Nemotron 3 Super (medium) leads on average score with 5.5 vs 5.4. Qwen3.8 27B has the lower benchmark cost at ~$0.010 vs $0.081. Qwen3.8 27B is faster at 5.05s vs 56.40s, with pass rates of 42.0% vs 39.1%.
Last updated at:
2026-10-01
Compared models
Rank
#264
Total Output Tokens
147,935
Response Time (avg)
56.40s
Total Cost
$0.081
Candidate responses were generated on local hardware. OpenRouter was used only for judging.
Rank
#272
Total Output Tokens
13,791
Response Time (avg)
5.05s
Total Cost
~$0.010Estimated GPU electricity cost only. It excludes the rest of the computer and hardware ownership. NVIDIA GeForce RTX 3090: 0.0968 h × 0.300 kW × €0.2896/kWh × 1.138 USD/EUR = ~$0.009566.
Recommended modelQwen3.8 27B
Its score stays close to the best score here (5.4 vs 5.5), while costing about 8.4x less than Nemotron 3 Super (medium).
A test is fully passed only if every run passed for that test.Wrong answer: 12Did not follow instructions: 1Invalid tool call: 1Response Time (avg)5.05sResponse Time (max)47.42sResponse Time (total)116.11sA test is fully passed only if every run passed for that test.…
Attempt pass rate
42.0%Attempt pass rate = passed attempts / total attempts across runs.…
39.1%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).…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
Total Runs
69Total Runs…
69Total Runs…
Cost per result
0.004
~0.107Estimated GPU electricity cost only. It excludes the rest of the computer and hardware ownership. NVIDIA GeForce RTX 3090: 0.0968 h × 0.300 kW × €0.2896/kWh × 1.138 USD/EUR = ~$0.009566.
Total Cost
$0.081
~$0.010Estimated GPU electricity cost only. It excludes the rest of the computer and hardware ownership. NVIDIA GeForce RTX 3090: 0.0968 h × 0.300 kW × €0.2896/kWh × 1.138 USD/EUR = ~$0.009566.
Input Price
$0.080 / 1MInput Price…
N/AInput Price…
Output Price
$0.450 / 1MOutput Price…
N/AOutput Price…
Total Input Tokens
229,346Total Input Tokens…
281,460Total Input Tokens…
Output Tokens
18,597Output Tokens…
13,791Output Tokens…
Reasoning Tokens
129,338Reasoning Tokens…
0Reasoning Tokens…
Response Time (avg)
56.40sResponse Time (avg)…
5.05sResponse Time (avg)…
Response Time (max)
431.98sResponse Time (max)…
47.42sResponse Time (max)…
Response Time (total)
1184.46sResponse Time (total)…
116.11sResponse Time (total)…
Parameters
120B total (12B 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.
#264 Nemotron 3 Super
medium
Cost
$0.000
Time
272.6s
Tokens
5,296 tok
#272 Qwen3.8 27B
noneCandidate responses were generated on local hardware. OpenRouter was used only for judging.
Cost
~$0.001Estimated GPU electricity cost only. It excludes the rest of the computer and hardware ownership. NVIDIA GeForce RTX 3090: 0.0066 h × 0.300 kW × €0.2896/kWh × 1.138 USD/EUR = ~$0.000657.
4.7Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
1.6Consistency 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.Wrong answer: 1Response Time (avg)138.25sResponse Time (max)138.25sResponse Time (total)138.25sA test is fully passed only if every run passed for that test.…
138.25sResponse Time (avg)…
147,908Total Input Tokens…
923Output Tokens…
31,438Reasoning 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.Wrong answer: 1Response Time (avg)47.42sResponse Time (max)47.42sResponse Time (total)47.42sA test is fully passed only if every run passed for that test.…
8.3Summarizes 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).…
75.0%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)7.85sResponse Time (max)22.30sResponse Time (total)31.40sA test is fully passed only if every run passed for that test.…
7.85sResponse Time (avg)…
686Total Input Tokens…
748Output Tokens…
1,305Reasoning 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.…
3.1Summarizes 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.API error: 3Response Time (avg)147.32sResponse Time (max)232.25sResponse Time (total)294.64sA test is fully passed only if every run passed for that test.…
147.32sResponse Time (avg)…
2,275Total Input Tokens…
797Output Tokens…
4,424Reasoning 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.…
5.8Consistency 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.API error: 1Response Time (avg)259.89sResponse Time (max)431.98sResponse Time (total)519.77sA test is fully passed only if every run passed for that test.…
259.89sResponse Time (avg)…
59,463Total Input Tokens…
5,542Output Tokens…
75,095Reasoning 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.…
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)18.16sResponse Time (max)20.65sResponse Time (total)36.33sA test is fully passed only if every run passed for that test.…
18.16sResponse Time (avg)…
7,944Total Input Tokens…
877Output Tokens…
2,607Reasoning 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: 2Timed out: 1Response Time (avg)19.35sResponse Time (max)21.56sResponse Time (total)38.71sA test is fully passed only if every run passed for that test.…
19.35sResponse Time (avg)…
465Total Input Tokens…
4,558Output Tokens…
5,119Reasoning 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.…
4.1Summarizes 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)6.91sResponse Time (max)6.91sResponse Time (total)6.91sA test is fully passed only if every run passed for that test.…
6.91sResponse Time (avg)…
492Total Input Tokens…
105Output Tokens…
363Reasoning 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.…
7.3Summarizes 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.Did not follow instructions: 1Response Time (avg)6.97sResponse Time (max)11.23sResponse Time (total)13.95sA test is fully passed only if every run passed for that test.…
6.97sResponse Time (avg)…
723Total Input Tokens…
956Output Tokens…
2,383Reasoning 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.…
3.0Summarizes 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: 2Did not follow instructions: 1Response Time (avg)3.15sResponse Time (max)4.52sResponse Time (total)9.45sA test is fully passed only if every run passed for that test.…
3.15sResponse Time (avg)…
708Total Input Tokens…
570Output Tokens…
1,322Reasoning 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)39.75sResponse Time (max)39.75sResponse Time (total)39.75sA test is fully passed only if every run passed for that test.…
39.75sResponse Time (avg)…
8,544Total Input Tokens…
270Output Tokens…
1,969Reasoning 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)55.32sResponse Time (max)55.32sResponse Time (total)55.32sA test is fully passed only if every run passed for that test.…
55.32sResponse Time (avg)…
138Total Input Tokens…
3,251Output Tokens…
3,313Reasoning 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.…