GPT-5.6 Sol (high) leads on average score with 9.4 vs 9.1. Qwen3.8 Max (medium) has the lower benchmark cost at $0.728 vs $1.234. GPT-5.6 Sol (high) is faster at 11.73s vs 21.53s, with pass rates of 89.4% vs 84.9%.
Last updated at:
2026-08-04
Rank
#7
Total Output Tokens
27,899
Response Time (avg)
11.73s
Total Cost
$1.234
Rank
#14
Total Output Tokens
84,826
Response Time (avg)
21.53s
Total Cost
$0.728
Recommended modelGPT-5.6 Sol (high)
It has the best score here (9.4), while responding about 1.8x faster than Qwen3.8 Max (medium).
9.4Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
9.1Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
Rank
#7
#14
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.…
10.0First-attempt success score: 10.0 means no retryable target API or rate-limit failures before successful calls; tracked failures lower the score.…
Consistency
8.9Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
9.7Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
Benchmark coverage
22/22 tests · 66/66 attempts
22/22 tests · 66/66 attempts
Tests Correct
A test is fully passed only if every run passed for that test.Wrong answer: 4Response Time (avg)11.73sResponse Time (max)54.79sResponse Time (total)257.99sA 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.Wrong answer: 3Invalid tool call: 1Response Time (avg)21.53sResponse Time (max)126.60sResponse Time (total)473.75sA test is fully passed only if every run passed for that test.…
Attempt pass rate
89.4%Attempt pass rate = passed attempts / total attempts across runs.…
84.9%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).…
1Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
Total Runs
66Total Runs…
66Total Runs…
Cost per result
6.852Shows the average cost per correct benchmark answer in cents (lower is better).…
4.040Shows the average cost per correct benchmark answer in cents (lower is better).…
Total Cost
$1.234Total Cost (Current Price)…
$0.728Total Cost (Current Price)…
Input Price
$5.000 / 1MInput Price…
$2.000 / 1MInput Price…
Output Price
$30.000 / 1MOutput Price…
$6.000 / 1MOutput Price…
Total Input Tokens
79,249Total Input Tokens…
109,046Total Input Tokens…
Output Tokens
4,855Output Tokens…
6,567Output Tokens…
Reasoning Tokens
23,044Reasoning Tokens…
78,259Reasoning Tokens…
Response Time (avg)
11.73sResponse Time (avg)…
21.53sResponse Time (avg)…
Response Time (max)
54.79sResponse Time (max)…
126.60sResponse Time (max)…
Response Time (total)
257.99sResponse Time (total)…
473.75sResponse Time (total)…
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
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)3.39sResponse Time (max)4.12sResponse Time (total)13.56sA 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)4.17sResponse Time (max)6.30sResponse Time (total)16.69sA 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)12.52sResponse Time (max)21.67sResponse Time (total)37.56sA 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)41.35sResponse Time (max)74.36sResponse Time (total)124.04sA 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)24.99sResponse Time (max)36.30sResponse Time (total)49.98sA test is fully passed only if every run passed for that test.…
8.7Summarizes 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).…
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.Invalid tool call: 1Response Time (avg)91.25sResponse Time (max)126.60sResponse Time (total)182.50sA 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)1.21sResponse Time (total)2.32sA 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)8.72sResponse Time (max)9.59sResponse Time (total)17.44sA 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)39.45sResponse Time (max)54.79sResponse Time (total)118.36sA 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)28.52sResponse Time (max)49.58sResponse Time (total)85.57sA 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)4.40sResponse Time (max)4.40sResponse Time (total)4.40sA 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)6.41sResponse Time (max)6.41sResponse Time (total)6.41sA 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)2.73sResponse Time (max)3.42sResponse Time (total)5.46sA 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)3.49sResponse Time (max)4.45sResponse Time (total)6.98sA 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)4.10sResponse Time (max)4.40sResponse Time (total)12.30sA 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)4.93sResponse Time (max)6.68sResponse Time (total)14.79sA 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)7.08sResponse Time (max)7.08sResponse Time (total)7.08sA 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)7.83sResponse Time (max)7.83sResponse Time (total)7.83sA 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.…
1.6Consistency 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.Wrong answer: 1Response Time (avg)6.97sResponse Time (max)6.97sResponse Time (total)6.97sA 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)11.49sResponse Time (max)11.49sResponse Time (total)11.49sA test is fully passed only if every run passed for that test.…