GPT-5 Nano (medium) leads on average score with 5.7 vs 5.6. Qwen3.5-35B-A3B has the lower benchmark cost at $0.120 vs $0.159. Qwen3.5-35B-A3B is faster at 18.31s vs 56.55s, with pass rates of 53.6% vs 37.7%.
Last updated at:
2026-10-16
Compared models
Rank
#288
Total Output Tokens
307,921
Response Time (avg)
56.55s
Total Cost
$0.159
Rank
#299
Total Output Tokens
135,768
Response Time (avg)
18.31s
Total Cost
$0.120
Recommended modelQwen3.5-35B-A3B
Its score stays close to the best score here (5.6 vs 5.7), while responding about 3.1x faster than GPT-5 Nano (medium).
A test is fully passed only if every run passed for that test.Wrong answer: 14Did not follow instructions: 2Invalid tool call: 1Response Time (avg)18.31sResponse Time (max)209.15sResponse Time (total)421.19sA test is fully passed only if every run passed for that test.…
Attempt pass rate
53.6%Attempt pass rate = passed attempts / total attempts across runs.…
37.7%Attempt pass rate = passed attempts / total attempts across runs.…
Flaky tests
10Flaky 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
69Total Runs…
69Total Runs…
Cost per result
1.737
3.135
Total Cost
$0.159
$0.120
Input Price
$0.050 / 1MInput Price…
$0.080 / 1MInput Price…
Output Price
$0.400 / 1MOutput Price…
$0.750 / 1MOutput Price…
Cache Read Price
$0.005 / 1MCache Read Price…
$0.040 / 1MCache Read Price…
Cache Write Price
N/ACache Write Price…
N/ACache Write Price…
Total Input Tokens
314,436Total Input Tokens…
218,886Total Input Tokens…
Output Tokens
13,578Output Tokens…
135,768Output Tokens…
Reasoning Tokens
294,343Reasoning Tokens…
0Reasoning Tokens…
Response Time (avg)
56.55sResponse Time (avg)…
18.31sResponse Time (avg)…
Response Time (max)
227.89sResponse Time (max)…
209.15sResponse Time (max)…
Response Time (total)
961.32sResponse Time (total)…
421.19sResponse Time (total)…
Parameters
~120B total (~5B active)
35B total (3B active)
Availability
Closed
Open source
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.
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.Wrong answer: 1Response Time (avg)94.09sResponse Time (max)94.09sResponse Time (total)94.09sA test is fully passed only if every run passed for that test.…
3.9Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
9.6Consistency 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)141.22sResponse Time (max)141.22sResponse Time (total)141.22sA test is fully passed only if every run passed for that test.…
6.5Summarizes 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).…
58.3%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: 2Response Time (avg)25.50sResponse Time (max)37.73sResponse Time (total)51.00sA test is fully passed only if every run passed for that test.…
3.4Summarizes 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).…
16.7%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: 4Response Time (avg)1.43sResponse Time (max)4.39sResponse Time (total)5.71sA test is fully passed only if every run passed for that test.…
7.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
7.7Consistency 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)41.62sResponse Time (max)54.86sResponse Time (total)124.86sA test is fully passed only if every run passed for that test.…
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)1.39sResponse Time (max)2.67sResponse Time (total)4.18sA 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.No answer: 1Response Time (avg)146.93sResponse Time (max)227.89sResponse Time (total)293.85sA test is fully passed only if every run passed for that test.…
3.8Summarizes 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).…
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.Invalid tool call: 1Wrong answer: 1Response Time (avg)128.29sResponse Time (max)209.15sResponse Time (total)256.58sA test is fully passed only if every run passed for that test.…
3.7Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
1.7Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
50.0%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.Wrong answer: 2Response Time (avg)21.42sResponse Time (max)21.42sResponse Time (total)21.42sA 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)1.16sResponse Time (max)1.42sResponse Time (total)2.33sA test is fully passed only if every run passed for that test.…
3.4Summarizes 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).…
44.4%Attempt pass rate = passed attempts / total attempts across runs.…
3Flaky 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)124.13sResponse Time (max)204.02sResponse Time (total)248.27sA 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.…
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)507msResponse Time (max)549msResponse Time (total)1.52sA 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)17.51sResponse Time (max)17.51sResponse Time (total)17.51sA test is fully passed only if every run passed for that test.…
6.5Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
3.4Consistency 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.Did not follow instructions: 1Response Time (avg)1.19sResponse Time (max)1.19sResponse Time (total)1.19sA 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)15.64sResponse Time (max)15.64sResponse Time (total)15.64sA test is fully passed only if every run passed for that test.…
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)809msResponse Time (max)983msResponse Time (total)1.62sA 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.Did not follow instructions: 1Wrong answer: 1Response Time (avg)20.63sResponse Time (max)22.94sResponse Time (total)41.26sA test is fully passed only if every run passed for that test.…
3.7Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
7.4Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
22.2%Attempt pass rate = passed attempts / total attempts across runs.…
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: 2Did not follow instructions: 1Response Time (avg)1.35sResponse Time (max)2.26sResponse Time (total)4.05sA 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)33.30sResponse Time (max)33.30sResponse Time (total)33.30sA 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)2.30sResponse Time (max)2.30sResponse Time (total)2.30sA 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)20.13sResponse Time (max)20.13sResponse Time (total)20.13sA 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)493msResponse Time (max)493msResponse Time (total)493msA test is fully passed only if every run passed for that test.…