Muse Spark Open (medium) leads on average score with 8.8 vs 8.7. Qwen3.8 27B (high) has the lower benchmark cost at ~$0.298 vs $1.260. Muse Spark Open (medium) is faster at 77.44s vs 166.34s, with pass rates of 78.3% vs 78.3%.
Last updated at:
2026-10-16
Compared models
Rank
#61
Total Output Tokens
220,815
Response Time (avg)
77.44s
Total Cost
$1.260
Candidate responses were generated on local hardware. OpenRouter was used only for judging. qwen3.8:latest · Q4_K_M · Ollama 0.32.12 · NVIDIA GeForce RTX 3090.
Rank
#66
Total Output Tokens
677,080
Response Time (avg)
166.34s
Total Cost
~$0.298Estimated GPU electricity cost only. It excludes the rest of the computer and hardware ownership. NVIDIA GeForce RTX 3090: 3.0102 h × 0.300 kW × €0.2896/kWh × 1.138 USD/EUR = ~$0.297613.
Recommended modelQwen3.8 27B (high)
Its score stays close to the best score here (8.7 vs 8.8), while costing about 4.2x less than Muse Spark Open (medium).
Qwen3.8 27BQwen3.8 27BhighCandidate responses were generated on local hardware. OpenRouter was used only for judging. qwen3.8:latest · Q4_K_M · Ollama 0.32.12 · NVIDIA GeForce RTX 3090.Release: 2026-08-14Free Available
Qwen3.8 27BQwen3.8 27BhighCandidate responses were generated on local hardware. OpenRouter was used only for judging. qwen3.8:latest · Q4_K_M · Ollama 0.32.12 · NVIDIA GeForce RTX 3090.Release: 2026-08-14Free Available
Score
8.8Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
8.7Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
Rank
#61
#66
Reliability
9.8First-attempt success score: 10.0 means no retryable target API or rate-limit failures before successful calls; tracked failures lower the score.…
9.7First-attempt success score: 10.0 means no retryable target API or rate-limit failures before successful calls; tracked failures lower the score.…
Consistency
8.2Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
9.2Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
A test is fully passed only if every run passed for that test.Did not follow instructions: 2No answer: 2Wrong answer: 2Response Time (avg)166.34sResponse Time (max)640.85sResponse Time (total)3825.81sA test is fully passed only if every run passed for that test.…
Attempt pass rate
78.3%Attempt pass rate = passed attempts / total attempts across runs.…
78.3%Attempt pass rate = passed attempts / total attempts across runs.…
Flaky tests
5Flaky 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
69Total Runs…
69Total Runs…
Cost per result
8.396
~1.751Estimated GPU electricity cost only. It excludes the rest of the computer and hardware ownership. NVIDIA GeForce RTX 3090: 3.0102 h × 0.300 kW × €0.2896/kWh × 1.138 USD/EUR = ~$0.297613.
Total Cost
$1.260
~$0.298Estimated GPU electricity cost only. It excludes the rest of the computer and hardware ownership. NVIDIA GeForce RTX 3090: 3.0102 h × 0.300 kW × €0.2896/kWh × 1.138 USD/EUR = ~$0.297613.
Input Price
$1.250 / 1MInput Price…
N/AInput Price…
Output Price
$4.250 / 1MOutput Price…
N/AOutput Price…
Cache Read Price
$0.150 / 1MCache Read Price…
N/ACache Read Price…
Cache Write Price
N/ACache Write Price…
N/ACache Write Price…
Total Input Tokens
256,646Total Input Tokens…
348,967Total Input Tokens…
Output Tokens
10,490Output Tokens…
1,005Output Tokens…
Reasoning Tokens
210,325Reasoning Tokens…
676,075Reasoning Tokens…
Response Time (avg)
77.44sResponse Time (avg)…
166.34sResponse Time (avg)…
Response Time (max)
643.19sResponse Time (max)…
640.85sResponse Time (max)…
Response Time (total)
1781.16sResponse Time (total)…
3825.81sResponse Time (total)…
Parameters
816B total (42B active)
27.3B
Availability
Weights available
Weights available
Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#61 Muse Spark Open
medium
Cost
$0.018
Time
10.0s
Tokens
4,265 tok
#66 Qwen3.8 27B
highCandidate responses were generated on local hardware. OpenRouter was used only for judging. qwen3.8:latest · Q4_K_M · Ollama 0.32.12 · NVIDIA GeForce RTX 3090.
Cost
~$0.008Estimated GPU electricity cost only. It excludes the rest of the computer and hardware ownership. NVIDIA GeForce RTX 3090: 0.0750 h × 0.300 kW × €0.2896/kWh × 1.138 USD/EUR = ~$0.007419.
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)43.27sResponse Time (max)43.27sResponse Time (total)43.27sA test is fully passed only if every run passed for that test.…
43.27sResponse Time (avg)…
142,559Total Input Tokens…
2,198Output Tokens…
5,604Reasoning Tokens…
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging. qwen3.8:latest · Q4_K_M · Ollama 0.32.12 · NVIDIA GeForce RTX 3090.
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)132.27sResponse Time (max)132.27sResponse Time (total)132.27sA test is fully passed only if every run passed for that test.…
6.9Summarizes 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).…
75.0%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: 1Wrong answer: 1Response Time (avg)175.36sResponse Time (max)643.19sResponse Time (total)701.44sA test is fully passed only if every run passed for that test.…
175.36sResponse Time (avg)…
1,851Total Input Tokens…
494Output Tokens…
6,363Reasoning Tokens…
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging. qwen3.8:latest · Q4_K_M · Ollama 0.32.12 · NVIDIA GeForce RTX 3090.
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)8.10sResponse Time (max)21.48sResponse Time (total)32.40sA test is fully passed only if every run passed for that test.…
8.2Summarizes 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).…
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.Extra formatting: 1Response Time (avg)18.01sResponse Time (max)41.41sResponse Time (total)54.04sA test is fully passed only if every run passed for that test.…
18.01sResponse Time (avg)…
8,478Total Input Tokens…
821Output Tokens…
18,472Reasoning Tokens…
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging. qwen3.8:latest · Q4_K_M · Ollama 0.32.12 · NVIDIA GeForce RTX 3090.
8.1Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
7.0Consistency 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.Did not follow instructions: 1Response Time (avg)248.62sResponse Time (max)458.25sResponse Time (total)745.85sA 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)72.16sResponse Time (max)110.81sResponse Time (total)144.32sA test is fully passed only if every run passed for that test.…
72.16sResponse Time (avg)…
76,922Total Input Tokens…
5,197Output Tokens…
15,661Reasoning Tokens…
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging. qwen3.8:latest · Q4_K_M · Ollama 0.32.12 · NVIDIA GeForce RTX 3090.
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)185.57sResponse Time (max)333.21sResponse Time (total)371.15sA 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)10.67sResponse Time (max)19.97sResponse Time (total)21.35sA test is fully passed only if every run passed for that test.…
10.67sResponse Time (avg)…
7,767Total Input Tokens…
229Output Tokens…
3,036Reasoning Tokens…
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging. qwen3.8:latest · Q4_K_M · Ollama 0.32.12 · NVIDIA GeForce RTX 3090.
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)34.85sResponse Time (max)57.71sResponse Time (total)69.71sA test is fully passed only if every run passed for that test.…
5.9Summarizes 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).…
55.6%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)216.17sResponse Time (max)359.46sResponse Time (total)648.50sA test is fully passed only if every run passed for that test.…
216.17sResponse Time (avg)…
1,937Total Input Tokens…
90Output Tokens…
137,454Reasoning Tokens…
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging. qwen3.8:latest · Q4_K_M · Ollama 0.32.12 · NVIDIA GeForce RTX 3090.
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.No answer: 1Wrong answer: 1Response Time (avg)526.74sResponse Time (max)640.85sResponse Time (total)1580.21sA 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)4.90sResponse Time (max)4.90sResponse Time (total)4.90sA test is fully passed only if every run passed for that test.…
4.90sResponse Time (avg)…
879Total Input Tokens…
116Output Tokens…
2,605Reasoning Tokens…
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging. qwen3.8:latest · Q4_K_M · Ollama 0.32.12 · NVIDIA GeForce RTX 3090.
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)8.45sResponse Time (max)8.45sResponse Time (total)8.45sA 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.Did not follow instructions: 1Response Time (avg)18.42sResponse Time (max)22.75sResponse Time (total)36.84sA test is fully passed only if every run passed for that test.…
18.42sResponse Time (avg)…
1,467Total Input Tokens…
267Output Tokens…
3,850Reasoning Tokens…
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging. qwen3.8:latest · Q4_K_M · Ollama 0.32.12 · NVIDIA GeForce RTX 3090.
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)8.24sResponse Time (max)10.18sResponse Time (total)16.49sA test is fully passed only if every run passed for that test.…
8.4Summarizes 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).…
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.Did not follow instructions: 1Response Time (avg)29.40sResponse Time (max)62.30sResponse Time (total)88.19sA test is fully passed only if every run passed for that test.…
29.40sResponse Time (avg)…
1,848Total Input Tokens…
510Output Tokens…
11,431Reasoning Tokens…
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging. qwen3.8:latest · Q4_K_M · Ollama 0.32.12 · NVIDIA GeForce RTX 3090.
7.6Summarizes 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).…
77.8%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.No answer: 1Response Time (avg)199.90sResponse Time (max)569.33sResponse Time (total)599.69sA 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)8.45sResponse Time (max)8.45sResponse Time (total)8.45sA test is fully passed only if every run passed for that test.…
8.45sResponse Time (avg)…
12,354Total Input Tokens…
365Output Tokens…
1,162Reasoning Tokens…
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging. qwen3.8:latest · Q4_K_M · Ollama 0.32.12 · NVIDIA GeForce RTX 3090.
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)5.62sResponse Time (max)5.62sResponse Time (total)5.62sA 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)29.87sResponse Time (max)29.87sResponse Time (total)29.87sA test is fully passed only if every run passed for that test.…
29.87sResponse Time (avg)…
584Total Input Tokens…
203Output Tokens…
4,687Reasoning Tokens…
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging. qwen3.8:latest · Q4_K_M · Ollama 0.32.12 · NVIDIA GeForce RTX 3090.
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)263.98sResponse Time (max)263.98sResponse Time (total)263.98sA test is fully passed only if every run passed for that test.…