The average score is effectively tied at 7.9 vs 7.9. Local hardware cost was not measured, so cost comparisons are unavailable. GPT-5.2 Chat is faster at 7.73s vs 39.11s, with pass rates of 69.7% vs 68.2%.
Last updated at:
2026-08-15
Rank
#59
Total Output Tokens
29,742
Response Time (avg)
7.73s
Total Cost
$0.594
Rank
#61
Total Output Tokens
169,329
Response Time (avg)
39.11s
Total Cost
N/A
Recommended modelGPT-5.2 Chat
It has the best score here (7.9), while responding about 5.1x faster than Qwen3.8 27B (low).
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.…
Attempt pass rate
69.7%Attempt pass rate = passed attempts / total attempts across runs.…
68.2%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
66Total Runs…
66Total Runs…
Cost per result
4.564Shows 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
$0.594Total Cost (Current Price)…
N/ATotal Cost (Current Price)…
Input Price
$1.750 / 1MInput Price…
N/AInput Price…
Output Price
$14.000 / 1MOutput Price…
N/AOutput Price…
Total Input Tokens
101,104Total Input Tokens…
99,705Total Input Tokens…
Output Tokens
29,742Output Tokens…
1,545Output Tokens…
Reasoning Tokens
0Reasoning Tokens…
167,784Reasoning Tokens…
Response Time (avg)
7.73sResponse Time (avg)…
39.11sResponse Time (avg)…
Response Time (max)
38.52sResponse Time (max)…
376.04sResponse Time (max)…
Response Time (total)
162.40sResponse Time (total)…
860.51sResponse Time (total)…
Parameters
~400B total (~17B 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.
#59 GPT-5.2 Chat
none
Cost
$0.010
Time
15.3s
Tokens
797 tok
#61 Qwen3.8 27B
lowCandidate responses were generated on local hardware. OpenRouter was used only for judging.
8.7Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
7.9Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
91.7%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)3.40sResponse Time (max)4.78sResponse Time (total)13.59sA test is fully passed only if every run passed for that test.…
3.40sResponse Time (avg)…
606Total Input Tokens…
1,807Output Tokens…
0Reasoning 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.…
8.8Summarizes 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)9.82sResponse Time (max)13.35sResponse Time (total)29.45sA test is fully passed only if every run passed for that test.…
9.82sResponse Time (avg)…
7,305Total Input Tokens…
6,731Output Tokens…
0Reasoning 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.…
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)13.91sResponse Time (max)18.70sResponse Time (total)27.82sA test is fully passed only if every run passed for that test.…
13.91sResponse Time (avg)…
78,055Total Input Tokens…
7,923Output Tokens…
0Reasoning 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.…
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)3.05sResponse Time (max)3.33sResponse Time (total)6.10sA test is fully passed only if every run passed for that test.…
3.05sResponse Time (avg)…
7,140Total Input Tokens…
980Output Tokens…
0Reasoning 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.…
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: 2API error: 1Response Time (avg)23.67sResponse Time (max)38.52sResponse Time (total)47.34sA test is fully passed only if every run passed for that test.…
23.67sResponse Time (avg)…
579Total Input Tokens…
7,128Output Tokens…
0Reasoning 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.…
4.4Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
3.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
33.3%Attempt pass rate = passed attempts / total attempts across runs.…
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)3.20sResponse Time (max)3.20sResponse Time (total)3.20sA test is fully passed only if every run passed for that test.…
3.20sResponse Time (avg)…
477Total Input Tokens…
335Output Tokens…
0Reasoning 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.…
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)5.51sResponse Time (max)6.55sResponse Time (total)11.02sA test is fully passed only if every run passed for that test.…
5.51sResponse Time (avg)…
660Total Input Tokens…
1,441Output Tokens…
0Reasoning 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.…
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)4.10sResponse Time (max)5.04sResponse Time (total)12.31sA test is fully passed only if every run passed for that test.…
4.10sResponse Time (avg)…
642Total Input Tokens…
1,603Output Tokens…
0Reasoning 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)4.68sResponse Time (max)4.68sResponse Time (total)4.68sA test is fully passed only if every run passed for that test.…
4.68sResponse Time (avg)…
5,445Total Input Tokens…
555Output Tokens…
0Reasoning 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.Wrong answer: 1Response Time (avg)6.89sResponse Time (max)6.89sResponse Time (total)6.89sA test is fully passed only if every run passed for that test.…
6.89sResponse Time (avg)…
195Total Input Tokens…
1,239Output Tokens…
0Reasoning 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.…