The average score is effectively tied at 7.9 vs 7.9. Local hardware cost was not measured, so cost comparisons are unavailable. Step 3.7 Flash (medium) is faster at 23.51s vs 39.11s, with pass rates of 68.2% vs 68.2%.
Last updated at:
2026-08-15
Rank
#61
Total Output Tokens
169,329
Response Time (avg)
39.11s
Total Cost
N/A
Rank
#60
Total Output Tokens
409,709
Response Time (avg)
23.51s
Total Cost
$0.495
Recommended modelStep 3.7 Flash (medium)
It has the best score here (7.9), while responding about 1.7x faster than Qwen3.8 27B (low).
Detailed comparison
Metric
Qwen3.8 27BQwen3.8 27BlowCandidate responses were generated on local hardware. OpenRouter was used only for judging.Release: 2026-08-14
7.9Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
7.9Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
Rank
#61
#60
Reliability
10.0First-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
10.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
8.9Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
Attempts
66/66
66/66
Tests Correct
A test is fully passed only if every run passed for that test.Wrong answer: 4No answer: 2Did not follow instructions: 1Response Time (avg)39.11sResponse Time (max)376.04sResponse Time (total)860.51sA test is fully passed only if every run passed for that test.…
68.2%Attempt pass rate = passed attempts / total attempts across runs.…
68.2%Attempt pass rate = passed attempts / total attempts across runs.…
Flaky tests
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
3Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
Total Runs
66Total Runs…
66Total Runs…
Cost per result
N/AShows the average cost per correct benchmark answer in cents (lower is better).…
3.801Shows the average cost per correct benchmark answer in cents (lower is better).…
Total Cost
N/ATotal Cost (Current Price)…
$0.495Total Cost (Current Price)…
Input Price
N/AInput Price…
$0.200 / 1MInput Price…
Output Price
N/AOutput Price…
$1.150 / 1MOutput Price…
Total Input Tokens
99,705Total Input Tokens…
114,191Total Input Tokens…
Output Tokens
1,545Output Tokens…
409,709Output Tokens…
Reasoning Tokens
167,784Reasoning Tokens…
0Reasoning Tokens…
Response Time (avg)
39.11sResponse Time (avg)…
23.51sResponse Time (avg)…
Response Time (max)
376.04sResponse Time (max)…
152.83sResponse Time (max)…
Response Time (total)
860.51sResponse Time (total)…
517.21sResponse Time (total)…
Parameters
27.3B
198B total (11B active)
Availability
Weights available
Open source
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#61 Qwen3.8 27B
lowCandidate responses were generated on local hardware. OpenRouter was used only for judging.
Cost
N/A
Time
92.8s
Tokens
6,902 tok
#60 Step 3.7 Flash
medium
Cost
$0.006
Time
46.2s
Tokens
4,466 tok
Score
-
Cost
-
Time
-
Tokens
-
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)
Input Tokens
Output Tokens
Reasoning Tokens
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging.
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)3.02sResponse Time (max)5.68sResponse Time (total)12.07sA test is fully passed only if every run passed for that test.…
8.7Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
7.9Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
91.7%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)9.65sResponse Time (max)35.08sResponse Time (total)38.62sA test is fully passed only if every run passed for that test.…
9.65sResponse Time (avg)…
756Total Input Tokens…
32,185Output Tokens…
0Reasoning Tokens…
Coding
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Input Tokens
Output Tokens
Reasoning Tokens
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging.
7.7Summarizes 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.No answer: 1Response Time (avg)140.92sResponse Time (max)376.04sResponse Time (total)422.75sA test is fully passed only if every run passed for that test.…
8.8Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
7.8Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
88.9%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)27.42sResponse Time (max)60.98sResponse Time (total)82.26sA test is fully passed only if every run passed for that test.…
27.42sResponse Time (avg)…
7,437Total Input Tokens…
44,797Output Tokens…
0Reasoning Tokens…
Combined
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Input Tokens
Output Tokens
Reasoning Tokens
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging.
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)90.63sResponse Time (max)143.71sResponse Time (total)181.27sA test is fully passed only if every run passed for that test.…
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.Invalid tool call: 1Response Time (avg)80.94sResponse Time (max)152.83sResponse Time (total)161.89sA test is fully passed only if every run passed for that test.…
80.94sResponse Time (avg)…
87,764Total Input Tokens…
114,720Output Tokens…
0Reasoning Tokens…
Data parsing and extraction
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Input Tokens
Output Tokens
Reasoning Tokens
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging.
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)8.03sResponse Time (max)9.09sResponse Time (total)16.06sA 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)2.75sResponse Time (max)3.35sResponse Time (total)5.49sA test is fully passed only if every run passed for that test.…
2.75sResponse Time (avg)…
7,398Total Input Tokens…
3,020Output Tokens…
0Reasoning Tokens…
Domain specific
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Input Tokens
Output Tokens
Reasoning Tokens
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging.
5.3Summarizes 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.Wrong answer: 2Response Time (avg)60.78sResponse Time (max)120.94sResponse Time (total)182.34sA test is fully passed only if every run passed for that test.…
5.3Summarizes 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.Wrong answer: 2Response Time (avg)27.26sResponse Time (max)34.06sResponse Time (total)81.77sA test is fully passed only if every run passed for that test.…
27.26sResponse Time (avg)…
837Total Input Tokens…
52,484Output Tokens…
0Reasoning Tokens…
General Intelligence
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Input Tokens
Output Tokens
Reasoning Tokens
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging.
5.0Summarizes 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)5.37sResponse Time (max)5.37sResponse Time (total)5.37sA test is fully passed only if every run passed for that test.…
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).…
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)6.85sResponse Time (max)6.85sResponse Time (total)6.85sA test is fully passed only if every run passed for that test.…
6.85sResponse Time (avg)…
525Total Input Tokens…
3,987Output Tokens…
0Reasoning Tokens…
Instructions following
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Input Tokens
Output Tokens
Reasoning Tokens
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging.
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)2.43sResponse Time (max)2.87sResponse Time (total)4.86sA test is fully passed only if every run passed for that test.…
9.8Summarizes 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)1.83sResponse Time (max)2.21sResponse Time (total)3.65sA test is fully passed only if every run passed for that test.…
1.83sResponse Time (avg)…
735Total Input Tokens…
2,166Output Tokens…
0Reasoning Tokens…
Puzzle Solving
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Input Tokens
Output Tokens
Reasoning Tokens
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging.
7.7Summarizes 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.Wrong answer: 1Response Time (avg)4.91sResponse Time (max)8.81sResponse Time (total)14.74sA test is fully passed only if every run passed for that test.…
5.7Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
9.9Consistency 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.Wrong answer: 2Response Time (avg)6.19sResponse Time (max)12.51sResponse Time (total)18.56sA test is fully passed only if every run passed for that test.…
6.19sResponse Time (avg)…
756Total Input Tokens…
15,071Output Tokens…
0Reasoning Tokens…
Tool Calling
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Input Tokens
Output Tokens
Reasoning Tokens
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging.
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)8.42sResponse Time (max)8.42sResponse Time (total)8.42sA 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)4.16sResponse Time (max)4.16sResponse Time (total)4.16sA test is fully passed only if every run passed for that test.…
4.16sResponse Time (avg)…
7,746Total Input Tokens…
2,115Output Tokens…
0Reasoning Tokens…
Trivia
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Input Tokens
Output Tokens
Reasoning Tokens
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging.
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.No answer: 1Response Time (avg)12.64sResponse Time (max)12.64sResponse Time (total)12.64sA test is fully passed only if every run passed for that test.…
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.No answer: 1Response Time (avg)113.98sResponse Time (max)113.98sResponse Time (total)113.98sA test is fully passed only if every run passed for that test.…