4.6Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
7.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
Rank
#44
#24
Tests Correct
A test is fully passed only if every run passed for that test.Wrong answer: 8Did not follow instructions: 1Response Time (avg)1.46sResponse Time (max)2.89sResponse Time (total)21.86sA 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.Timed out: 3API error: 1Wrong answer: 1Response Time (avg)72.86sResponse Time (max)234.29sResponse Time (total)1092.84sA test is fully passed only if every run passed for that test.…
Consistency
8.9Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
7.8Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
Cost per result
1.496Shows the average cost per correct benchmark answer in cents (lower is better).…
0.565Shows the average cost per correct benchmark answer in cents (lower is better).…
Total Cost
$0.090Total Cost…
$0.057Total Cost…
Attempt pass rate
44.4%Attempt pass rate = passed attempts / total attempts across runs.…
82.2%Attempt pass rate = passed attempts / total attempts across runs.…
Flaky tests
2Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
4Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
common.totalRuns
45 (15 x 3)common.totalRuns…
45 (15 x 3)common.totalRuns…
Output Tokens
1,635Output Tokens…
1,708Output Tokens…
Reasoning Tokens
0Reasoning Tokens…
131,466Reasoning Tokens…
Response Time (avg)
1.46sResponse Time (avg)…
72.86sResponse Time (avg)…
Response Time (max)
2.89sResponse Time (max)…
234.29sResponse Time (max)…
Response Time (total)
21.86sResponse Time (total)…
1092.84sResponse Time (total)…
Top Models by Score
Score vs Total Cost
Response Time (avg)
Avg Score vs Response Time (avg)
Category Breakdown
Anti-AI Tricks
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Output Tokens
Reasoning Tokens
OpenAI: GPT-5.4
10.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
7.3Consistency 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)1.41sResponse Time (max)2.58sResponse Time (total)4.23sA test is fully passed only if every run passed for that test.…
1.41sResponse Time (avg)…
388Output Tokens…
0Reasoning Tokens…
Qwen: Qwen3.5-Flash
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)71.35sResponse Time (max)168.31sResponse Time (total)214.06sA test is fully passed only if every run passed for that test.…
71.35sResponse Time (avg)…
363Output Tokens…
23,645Reasoning Tokens…
Combined
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Output Tokens
Reasoning Tokens
OpenAI: GPT-5.4
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).…
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)2.89sResponse Time (max)2.89sResponse Time (total)2.89sA test is fully passed only if every run passed for that test.…
2.89sResponse Time (avg)…
291Output Tokens…
0Reasoning Tokens…
Qwen: Qwen3.5-Flash
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)17.78sResponse Time (max)17.78sResponse Time (total)17.78sA test is fully passed only if every run passed for that test.…
17.78sResponse Time (avg)…
483Output Tokens…
8,270Reasoning Tokens…
Data parsing and extraction
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Output Tokens
Reasoning Tokens
OpenAI: GPT-5.4
9.9Summarizes 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)1.04sResponse Time (max)1.06sResponse Time (total)2.08sA test is fully passed only if every run passed for that test.…
1.04sResponse Time (avg)…
222Output Tokens…
0Reasoning Tokens…
Qwen: Qwen3.5-Flash
5.5Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
5.9Consistency 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.API error: 1Response Time (avg)56.99sResponse Time (max)80.14sResponse Time (total)113.98sA test is fully passed only if every run passed for that test.…
56.99sResponse Time (avg)…
235Output Tokens…
16,237Reasoning Tokens…
Domain specific
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Output Tokens
Reasoning Tokens
OpenAI: GPT-5.4
4.0Summarizes 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).…
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.Wrong answer: 2Response Time (avg)1.07sResponse Time (max)1.54sResponse Time (total)3.22sA test is fully passed only if every run passed for that test.…
1.07sResponse Time (avg)…
50Output Tokens…
0Reasoning Tokens…
Qwen: Qwen3.5-Flash
4.0Summarizes 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).…
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.Timed out: 1Wrong answer: 1Response Time (avg)146.50sResponse Time (max)234.29sResponse Time (total)439.49sA test is fully passed only if every run passed for that test.…
146.50sResponse Time (avg)…
58Output Tokens…
43,615Reasoning Tokens…
Instructions following
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Output Tokens
Reasoning Tokens
OpenAI: GPT-5.4
5.5Summarizes 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).…
50.0%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)1.07sResponse Time (max)1.17sResponse Time (total)2.15sA test is fully passed only if every run passed for that test.…
1.07sResponse Time (avg)…
81Output Tokens…
0Reasoning Tokens…
Qwen: Qwen3.5-Flash
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)63.49sResponse Time (max)111.61sResponse Time (total)126.98sA test is fully passed only if every run passed for that test.…
63.49sResponse Time (avg)…
98Output Tokens…
14,139Reasoning Tokens…
Puzzle Solving
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Output Tokens
Reasoning Tokens
OpenAI: GPT-5.4
4.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
9.8Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
33.3%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.Did not follow instructions: 1Wrong answer: 1Response Time (avg)1.52sResponse Time (max)1.82sResponse Time (total)4.56sA test is fully passed only if every run passed for that test.…
1.52sResponse Time (avg)…
357Output Tokens…
0Reasoning Tokens…
Qwen: Qwen3.5-Flash
4.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
4.4Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
77.8%Attempt pass rate = passed attempts / total attempts across runs.…
2Flaky 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.Timed out: 2Response Time (avg)56.74sResponse Time (max)115.01sResponse Time (total)170.23sA test is fully passed only if every run passed for that test.…
56.74sResponse Time (avg)…
162Output Tokens…
24,276Reasoning Tokens…
Tool Calling
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Output Tokens
Reasoning Tokens
OpenAI: GPT-5.4
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)2.75sResponse Time (max)2.75sResponse Time (total)2.75sA test is fully passed only if every run passed for that test.…
2.75sResponse Time (avg)…
246Output Tokens…
0Reasoning Tokens…
Qwen: Qwen3.5-Flash
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)10.33sResponse Time (max)10.33sResponse Time (total)10.33sA test is fully passed only if every run passed for that test.…