Inkling (medium) leads on average score with 8.0 vs 7.9. Qwen3.8 27B (low) has the lower benchmark cost at ~$0.071 vs $0.383. Inkling (medium) is faster at 15.66s vs 39.11s, with pass rates of 68.2% vs 75.8%.
Last updated at:
2026-09-28
Compared models
Candidate responses were generated on local hardware. OpenRouter was used only for judging.
Rank
#93
Total Output Tokens
169,329
Response Time (avg)
39.11s
Total Cost
~$0.071Estimated GPU electricity cost only. It excludes the rest of the computer and hardware ownership. NVIDIA GeForce RTX 3090: 0.7171 h × 0.300 kW × €0.2896/kWh × 1.138 USD/EUR = ~$0.070898.
Rank
#87
Total Output Tokens
63,842
Response Time (avg)
15.66s
Total Cost
$0.383
Recommended modelQwen3.8 27B (low)
Its score stays close to the best score here (7.9 vs 8.0), while costing about 5.4x less than Inkling (medium).
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.…
8.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
Rank
#93
#87
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).…
8.5Consistency 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.…
A test is fully passed only if every run passed for that test.Wrong answer: 4API error: 1Invalid tool call: 1No answer: 1Response Time (avg)15.66sResponse Time (max)85.12sResponse Time (total)344.52sA test is fully passed only if every run passed for that test.…
Attempt pass rate
68.2%Attempt pass rate = passed attempts / total attempts across runs.…
75.8%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).…
4Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
Total Runs
66Total Runs…
66Total Runs…
Cost per result
~0.473Estimated GPU electricity cost only. It excludes the rest of the computer and hardware ownership. NVIDIA GeForce RTX 3090: 0.7171 h × 0.300 kW × €0.2896/kWh × 1.138 USD/EUR = ~$0.070898.
2.551
Total Cost
~$0.071Estimated GPU electricity cost only. It excludes the rest of the computer and hardware ownership. NVIDIA GeForce RTX 3090: 0.7171 h × 0.300 kW × €0.2896/kWh × 1.138 USD/EUR = ~$0.070898.
$0.383
Input Price
N/AInput Price…
$1.000 / 1MInput Price…
Output Price
N/AOutput Price…
$4.050 / 1MOutput Price…
Total Input Tokens
99,705Total Input Tokens…
124,062Total Input Tokens…
Output Tokens
1,545Output Tokens…
12,190Output Tokens…
Reasoning Tokens
167,784Reasoning Tokens…
51,652Reasoning Tokens…
Response Time (avg)
39.11sResponse Time (avg)…
15.66sResponse Time (avg)…
Response Time (max)
376.04sResponse Time (max)…
85.12sResponse Time (max)…
Response Time (total)
860.51sResponse Time (total)…
344.52sResponse Time (total)…
Parameters
27.3B
975B total (41B 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.
#93 Qwen3.8 27B
lowCandidate responses were generated on local hardware. OpenRouter was used only for judging.
Cost
~$0.003Estimated GPU electricity cost only. It excludes the rest of the computer and hardware ownership. NVIDIA GeForce RTX 3090: 0.0258 h × 0.300 kW × €0.2896/kWh × 1.138 USD/EUR = ~$0.002549.
Time
92.8s
Tokens
6,902 tok
#87 Thinking Machines: Inkling
medium
Cost
$0.004
Time
11.2s
Tokens
852 tok
Rank
-
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.…
9.5Consistency 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.API error: 1Response Time (avg)6.49sResponse Time (max)15.22sResponse Time (total)25.95sA test is fully passed only if every run passed for that test.…
6.49sResponse Time (avg)…
645Total Input Tokens…
333Output Tokens…
3,091Reasoning 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.…
8.4Summarizes 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).…
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.Wrong answer: 1Response Time (avg)25.20sResponse Time (max)46.41sResponse Time (total)75.61sA test is fully passed only if every run passed for that test.…
25.20sResponse Time (avg)…
7,374Total Input Tokens…
525Output Tokens…
14,457Reasoning 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.No answer: 1Response Time (avg)41.15sResponse Time (max)74.33sResponse Time (total)82.31sA test is fully passed only if every run passed for that test.…
41.15sResponse Time (avg)…
98,542Total Input Tokens…
10,088Output Tokens…
4,626Reasoning 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)3.60sResponse Time (max)3.75sResponse Time (total)7.20sA test is fully passed only if every run passed for that test.…
3.60sResponse Time (avg)…
7,068Total Input Tokens…
216Output Tokens…
813Reasoning 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.…
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)31.59sResponse Time (max)85.12sResponse Time (total)94.77sA test is fully passed only if every run passed for that test.…
31.59sResponse Time (avg)…
804Total Input Tokens…
69Output Tokens…
18,378Reasoning 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.…
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)4.65sResponse Time (max)4.65sResponse Time (total)4.65sA test is fully passed only if every run passed for that test.…
4.65sResponse Time (avg)…
501Total Input Tokens…
170Output Tokens…
699Reasoning 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)6.17sResponse Time (max)7.52sResponse Time (total)12.34sA test is fully passed only if every run passed for that test.…
6.17sResponse Time (avg)…
708Total Input Tokens…
93Output Tokens…
1,886Reasoning 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.…
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)5.18sResponse Time (max)8.14sResponse Time (total)15.53sA test is fully passed only if every run passed for that test.…
5.18sResponse Time (avg)…
714Total Input Tokens…
370Output Tokens…
2,310Reasoning 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.…
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: 1Response Time (avg)4.48sResponse Time (max)4.48sResponse Time (total)4.48sA test is fully passed only if every run passed for that test.…
4.48sResponse Time (avg)…
7,487Total Input Tokens…
296Output Tokens…
298Reasoning 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.…
2.8Summarizes 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).…
33.3%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.Wrong answer: 1Response Time (avg)21.69sResponse Time (max)21.69sResponse Time (total)21.69sA test is fully passed only if every run passed for that test.…