Qwen3.8 2.4T A95B (low) leads on average score with 8.2 vs 8.1. GPT-5 Mini (medium) has the lower benchmark cost at $0.237 vs $3.113. GPT-5 Mini (medium) is faster at 27.63s vs 132.39s, with pass rates of 63.6% vs 78.8%.
Last updated at:
2026-08-12
Rank
#47
Total Output Tokens
105,932
Response Time (avg)
27.63s
Total Cost
$0.237
Rank
#46
Total Output Tokens
554,485
Response Time (avg)
132.39s
Total Cost
$3.113
Recommended modelGPT-5 Mini (medium)
Its score stays close to the best score here (8.1 vs 8.2), while costing about 13.2x less than Qwen3.8 2.4T A95B (low).
A test is fully passed only if every run passed for that test.Wrong answer: 3No answer: 2Invalid tool call: 1Response Time (avg)132.39sResponse Time (max)534.21sResponse Time (total)2912.56sA test is fully passed only if every run passed for that test.…
Attempt pass rate
63.6%Attempt pass rate = passed attempts / total attempts across runs.…
78.8%Attempt pass rate = passed attempts / total attempts across runs.…
Flaky tests
3Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
3Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
Total Runs
66Total Runs…
66Total Runs…
Cost per result
1.971Shows the average cost per correct benchmark answer in cents (lower is better).…
19.453Shows the average cost per correct benchmark answer in cents (lower is better).…
Total Cost
$0.237Total Cost (Current Price)…
$3.113Total Cost (Current Price)…
Input Price
$0.250 / 1MInput Price…
$2.000 / 1MInput Price…
Output Price
$2.000 / 1MOutput Price…
$6.000 / 1MOutput Price…
Total Input Tokens
98,374Total Input Tokens…
113,340Total Input Tokens…
Output Tokens
14,434Output Tokens…
107,311Output Tokens…
Reasoning Tokens
91,498Reasoning Tokens…
447,174Reasoning Tokens…
Response Time (avg)
27.63sResponse Time (avg)…
132.39sResponse Time (avg)…
Response Time (max)
111.48sResponse Time (max)…
534.21sResponse Time (max)…
Response Time (total)
607.92sResponse Time (total)…
2912.56sResponse Time (total)…
Parameters
~400B total (~17B active)
2.4T total (95B active)
Availability
Closed
Weights available
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
7.1Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
7.6Consistency 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: 1Wrong answer: 1Response Time (avg)13.86sResponse Time (max)26.00sResponse Time (total)55.45sA 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)22.04sResponse Time (max)42.15sResponse Time (total)88.14sA 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)27.63sResponse Time (max)38.31sResponse Time (total)82.89sA 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.No answer: 1Response Time (avg)172.53sResponse Time (max)384.94sResponse Time (total)517.59sA 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)99.82sResponse Time (max)111.48sResponse Time (total)199.63sA 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.…
6.9Consistency 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)231.85sResponse Time (max)331.16sResponse Time (total)463.69sA 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)12.58sResponse Time (max)13.87sResponse Time (total)25.16sA 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)22.27sResponse Time (max)37.21sResponse Time (total)44.54sA test is fully passed only if every run passed for that test.…
3.6Summarizes 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).…
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: 2Timed out: 1Response Time (avg)44.63sResponse Time (max)82.55sResponse Time (total)133.89sA 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.…
9.3Consistency 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)386.04sResponse Time (max)534.21sResponse Time (total)1158.11sA test is fully passed only if every run passed for that test.…
4.5Summarizes 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).…
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)13.50sResponse Time (max)13.50sResponse Time (total)13.50sA test is fully passed only if every run passed for that test.…
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.Wrong answer: 1Response Time (avg)22.97sResponse Time (max)22.97sResponse Time (total)22.97sA 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)11.59sResponse Time (max)13.66sResponse Time (total)23.18sA 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)19.54sResponse Time (max)28.63sResponse Time (total)39.07sA test is fully passed only if every run passed for that test.…
5.6Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
9.8Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
33.3%Attempt pass rate = passed attempts / total attempts across runs.…
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: 1Wrong answer: 1Response Time (avg)15.20sResponse Time (max)18.90sResponse Time (total)45.59sA 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)43.37sResponse Time (max)96.64sResponse Time (total)130.12sA 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)18.64sResponse Time (max)18.64sResponse Time (total)18.64sA 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)25.88sResponse Time (max)25.88sResponse Time (total)25.88sA 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)9.99sResponse Time (max)9.99sResponse Time (total)9.99sA 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)422.46sResponse Time (max)422.46sResponse Time (total)422.46sA test is fully passed only if every run passed for that test.…