7.5Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
8.4Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
Rank
#48
#14
Reliability
9.8First-attempt success score: 10.0 means no retryable target API or rate-limit failures before successful calls; tracked failures lower the score.…
10.0First-attempt success score: 10.0 means no retryable target API or rate-limit failures before successful calls; tracked failures lower the score.…
Consistency
8.1Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
9.2Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
Tests Correct
A test is fully passed only if every run passed for that test.Did not follow instructions: 3Wrong answer: 3No answer: 1Response Time (avg)61.96sResponse Time (max)149.23sResponse Time (total)1115.31sA test is fully passed only if every run passed for that test.…
A test is fully passed only if every run passed for that test.Wrong answer: 5Response Time (avg)58.41sResponse Time (max)238.07sResponse Time (total)1168.27sA test is fully passed only if every run passed for that test.…
Attempt pass rate
74.1%Attempt pass rate = passed attempts / total attempts across runs.…
80.0%Attempt pass rate = passed attempts / total attempts across runs.…
Flaky tests
4Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
2Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
Total Runs
54Total Runs…
60Total Runs…
Cost per result
18.579Shows the average cost per correct benchmark answer in cents (lower is better).…
6.906Shows the average cost per correct benchmark answer in cents (lower is better).…
Total Cost
$2.044Total Cost…
$1.036Total Cost…
Input Price
$0.250 / 1MInput Price…
$1.040 / 1MInput Price…
Output Price
$1.500 / 1MOutput Price…
$6.240 / 1MOutput Price…
Output Tokens
1,984Output Tokens…
2,225Output Tokens…
Reasoning Tokens
1,355,583Reasoning Tokens…
130,808Reasoning Tokens…
Response Time (avg)
61.96sResponse Time (avg)…
58.41sResponse Time (avg)…
Response Time (max)
149.23sResponse Time (max)…
238.07sResponse Time (max)…
Response Time (total)
1115.31sResponse Time (total)…
1168.27sResponse Time (total)…
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Category Breakdown
Anti-AI Tricks
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Output Tokens
Reasoning Tokens
Gemini 3.1 Flash LiteArchived model: this model is no longer updated or tested on new tests.
9.4Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)37.16sResponse Time (max)140.53sResponse Time (total)148.65sA test is fully passed only if every run passed for that test.…
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)22.13sResponse Time (max)28.70sResponse Time (total)88.50sA test is fully passed only if every run passed for that test.…
22.13sResponse Time (avg)…
228Output Tokens…
10,075Reasoning Tokens…
Coding
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Output Tokens
Reasoning Tokens
Gemini 3.1 Flash LiteArchived model: this model is no longer updated or tested on new tests.
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)137.63sResponse Time (max)137.63sResponse Time (total)137.63sA test is fully passed only if every run passed for that test.…
8.2Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
6.7Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
83.3%Attempt pass rate = passed attempts / total attempts across runs.…
1Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)177.97sResponse Time (max)238.07sResponse Time (total)355.94sA test is fully passed only if every run passed for that test.…
177.97sResponse Time (avg)…
407Output Tokens…
39,442Reasoning Tokens…
Combined
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Output Tokens
Reasoning Tokens
Gemini 3.1 Flash LiteArchived model: this model is no longer updated or tested on new tests.
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)149.23sResponse Time (max)149.23sResponse Time (total)149.23sA test is fully passed only if every run passed for that test.…
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)121.49sResponse Time (max)121.49sResponse Time (total)121.49sA test is fully passed only if every run passed for that test.…
121.49sResponse Time (avg)…
390Output Tokens…
14,575Reasoning Tokens…
Data parsing and extraction
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Output Tokens
Reasoning Tokens
Gemini 3.1 Flash LiteArchived model: this model is no longer updated or tested on new tests.
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)4.49sResponse Time (max)4.96sResponse Time (total)8.98sA test is fully passed only if every run passed for that test.…
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)41.15sResponse Time (max)48.02sResponse Time (total)82.30sA test is fully passed only if every run passed for that test.…
41.15sResponse Time (avg)…
270Output Tokens…
10,106Reasoning Tokens…
Domain specific
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Output Tokens
Reasoning Tokens
Gemini 3.1 Flash LiteArchived model: this model is no longer updated or tested on new tests.
3.6Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
7.2Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
22.2%Attempt pass rate = passed attempts / total attempts across runs.…
1Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)139.90sResponse Time (max)141.40sResponse Time (total)419.69sA test is fully passed only if every run passed for that test.…
2.9Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
7.2Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
11.1%Attempt pass rate = passed attempts / total attempts across runs.…
1Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Wrong answer: 3Response Time (avg)95.91sResponse Time (max)186.74sResponse Time (total)287.73sA test is fully passed only if every run passed for that test.…
95.91sResponse Time (avg)…
60Output Tokens…
30,371Reasoning Tokens…
General Intelligence
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Output Tokens
Reasoning Tokens
Gemini 3.1 Flash LiteArchived model: this model is no longer updated or tested on new tests.
5.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
2.1Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
66.7%Attempt pass rate = passed attempts / total attempts across runs.…
1Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Did not follow instructions: 1Response Time (avg)45.69sResponse Time (max)45.69sResponse Time (total)45.69sA test is fully passed only if every run passed for that test.…
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)32.24sResponse Time (max)32.24sResponse Time (total)32.24sA test is fully passed only if every run passed for that test.…
32.24sResponse Time (avg)…
129Output Tokens…
3,510Reasoning Tokens…
Instructions following
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Output Tokens
Reasoning Tokens
Gemini 3.1 Flash LiteArchived model: this model is no longer updated or tested on new tests.
7.3Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
5.8Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
83.3%Attempt pass rate = passed attempts / total attempts across runs.…
1Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No answer: 1Response Time (avg)23.26sResponse Time (max)43.87sResponse Time (total)46.51sA test is fully passed only if every run passed for that test.…
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)24.31sResponse Time (max)27.94sResponse Time (total)48.63sA test is fully passed only if every run passed for that test.…
24.31sResponse Time (avg)…
103Output Tokens…
5,848Reasoning Tokens…
Puzzle Solving
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Output Tokens
Reasoning Tokens
Gemini 3.1 Flash LiteArchived model: this model is no longer updated or tested on new tests.
5.7Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
6.8Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
44.4%Attempt pass rate = passed attempts / total attempts across runs.…
1Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Did not follow instructions: 2Response Time (avg)50.83sResponse Time (max)144.85sResponse Time (total)152.49sA test is fully passed only if every run passed for that test.…
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)24.19sResponse Time (max)37.68sResponse Time (total)72.57sA test is fully passed only if every run passed for that test.…
24.19sResponse Time (avg)…
301Output Tokens…
7,649Reasoning Tokens…
Tool Calling
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Output Tokens
Reasoning Tokens
Gemini 3.1 Flash LiteArchived model: this model is no longer updated or tested on new tests.
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)6.44sResponse Time (max)6.44sResponse Time (total)6.44sA test is fully passed only if every run passed for that test.…
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
100.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.No failed answers.Response Time (avg)18.32sResponse Time (max)18.32sResponse Time (total)18.32sA test is fully passed only if every run passed for that test.…
18.32sResponse Time (avg)…
309Output Tokens…
1,571Reasoning Tokens…
Trivia
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Output Tokens
Reasoning Tokens
Gemini 3.1 Flash LiteArchived model: this model is no longer updated or tested on new tests.
3.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
0.0%Attempt pass rate = passed attempts / total attempts across runs.…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
A test is fully passed only if every run passed for that test.Wrong answer: 1Response Time (avg)60.56sResponse Time (max)60.56sResponse Time (total)60.56sA test is fully passed only if every run passed for that test.…