The average score is effectively tied at 5.6 vs 5.5. Local hardware cost was not measured, so cost comparisons are unavailable. Qwen3.8 27B is faster at 3.12s vs 58.26s, with pass rates of 50.0% vs 40.9%.
Last updated at:
2026-08-15
Rank
#208
Total Output Tokens
654,597
Response Time (avg)
58.26s
Total Cost
$0.168
Rank
#211
Total Output Tokens
11,445
Response Time (avg)
3.12s
Total Cost
N/A
Recommended modelQwen3.8 27B
It has the best score here (5.5), while responding about 18.7x faster than Nemotron 3.5 Lightning (high).
A test is fully passed only if every run passed for that test.Wrong answer: 11Did not follow instructions: 1Invalid tool call: 1Response Time (avg)3.12sResponse Time (max)44.76sResponse Time (total)68.69sA test is fully passed only if every run passed for that test.…
Attempt pass rate
50.0%Attempt pass rate = passed attempts / total attempts across runs.…
40.9%Attempt pass rate = passed attempts / total attempts across runs.…
Flaky tests
12Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
Total Runs
66Total Runs…
66Total Runs…
Cost per result
0.000Shows the average cost per correct benchmark answer in cents (lower is better).…
N/AShows the average cost per correct benchmark answer in cents (lower is better).…
Total Cost
$0.168Total Cost (Current Price)…
N/ATotal Cost (Current Price)…
Input Price
$0.100 / 1MInput Price…
N/AInput Price…
Output Price
$0.250 / 1MOutput Price…
N/AOutput Price…
Total Input Tokens
118,016Total Input Tokens…
122,463Total Input Tokens…
Output Tokens
148,344Output Tokens…
11,445Output Tokens…
Reasoning Tokens
506,253Reasoning Tokens…
0Reasoning Tokens…
Response Time (avg)
58.26sResponse Time (avg)…
3.12sResponse Time (avg)…
Response Time (max)
285.26sResponse Time (max)…
44.76sResponse Time (max)…
Response Time (total)
1281.79sResponse Time (total)…
68.69sResponse Time (total)…
Parameters
30B total (3B active)
27.3B
Availability
Weights available
Weights available
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#208 Nemotron 3.5 Lightning
high
Cost
$0.000
Time
92.8s
Tokens
11,343 tok
#211 Qwen3.8 27B
noneCandidate responses were generated on local hardware. OpenRouter was used only for judging.
5.5Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
3.7Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
66.7%Attempt pass rate = passed attempts / total attempts across runs.…
3Flaky 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)10.29sResponse Time (max)17.68sResponse Time (total)41.16sA test is fully passed only if every run passed for that test.…
10.29sResponse Time (avg)…
696Total Input Tokens…
2,432Output Tokens…
15,948Reasoning Tokens…
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging.
6.5Summarizes 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: 2Response Time (avg)828msResponse Time (max)1.95sResponse Time (total)3.31sA test is fully passed only if every run passed for that test.…
4.4Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
5.1Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
33.3%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.Wrong answer: 2Extra formatting: 1Response Time (avg)168.41sResponse Time (max)280.94sResponse Time (total)505.22sA test is fully passed only if every run passed for that test.…
168.41sResponse Time (avg)…
7,623Total Input Tokens…
68,533Output Tokens…
242,319Reasoning Tokens…
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging.
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).…
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)1.19sResponse Time (max)1.97sResponse Time (total)3.56sA test is fully passed only if every run passed for that test.…
6.4Summarizes 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).…
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.Invalid tool call: 1Response Time (avg)160.45sResponse Time (max)285.26sResponse Time (total)320.90sA test is fully passed only if every run passed for that test.…
160.45sResponse Time (avg)…
90,257Total Input Tokens…
17,550Output Tokens…
119,725Reasoning 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.Invalid tool call: 1Wrong answer: 1Response Time (avg)24.10sResponse Time (max)44.76sResponse Time (total)48.21sA 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.…
5.9Consistency 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.Did not follow instructions: 1Response Time (avg)13.99sResponse Time (max)18.67sResponse Time (total)27.97sA test is fully passed only if every run passed for that test.…
13.99sResponse Time (avg)…
7,944Total Input Tokens…
3,210Output Tokens…
16,835Reasoning Tokens…
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging.
6.5Summarizes 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)1.14sResponse Time (max)1.18sResponse Time (total)2.27sA 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.…
4.4Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
22.2%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.Wrong answer: 3Response Time (avg)88.61sResponse Time (max)226.92sResponse Time (total)265.83sA test is fully passed only if every run passed for that test.…
88.61sResponse Time (avg)…
798Total Input Tokens…
45,616Output Tokens…
72,496Reasoning 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)552msResponse Time (max)675msResponse Time (total)1.66sA test is fully passed only if every run passed for that test.…
3.7Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
9.5Consistency 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)7.58sResponse Time (max)7.58sResponse Time (total)7.58sA test is fully passed only if every run passed for that test.…
7.58sResponse Time (avg)…
516Total Input Tokens…
4,331Output Tokens…
4,408Reasoning Tokens…
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging.
4.2Summarizes 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).…
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)1.31sResponse Time (max)1.31sResponse Time (total)1.31sA test is fully passed only if every run passed for that test.…
8.5Summarizes 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)5.05sResponse Time (total)9.97sA test is fully passed only if every run passed for that test.…
4.98sResponse Time (avg)…
723Total Input Tokens…
502Output Tokens…
3,779Reasoning Tokens…
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging.
6.3Summarizes 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).…
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)582msResponse Time (max)633msResponse Time (total)1.16sA test is fully passed only if every run passed for that test.…
3.6Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
1.8Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
44.4%Attempt pass rate = passed attempts / total attempts across runs.…
3Flaky 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: 2Wrong answer: 1Response Time (avg)6.09sResponse Time (max)10.09sResponse Time (total)18.26sA test is fully passed only if every run passed for that test.…
6.09sResponse Time (avg)…
726Total Input Tokens…
1,236Output Tokens…
9,851Reasoning Tokens…
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging.
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).…
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)1.25sResponse Time (max)1.84sResponse Time (total)3.76sA 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)6.92sResponse Time (max)6.92sResponse Time (total)6.92sA test is fully passed only if every run passed for that test.…
6.92sResponse Time (avg)…
8,526Total Input Tokens…
3,745Output Tokens…
3,781Reasoning 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)2.75sResponse Time (max)2.75sResponse Time (total)2.75sA 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.Wrong answer: 1Response Time (avg)77.98sResponse Time (max)77.98sResponse Time (total)77.98sA test is fully passed only if every run passed for that test.…
77.98sResponse Time (avg)…
207Total Input Tokens…
1,189Output Tokens…
17,111Reasoning 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)703msResponse Time (max)703msResponse Time (total)703msA test is fully passed only if every run passed for that test.…