GPT-5.4 (medium) leads on average score with 8.5 vs 8.4. Local hardware cost was not measured, so cost comparisons are unavailable. GPT-5.4 (medium) is faster at 22.85s vs 167.89s, with pass rates of 77.3% vs 77.3%.
Last updated at:
2026-08-15
Rank
#36
Total Output Tokens
90,466
Response Time (avg)
22.85s
Total Cost
$1.560
Rank
#42
Total Output Tokens
656,635
Response Time (avg)
167.89s
Total Cost
N/A
Recommended modelGPT-5.4 (medium)
It has the best score here (8.5), while responding about 7.3x faster than Qwen3.8 27B (high).
Qwen3.8 27BQwen3.8 27BhighCandidate responses were generated on local hardware. OpenRouter was used only for judging.Release: 2026-08-14
Score
8.5Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
8.4Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
Rank
#36
#42
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.…
9.6First-attempt success score: 10.0 means no retryable target API or rate-limit failures before successful calls; tracked failures lower the score.…
Consistency
8.6Consistency 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).…
Attempts
66/66
66/66
Tests Correct
A test is fully passed only if every run passed for that test.Wrong answer: 5Did not follow instructions: 2Response Time (avg)22.85sResponse Time (max)100.41sResponse Time (total)502.78sA 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.Did not follow instructions: 2No answer: 2Wrong answer: 2Response Time (avg)167.89sResponse Time (max)640.85sResponse Time (total)3693.54sA test is fully passed only if every run passed for that test.…
Attempt pass rate
77.3%Attempt pass rate = passed attempts / total attempts across runs.…
77.3%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).…
2Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
Total Runs
66Total Runs…
66Total Runs…
Cost per result
10.399Shows 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
$1.560Total Cost (Current Price)…
N/ATotal Cost (Current Price)…
Input Price
$2.500 / 1MInput Price…
N/AInput Price…
Output Price
$15.000 / 1MOutput Price…
N/AOutput Price…
Total Input Tokens
81,136Total Input Tokens…
100,179Total Input Tokens…
Output Tokens
6,155Output Tokens…
904Output Tokens…
Reasoning Tokens
84,311Reasoning Tokens…
655,731Reasoning Tokens…
Response Time (avg)
22.85sResponse Time (avg)…
167.89sResponse Time (avg)…
Response Time (max)
100.41sResponse Time (max)…
640.85sResponse Time (max)…
Response Time (total)
502.78sResponse Time (total)…
3693.54sResponse Time (total)…
Parameters
~1.5T total (~100B active)
27.3B
Availability
Closed
Weights available
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#36 GPT-5.4
medium
Cost
$0.214
Time
199.6s
Tokens
14,349 tok
#42 Qwen3.8 27B
highCandidate responses were generated on local hardware. OpenRouter was used only for judging.
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.Wrong answer: 1Response Time (avg)4.11sResponse Time (max)6.42sResponse Time (total)16.42sA test is fully passed only if every run passed for that test.…
4.11sResponse Time (avg)…
606Total Input Tokens…
240Output Tokens…
1,511Reasoning 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)8.10sResponse Time (max)21.48sResponse Time (total)32.40sA 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)44.36sResponse Time (max)96.94sResponse Time (total)133.08sA test is fully passed only if every run passed for that test.…
44.36sResponse Time (avg)…
7,305Total Input Tokens…
433Output Tokens…
24,216Reasoning Tokens…
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging.
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)29.77sResponse Time (max)38.97sResponse Time (total)59.55sA test is fully passed only if every run passed for that test.…
29.77sResponse Time (avg)…
58,038Total Input Tokens…
4,214Output Tokens…
13,351Reasoning 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)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)5.32sResponse Time (max)5.40sResponse Time (total)10.64sA test is fully passed only if every run passed for that test.…
5.32sResponse Time (avg)…
7,140Total Input Tokens…
234Output Tokens…
804Reasoning 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)34.85sResponse Time (max)57.71sResponse Time (total)69.71sA 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)72.44sResponse Time (max)100.41sResponse Time (total)217.32sA test is fully passed only if every run passed for that test.…
72.44sResponse Time (avg)…
628Total Input Tokens…
61Output Tokens…
36,544Reasoning 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.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.…
4.7Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
3.1Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
33.3%Attempt pass rate = passed attempts / total attempts across runs.…
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)4.92sResponse Time (max)4.92sResponse Time (total)4.92sA test is fully passed only if every run passed for that test.…
4.92sResponse Time (avg)…
477Total Input Tokens…
145Output Tokens…
321Reasoning 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)8.45sResponse Time (max)8.45sResponse Time (total)8.45sA 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)3.11sResponse Time (max)3.68sResponse Time (total)6.22sA test is fully passed only if every run passed for that test.…
3.11sResponse Time (avg)…
660Total Input Tokens…
93Output Tokens…
897Reasoning Tokens…
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging.
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.…
8.2Summarizes 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.Did not follow instructions: 1Response Time (avg)9.14sResponse Time (max)18.14sResponse Time (total)27.41sA test is fully passed only if every run passed for that test.…
9.14sResponse Time (avg)…
642Total Input Tokens…
441Output Tokens…
3,815Reasoning Tokens…
Qwen3.8 27BCandidate responses were generated on local hardware. OpenRouter was used only for judging.
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)13.28sResponse Time (max)13.28sResponse Time (total)13.28sA test is fully passed only if every run passed for that test.…
13.28sResponse Time (avg)…
5,445Total Input Tokens…
264Output Tokens…
1,031Reasoning 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)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.Wrong answer: 1Response Time (avg)13.95sResponse Time (max)13.95sResponse Time (total)13.95sA test is fully passed only if every run passed for that test.…
13.95sResponse Time (avg)…
195Total Input Tokens…
30Output Tokens…
1,821Reasoning 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)263.98sResponse Time (max)263.98sResponse Time (total)263.98sA test is fully passed only if every run passed for that test.…