7.7Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
7.4Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
Consistency
9.5Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
9.1Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
Cost per result
8.525Shows the average cost per correct benchmark answer in cents (lower is better).…
0.000Shows the average cost per correct benchmark answer in cents (lower is better).…
Total Cost
$1.023Total Cost…
$0.000Total Cost…
Tests Correct
A test is fully passed only if every run passed for that test.Extra formatting: 2Timed out: 1Wrong answer: 1Response Time (avg)11.23sResponse Time (max)46.35sResponse Time (total)89.84sA 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.Did not follow instructions: 3Wrong answer: 3Response Time (avg)29.10sResponse Time (max)170.45sResponse Time (total)290.96sA test is fully passed only if every run passed for that test.…
Attempt pass rate
77.1%Attempt pass rate = passed attempts / total attempts across runs.…
68.8%Attempt pass rate = passed attempts / total attempts across runs.…
Flaky tests
1Flaky 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
48 (16 x 3)Total Runs…
48 (16 x 3)Total Runs…
Output Tokens
35,159Output Tokens…
71,452Output Tokens…
Reasoning Tokens
24,687Reasoning Tokens…
155,147Reasoning Tokens…
Response Time (avg)
11.23sResponse Time (avg)…
29.10sResponse Time (avg)…
Response Time (max)
46.35sResponse Time (max)…
170.45sResponse Time (max)…
Response Time (total)
89.84sResponse Time (total)…
290.96sResponse 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
Anthropic: Claude Sonnet 4.6
7.0Summarizes 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).…
66.7%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.Extra formatting: 1Response Time (avg)4.95sResponse Time (max)4.95sResponse Time (total)4.95sA test is fully passed only if every run passed for that test.…
4.95sResponse Time (avg)…
1,031Output Tokens…
1,093Reasoning Tokens…
StepFun: Step 3.5 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)18.54sResponse Time (max)32.30sResponse Time (total)37.07sA test is fully passed only if every run passed for that test.…
18.54sResponse Time (avg)…
13,924Output Tokens…
17,208Reasoning Tokens…
Combined
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Output Tokens
Reasoning Tokens
Anthropic: Claude Sonnet 4.6
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)46.35sResponse Time (max)46.35sResponse Time (total)46.35sA test is fully passed only if every run passed for that test.…
46.35sResponse Time (avg)…
5,871Output Tokens…
3,962Reasoning Tokens…
StepFun: Step 3.5 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)29.57sResponse Time (max)29.57sResponse Time (total)29.57sA test is fully passed only if every run passed for that test.…
29.57sResponse Time (avg)…
1,176Output Tokens…
12,984Reasoning Tokens…
Data parsing and extraction
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Output Tokens
Reasoning Tokens
Anthropic: Claude Sonnet 4.6
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)13.90sResponse Time (max)13.90sResponse Time (total)13.90sA test is fully passed only if every run passed for that test.…
13.90sResponse Time (avg)…
649Output Tokens…
742Reasoning Tokens…
StepFun: Step 3.5 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)15.01sResponse Time (max)15.01sResponse Time (total)15.01sA test is fully passed only if every run passed for that test.…
15.01sResponse Time (avg)…
600Output Tokens…
13,886Reasoning Tokens…
Domain specific
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Output Tokens
Reasoning Tokens
Anthropic: Claude Sonnet 4.6
10.0Summarizes 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).…
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.Extra formatting: 1Timed out: 1Wrong answer: 1Response Time (avg)0msResponse Time (max)0msResponse Time (total)0msA test is fully passed only if every run passed for that test.…
0msResponse Time (avg)…
25,790Output Tokens…
16,919Reasoning Tokens…
StepFun: Step 3.5 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.Wrong answer: 2Response Time (avg)170.45sResponse Time (max)170.45sResponse Time (total)170.45sA test is fully passed only if every run passed for that test.…
170.45sResponse Time (avg)…
45,350Output Tokens…
90,436Reasoning Tokens…
General Intelligence
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Output Tokens
Reasoning Tokens
Anthropic: Claude Sonnet 4.6
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)4.94sResponse Time (max)4.94sResponse Time (total)4.94sA test is fully passed only if every run passed for that test.…
4.94sResponse Time (avg)…
256Output Tokens…
433Reasoning Tokens…
StepFun: Step 3.5 Flash
6.0Summarizes 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.Did not follow instructions: 1Response Time (avg)6.54sResponse Time (max)6.54sResponse Time (total)6.54sA test is fully passed only if every run passed for that test.…
6.54sResponse Time (avg)…
2,214Output Tokens…
2,584Reasoning Tokens…
Instructions following
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Output Tokens
Reasoning Tokens
Anthropic: Claude Sonnet 4.6
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)2.61sResponse Time (max)2.61sResponse Time (total)2.61sA test is fully passed only if every run passed for that test.…
2.61sResponse Time (avg)…
318Output Tokens…
552Reasoning Tokens…
StepFun: Step 3.5 Flash
9.0Summarizes 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).…
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.Did not follow instructions: 1Response Time (avg)4.98sResponse Time (max)4.98sResponse Time (total)4.98sA test is fully passed only if every run passed for that test.…
4.98sResponse Time (avg)…
2,284Output Tokens…
3,412Reasoning Tokens…
Puzzle Solving
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Output Tokens
Reasoning Tokens
Anthropic: Claude Sonnet 4.6
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)4.80sResponse Time (max)5.22sResponse Time (total)9.60sA test is fully passed only if every run passed for that test.…
4.80sResponse Time (avg)…
589Output Tokens…
635Reasoning Tokens…
StepFun: Step 3.5 Flash
4.0Summarizes 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).…
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)7.72sResponse Time (max)10.60sResponse Time (total)15.44sA test is fully passed only if every run passed for that test.…
7.72sResponse Time (avg)…
5,629Output Tokens…
10,835Reasoning Tokens…
Tool Calling
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Output Tokens
Reasoning Tokens
Anthropic: Claude Sonnet 4.6
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)7.48sResponse Time (max)7.48sResponse Time (total)7.48sA test is fully passed only if every run passed for that test.…
7.48sResponse Time (avg)…
655Output Tokens…
351Reasoning Tokens…
StepFun: Step 3.5 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)11.91sResponse Time (max)11.91sResponse Time (total)11.91sA test is fully passed only if every run passed for that test.…