The average score is effectively tied at 6.4 vs 6.3. Qwen3.6 27B has the lower benchmark cost at $0.148 vs $0.489. ERNIE-Light-DT-1.0 (low) is faster at 8.91s vs 12.71s, with pass rates of 65.2% vs 47.8%.
Last updated at:
2026-11-13
Compared models
Rank
#288
Total Output Tokens
43,895
Response Time (avg)
8.91s
Total Cost
$0.489
Rank
#294
Total Output Tokens
20,816
Response Time (avg)
12.71s
Total Cost
$0.148
Recommended modelQwen3.6 27B
It has the best score here (6.3), while costing about 3.3x less than ERNIE-Light-DT-1.0 (low).
A test is fully passed only if every run passed for that test.Wrong answer: 11Did not follow instructions: 2Invalid tool call: 2Response Time (avg)12.71sResponse Time (max)156.31sResponse Time (total)292.29sA test is fully passed only if every run passed for that test.…
Attempt pass rate
65.2%Attempt pass rate = passed attempts / total attempts across runs.…
47.8%Attempt pass rate = passed attempts / total attempts across runs.…
Flaky tests
9Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
6Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
Total Runs
69Total Runs…
69Total Runs…
Cost per result
4.441
1.874
Total Cost
$0.489
$0.148
Input Price
$1.130 / 1MInput Price…
$0.320 / 1MInput Price…
Output Price
$3.941 / 1MOutput Price…
$3.250 / 1MOutput Price…
Cache Read Price
$0.113 / 1MCache Read Price…
$0.030 / 1MCache Read Price…
Cache Write Price
N/ACache Write Price…
N/ACache Write Price…
Total Input Tokens
279,234Total Input Tokens…
250,919Total Input Tokens…
Output Tokens
13,328Output Tokens…
20,816Output Tokens…
Reasoning Tokens
30,567Reasoning Tokens…
0Reasoning Tokens…
Response Time (avg)
8.91sResponse Time (avg)…
12.71sResponse Time (avg)…
Response Time (max)
96.92sResponse Time (max)…
156.31sResponse Time (max)…
Response Time (total)
204.98sResponse Time (total)…
292.29sResponse Time (total)…
Parameters
~320B total (~18B active)
27B
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.
6.1Summarizes 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).…
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.Invalid tool call: 1Response Time (avg)96.92sResponse Time (max)96.92sResponse Time (total)96.92sA 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)58.61sResponse Time (max)58.61sResponse Time (total)58.61sA test is fully passed only if every run passed for that test.…
7.4Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
6.3Consistency 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.Did not follow instructions: 1Wrong answer: 1Response Time (avg)1.80sResponse Time (max)2.78sResponse Time (total)7.18sA 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.…
3.7Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
41.7%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: 4Response Time (avg)2.83sResponse Time (max)7.62sResponse Time (total)11.33sA test is fully passed only if every run passed for that test.…
5.7Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
4.8Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
55.6%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)5.33sResponse Time (max)7.23sResponse Time (total)15.99sA 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)4.16sResponse Time (max)10.18sResponse Time (total)12.49sA test is fully passed only if every run passed for that test.…
2.9Summarizes 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).…
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.Invalid tool call: 1Wrong answer: 1Response Time (avg)22.98sResponse Time (max)41.13sResponse Time (total)45.96sA test is fully passed only if every run passed for that test.…
3.2Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
9.1Consistency 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: 2Response Time (avg)83.13sResponse Time (max)156.31sResponse Time (total)166.26sA 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)1.60sResponse Time (max)1.69sResponse Time (total)3.19sA 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.Wrong answer: 1Response Time (avg)2.06sResponse Time (max)2.39sResponse Time (total)4.11sA 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)6.65sResponse Time (max)13.72sResponse Time (total)19.96sA 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)2.79sResponse Time (max)4.83sResponse Time (total)8.37sA test is fully passed only if every run passed for that test.…
5.1Summarizes 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).…
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)1.45sResponse Time (max)1.45sResponse Time (total)1.45sA test is fully passed only if every run passed for that test.…
5.2Summarizes 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).…
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)1.07sResponse Time (max)1.07sResponse Time (total)1.07sA 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)1.43sResponse Time (max)1.64sResponse Time (total)2.86sA test is fully passed only if every run passed for that test.…
6.2Summarizes 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.Wrong answer: 1Response Time (avg)1.92sResponse Time (max)1.94sResponse Time (total)3.83sA test is fully passed only if every run passed for that test.…
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.Did not follow instructions: 1Response Time (avg)1.77sResponse Time (max)2.32sResponse Time (total)5.32sA 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)5.15sResponse Time (max)11.82sResponse Time (total)15.45sA 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)4.27sResponse Time (max)4.27sResponse Time (total)4.27sA test is fully passed only if every run passed for that test.…
9.5Summarizes 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).…
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)6.74sResponse Time (max)6.74sResponse Time (total)6.74sA 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)1.89sResponse Time (max)1.89sResponse Time (total)1.89sA 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)4.03sResponse Time (max)4.03sResponse Time (total)4.03sA test is fully passed only if every run passed for that test.…