricks
: 5.3 A test is fully passed only if every run passed for that test.Extra formatting: 2Wrong answer: 1Response Time (avg)3.60sResponse Time (max)7.10sResponse Time (total)14.39s
Coding
: 4.6 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)3.67sResponse Time (max)5.83sResponse Time (total)11.02s
Combined
: 6.5 A test is fully passed only if every run passed for that test.No answer: 1Response Time (avg)31.43sResponse Time (max)33.39sResponse Time (total)62.86s
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)3.01sResponse Time (max)3.29sResponse Time (total)6.02s
Domain specific
: 2.9 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)3.32sResponse Time (max)4.75sResponse Time (total)9.96s
Instructions following
: 6.4 A test is fully passed only if every run passed for that test.Extra formatting: 1Response Time (avg)2.58sResponse Time (max)2.89sResponse Time (total)5.17s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)6.80sResponse Time (max)6.80sResponse Time (total)6.80s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.No answer: 1Response Time (avg)4.31sResponse Time (max)4.31sResponse Time (total)4.31s
Agentic
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)93.47sResponse Time (max)93.47sResponse Time (total)93.47s
Anti-AI Tricks
: 3.1 A test is fully passed only if every run passed for that test.Wrong answer: 4Response Time (avg)1.63sResponse Time (max)4.60sResponse Time (total)6.51s
Coding
: 5.4 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)1.79sResponse Time (max)2.46sResponse Time (total)5.36s
Combined
: 3.8 A test is fully passed only if every run passed for that test.Invalid tool call: 2Response Time (avg)26.50sResponse Time (max)48.79sResponse Time (total)53.01s
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)2.13sResponse Time (max)3.35sResponse Time (total)4.26s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)963msResponse Time (max)1.89sResponse Time (total)2.89s
General Intelligence
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)947msResponse Time (max)947msResponse Time (total)947ms
Instructions following
: 6.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.10sResponse Time (max)1.36sResponse Time (total)2.19s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.49sResponse Time (max)2.49sResponse Time (total)2.49s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)649msResponse Time (max)649msResponse Time (total)649ms
Agentic
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)43.82sResponse Time (max)43.82sResponse Time (total)43.82s
Anti-AI Tricks
: 7.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)1.07sResponse Time (max)1.91sResponse Time (total)4.27s
Coding
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)938msResponse Time (max)1.59sResponse Time (total)2.81s
Combined
: 3.0 A test is fully passed only if every run passed for that test.No answer: 1Wrong answer: 1Response Time (avg)9.49sResponse Time (max)16.25sResponse Time (total)18.98s
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)843msResponse Time (max)907msResponse Time (total)1.69s
Domain specific
: 2.9 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)701msResponse Time (max)814msResponse Time (total)2.10s
General Intelligence
: 4.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)992msResponse Time (max)992msResponse Time (total)992ms
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)859msResponse Time (max)975msResponse Time (total)1.72s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.97sResponse Time (max)2.97sResponse Time (total)2.97s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)733msResponse Time (max)733msResponse Time (total)733ms
Agentic
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)203.90sResponse Time (max)203.90sResponse Time (total)203.90s
Coding
: 5.9 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)38.37sResponse Time (max)68.16sResponse Time (total)115.10s
Combined
: 6.5 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)23.96sResponse Time (max)31.18sResponse Time (total)47.91s
Data parsing and extraction
: 6.4 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.98sResponse Time (max)1.98sResponse Time (total)1.98s
Domain specific
: 2.9 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)27.55sResponse Time (max)50.92sResponse Time (total)55.10s
Instructions following
: 9.9 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)7.63sResponse Time (max)7.63sResponse Time (total)7.63s
Tool Calling
: 9.8 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)6.91sResponse Time (max)6.91sResponse Time (total)6.91s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)26.51sResponse Time (max)26.51sResponse Time (total)26.51s
Agentic
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)50.03sResponse Time (max)50.03sResponse Time (total)50.03s
Anti-AI Tricks
: 8.3 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.10sResponse Time (max)1.65sResponse Time (total)4.42s
Coding
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)831msResponse Time (max)1.31sResponse Time (total)2.49s
Combined
: 3.0 A test is fully passed only if every run passed for that test.No answer: 1Wrong answer: 1Response Time (avg)7.75sResponse Time (max)12.97sResponse Time (total)15.50s
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)1.04sResponse Time (max)1.32sResponse Time (total)2.07s
Domain specific
: 2.9 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)972msResponse Time (max)1.16sResponse Time (total)2.92s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)932msResponse Time (max)1.00sResponse Time (total)1.86s
Puzzle Solving
: 6.0 A test is fully passed only if every run passed for that test.Did not follow instructions: 2Response Time (avg)2.15sResponse Time (max)4.49sResponse Time (total)6.45s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)3.51sResponse Time (max)3.51sResponse Time (total)3.51s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)724msResponse Time (max)724msResponse Time (total)724ms
Agentic
: 3.0 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)49msResponse Time (max)49msResponse Time (total)49ms
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.09sResponse Time (max)10.33sResponse Time (total)16.35s
Coding
: 7.8 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)10.49sResponse Time (max)17.26sResponse Time (total)31.48s
Combined
: 3.8 A test is fully passed only if every run passed for that test.Invalid tool call: 2Response Time (avg)8.89sResponse Time (max)12.00sResponse Time (total)17.78s
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)3.95sResponse Time (max)5.78sResponse Time (total)7.89s
Domain specific
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)7.65sResponse Time (max)14.20sResponse Time (total)22.94s
Tool Calling
: 3.0 A test is fully passed only if every run passed for that test.Did not follow instructions: 1Response Time (avg)2.12sResponse Time (max)2.12sResponse Time (total)2.12s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)14.19sResponse Time (max)14.19sResponse Time (total)14.19s
A test is fully passed only if every run passed for that test.Wrong answer: 14No answer: 1Response Time (avg)7.49sResponse Time (max)75.99sResponse Time (total)172.19s…
Agentic
: 5.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)75.99sResponse Time (max)75.99sResponse Time (total)75.99s
Anti-AI Tricks
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 4Response Time (avg)2.43sResponse Time (max)6.70sResponse Time (total)9.73s
Coding
: 5.6 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)2.83sResponse Time (max)4.61sResponse Time (total)8.49s
Combined
: 3.0 A test is fully passed only if every run passed for that test.No answer: 1Wrong answer: 1Response Time (avg)25.58sResponse Time (max)44.58sResponse Time (total)51.17s
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)1.82sResponse Time (max)1.97sResponse Time (total)3.63s
Domain specific
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)1.12sResponse Time (max)1.53sResponse Time (total)3.36s
General Intelligence
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)3.45sResponse Time (max)3.45sResponse Time (total)3.45s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.06sResponse Time (max)1.09sResponse Time (total)2.12s
Puzzle Solving
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)2.78sResponse Time (max)5.20sResponse Time (total)8.34s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)3.94sResponse Time (max)3.94sResponse Time (total)3.94s
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
: 5.0 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)66.15sResponse Time (max)66.15sResponse Time (total)66.15s
Anti-AI Tricks
: 3.5 A test is fully passed only if every run passed for that test.Wrong answer: 4Response Time (avg)1.87sResponse Time (max)5.31sResponse Time (total)7.50s
Coding
: 5.6 A test is fully passed only if every run passed for that test.Extra formatting: 2Response Time (avg)3.69sResponse Time (max)5.45sResponse Time (total)11.08s
Combined
: 2.9 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)7.78sResponse Time (max)12.50sResponse Time (total)15.56s
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)1.05sResponse Time (max)1.22sResponse Time (total)2.11s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)791msResponse Time (max)860msResponse Time (total)2.37s
Instructions following
: 9.8 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)803msResponse Time (max)870msResponse Time (total)1.61s
Puzzle Solving
: 7.9 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.67sResponse Time (max)2.31sResponse Time (total)5.01s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.44sResponse Time (max)2.44sResponse Time (total)2.44s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)106.86sResponse Time (max)106.86sResponse Time (total)106.86s
Agentic
: 4.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)77.99sResponse Time (max)77.99sResponse Time (total)77.99s
Anti-AI Tricks
: 8.2 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.56sResponse Time (max)2.05sResponse Time (total)6.26s
Coding
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)5.45sResponse Time (max)6.31sResponse Time (total)16.36s
Combined
: 2.8 A test is fully passed only if every run passed for that test.Invalid tool call: 1Wrong answer: 1Response Time (avg)42.40sResponse Time (max)73.01sResponse Time (total)84.79s
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)1.59sResponse Time (max)1.63sResponse Time (total)3.17s
Domain specific
: 3.5 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)3.87sResponse Time (max)4.85sResponse Time (total)11.62s
General Intelligence
: 4.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)2.07sResponse Time (max)2.07sResponse Time (total)2.07s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)1.34sResponse Time (max)1.42sResponse Time (total)2.69s
Puzzle Solving
: 7.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.89sResponse Time (max)2.38sResponse Time (total)5.68s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)9.52sResponse Time (max)9.52sResponse Time (total)9.52s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.No answer: 1Response Time (avg)2.69sResponse Time (max)2.69sResponse Time (total)2.69s
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
: 5.5 A test is fully passed only if every run passed for that test.Extra formatting: 1Wrong answer: 1Response Time (avg)5.19sResponse Time (max)9.79sResponse Time (total)15.56s
Combined
: 9.8 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)37.51sResponse Time (max)51.18sResponse Time (total)75.03s
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)3.43sResponse Time (max)3.43sResponse Time (total)3.43s
Domain specific
: 7.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)2.27sResponse Time (max)3.54sResponse Time (total)4.54s
Instructions following
: 6.5 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
Puzzle Solving
: 7.7 A test is fully passed only if every run passed for that test.Extra formatting: 1Response Time (avg)2.53sResponse Time (max)2.54sResponse Time (total)5.06s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.11sResponse Time (max)4.11sResponse Time (total)4.11s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)4.67sResponse Time (max)4.67sResponse Time (total)4.67s
Agentic
: 3.4 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)85.34sResponse Time (max)85.34sResponse Time (total)85.34s
Anti-AI Tricks
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)8.24sResponse Time (max)19.73sResponse Time (total)32.95s
Coding
: 4.3 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)51.01sResponse Time (max)82.35sResponse Time (total)153.02s
Combined
: 6.4 A test is fully passed only if every run passed for that test.No answer: 1Response Time (avg)66.43sResponse Time (max)115.57sResponse Time (total)132.87s
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)14.99sResponse Time (max)19.83sResponse Time (total)29.99s
Domain specific
: 4.1 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)63.74sResponse Time (max)105.49sResponse Time (total)191.21s
Puzzle Solving
: 8.2 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)15.19sResponse Time (max)25.27sResponse Time (total)45.56s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.62sResponse Time (max)4.62sResponse Time (total)4.62s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)42.92sResponse Time (max)42.92sResponse Time (total)42.92s
Agentic
: 3.0 A test is fully passed only if every run passed for that test.API error: 1Response Time (avg)1.90sResponse Time (max)1.90sResponse Time (total)1.90s
Anti-AI Tricks
: 8.7 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)4.58sResponse Time (max)7.94sResponse Time (total)18.33s
Coding
: 6.1 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)22.52sResponse Time (max)30.63sResponse Time (total)67.55s
Combined
: 4.1 A test is fully passed only if every run passed for that test.Invalid tool call: 1Wrong answer: 1Response Time (avg)183.08sResponse Time (max)335.41sResponse Time (total)366.16s
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)5.07sResponse Time (max)5.35sResponse Time (total)10.15s
Domain specific
: 4.1 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)24.90sResponse Time (max)53.57sResponse Time (total)74.71s
General Intelligence
: 4.8 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
Instructions following
: 9.8 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.61sResponse Time (max)2.82sResponse Time (total)5.23s
Puzzle Solving
: 8.2 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)3.03sResponse Time (max)4.12sResponse Time (total)9.10s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)5.93sResponse Time (max)5.93sResponse Time (total)5.93s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)9.91sResponse Time (max)9.91sResponse Time (total)9.91s
Agentic
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)149.50sResponse Time (max)149.50sResponse Time (total)149.50s
Anti-AI Tricks
: 8.4 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)10.34sResponse Time (max)35.62sResponse Time (total)41.36s
Coding
: 5.5 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)12.09sResponse Time (max)21.31sResponse Time (total)36.27s
Combined
: 3.0 A test is fully passed only if every run passed for that test.No answer: 1Timed out: 1Response Time (avg)291.12sResponse Time (max)557.96sResponse Time (total)582.25s
Data parsing and extraction
: 6.5 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.43sResponse Time (max)2.31sResponse Time (total)2.87s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)13.96sResponse Time (max)40.61sResponse Time (total)41.88s
Puzzle Solving
: 3.1 A test is fully passed only if every run passed for that test.Timed out: 2Wrong answer: 1Response Time (avg)75.99sResponse Time (max)116.19sResponse Time (total)227.96s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)2.28sResponse Time (max)2.28sResponse Time (total)2.28s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)2.24sResponse Time (max)2.24sResponse Time (total)2.24s
Agentic
: 6.1 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)95.77sResponse Time (max)95.77sResponse Time (total)95.77s
Anti-AI Tricks
: 6.4 A test is fully passed only if every run passed for that test.API error: 1Wrong answer: 1Response Time (avg)12.58sResponse Time (max)36.18sResponse Time (total)50.32s
Coding
: 2.8 A test is fully passed only if every run passed for that test.No answer: 2Did not follow instructions: 1Response Time (avg)363.90sResponse Time (max)369.01sResponse Time (total)1091.69s
Combined
: 7.3 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)124.99sResponse Time (max)231.73sResponse Time (total)249.98s
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)4.10sResponse Time (max)5.14sResponse Time (total)8.20s
Domain specific
: 2.9 A test is fully passed only if every run passed for that test.No answer: 3Response Time (avg)323.23sResponse Time (max)438.09sResponse Time (total)969.70s
Instructions following
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.23sResponse Time (max)4.40sResponse Time (total)8.46s
Puzzle Solving
: 7.8 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)59.88sResponse Time (max)173.78sResponse Time (total)179.64s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)3.84sResponse Time (max)3.84sResponse Time (total)3.84s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.No answer: 1Response Time (avg)437.86sResponse Time (max)437.86sResponse Time (total)437.86s
Agentic
: 6.1 A test is fully passed only if every run passed for that test.Invalid tool call: 1Response Time (avg)137.10sResponse Time (max)137.10sResponse Time (total)137.10s
Anti-AI Tricks
: 4.8 A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)1.88sResponse Time (max)4.81sResponse Time (total)7.53s
Combined
: 6.4 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)109.69sResponse Time (max)206.05sResponse Time (total)219.37s
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)2.82sResponse Time (max)3.86sResponse Time (total)5.65s
Domain specific
: 5.3 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)1.06sResponse Time (max)1.71sResponse Time (total)3.19s
Instructions following
: 6.2 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)1.17sResponse Time (max)1.33sResponse Time (total)2.35s
Puzzle Solving
: 6.7 A test is fully passed only if every run passed for that test.Wrong answer: 2Response Time (avg)1.97sResponse Time (max)3.43sResponse Time (total)5.91s
Tool Calling
: 10.0 A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.42sResponse Time (max)4.42sResponse Time (total)4.42s
Trivia
: 3.0 A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)33.34sResponse Time (max)33.34sResponse Time (total)33.34s
Global benchmark trends
See how current models trade score for cost, speed, output length, and category strength.