The average score is effectively tied at 7.5 vs 7.5. Qwen3.5 Plus 2026-02-15 (medium) has the lower benchmark cost at $0.459 vs $0.533. GPT 5.3 Chat is faster at 6.56s vs 91.76s, with pass rates of 65.2% vs 72.7%.
Last updated at:
2026-09-10
Compared models
Rank
#105
Total Output Tokens
28,179
Response Time (avg)
6.56s
Total Cost
$0.533
Rank
#106
Total Output Tokens
274,709
Response Time (avg)
91.76s
Total Cost
$0.459
Recommended modelGPT 5.3 Chat
It has the best score here (7.5), while responding about 14.0x faster than Qwen3.5 Plus 2026-02-15 (medium).
7.5Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
7.5Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
Rank
#105
#106
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
8.6Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
8.1Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
Attempts
66/66
66/66
Tests Correct
A test is fully passed only if every run passed for that test.Wrong answer: 6Did not follow instructions: 2API error: 1Response Time (avg)6.56sResponse Time (max)18.33sResponse Time (total)137.77sA 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: 4Timed out: 2API error: 1Invalid tool call: 1Response Time (avg)91.76sResponse Time (max)304.85sResponse Time (total)1376.42sA 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.…
72.7%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).…
5Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
Total Runs
66Total Runs…
66Total Runs…
Cost per result
4.097
3.483
Total Cost
$0.533
$0.459
Input Price
$1.750 / 1MInput Price…
$0.260 / 1MInput Price…
Output Price
$14.000 / 1MOutput Price…
$1.560 / 1MOutput Price…
Total Input Tokens
78,846Total Input Tokens…
113,569Total Input Tokens…
Output Tokens
28,179Output Tokens…
9,823Output Tokens…
Reasoning Tokens
0Reasoning Tokens…
264,886Reasoning Tokens…
Response Time (avg)
6.56sResponse Time (avg)…
91.76sResponse Time (avg)…
Response Time (max)
18.33sResponse Time (max)…
304.85sResponse Time (max)…
Response Time (total)
137.77sResponse Time (total)…
1376.42sResponse Time (total)…
Parameters
~400B total (~17B active)
~397B total (~17B active)
Availability
Closed
Closed
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
6.7Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
8.1Consistency 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.Did not follow instructions: 1Wrong answer: 1Response Time (avg)3.86sResponse Time (max)7.35sResponse Time (total)15.44sA 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.…
7.9Consistency 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.Wrong answer: 1Response Time (avg)45.78sResponse Time (max)81.20sResponse Time (total)91.57sA 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.…
4.7Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
55.6%Attempt pass rate = passed attempts / total attempts across runs.…
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)10.52sResponse Time (max)11.72sResponse Time (total)31.55sA test is fully passed only if every run passed for that test.…
6.6Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
7.1Consistency 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.API error: 1Wrong answer: 1Response Time (avg)180.70sResponse Time (max)266.69sResponse Time (total)542.10sA 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)15.07sResponse Time (max)18.19sResponse Time (total)30.14sA test is fully passed only if every run passed for that test.…
6.9Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
5.9Consistency 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)175.85sResponse Time (max)304.85sResponse Time (total)351.70sA 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)2.21sResponse Time (max)2.52sResponse Time (total)4.42sA 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)46.91sResponse Time (max)46.91sResponse Time (total)46.91sA 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.…
7.2Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
11.1%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: 2API error: 1Response Time (avg)12.75sResponse Time (max)18.33sResponse Time (total)25.50sA 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.Timed out: 1Wrong answer: 1Response Time (avg)55.99sResponse Time (max)55.99sResponse Time (total)55.99sA test is fully passed only if every run passed for that test.…
4.6Summarizes 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)1.99sResponse Time (max)1.99sResponse Time (total)1.99sA 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.Timed out: 1Response Time (avg)79.86sResponse Time (max)79.86sResponse Time (total)79.86sA 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)3.51sResponse Time (max)4.60sResponse Time (total)7.01sA 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)31.93sResponse Time (max)31.93sResponse Time (total)31.93sA 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)2.99sResponse Time (max)3.16sResponse Time (total)8.97sA 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)32.50sResponse Time (max)49.12sResponse Time (total)65.01sA 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)8.36sResponse Time (max)8.36sResponse Time (total)8.36sA 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)7.54sResponse Time (max)7.54sResponse Time (total)7.54sA 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)4.38sResponse Time (max)4.38sResponse Time (total)4.38sA 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)103.81sResponse Time (max)103.81sResponse Time (total)103.81sA test is fully passed only if every run passed for that test.…