The average score is effectively tied at 4.8 vs 4.8. GPT-5.4 Nano has the lower benchmark cost at $0.041 vs $0.070. GPT-5.4 Nano is faster at 2.56s vs 12.46s, with pass rates of 36.4% vs 27.3%.
Last updated at:
2026-09-10
Compared models
Rank
#290
Total Output Tokens
97,752
Response Time (avg)
12.46s
Total Cost
$0.070
Rank
#287
Total Output Tokens
13,794
Response Time (avg)
2.56s
Total Cost
$0.041
Recommended modelGPT-5.4 Nano
It has the best score here (4.8), while costing about 1.7x less than KAT-Coder-Air V2.5.
4.8Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
4.8Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
Rank
#290
#287
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
7.2Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
8.6Consistency 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: 13Extra formatting: 3API error: 1Response Time (avg)12.46sResponse Time (max)121.05sResponse Time (total)274.11sA 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: 15Did not follow instructions: 2No answer: 1Response Time (avg)2.56sResponse Time (max)25.50sResponse Time (total)56.37sA test is fully passed only if every run passed for that test.…
Attempt pass rate
36.4%Attempt pass rate = passed attempts / total attempts across runs.…
27.3%Attempt pass rate = passed attempts / total attempts across runs.…
Flaky tests
7Flaky 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
66Total Runs…
66Total Runs…
Cost per result
1.382
1.011
Total Cost
$0.070
$0.041
Input Price
$0.150 / 1MInput Price…
$0.200 / 1MInput Price…
Output Price
$0.600 / 1MOutput Price…
$1.250 / 1MOutput Price…
Total Input Tokens
69,376Total Input Tokens…
115,933Total Input Tokens…
Output Tokens
97,752Output Tokens…
13,794Output Tokens…
Reasoning Tokens
0Reasoning Tokens…
0Reasoning Tokens…
Response Time (avg)
12.46sResponse Time (avg)…
2.56sResponse Time (avg)…
Response Time (max)
121.05sResponse Time (max)…
25.50sResponse Time (max)…
Response Time (total)
274.11sResponse Time (total)…
56.37sResponse Time (total)…
Parameters
~35B total (~3B active)
~120B total (~5B active)
Availability
Closed
Closed
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
5.3Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
5.6Consistency 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: 3Response Time (avg)2.68sResponse Time (max)5.78sResponse Time (total)10.73sA test is fully passed only if every run passed for that test.…
3.5Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
8.0Consistency 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)1.18sResponse Time (max)1.81sResponse Time (total)4.70sA test is fully passed only if every run passed for that test.…
3.3Summarizes 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.Extra formatting: 2Wrong answer: 1Response Time (avg)14.31sResponse Time (max)21.40sResponse Time (total)42.94sA 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.…
7.9Consistency 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: 3Response Time (avg)2.22sResponse Time (max)4.47sResponse Time (total)6.65sA 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.…
1.6Consistency 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.API error: 1Wrong answer: 1Response Time (avg)73.00sResponse Time (max)121.05sResponse Time (total)146.00sA 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: 1Wrong answer: 1Response Time (avg)14.67sResponse Time (max)25.50sResponse Time (total)29.34sA 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.…
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.Extra formatting: 1Response Time (avg)2.66sResponse Time (max)2.69sResponse Time (total)5.33sA 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.…
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)1.11sResponse Time (max)1.25sResponse Time (total)2.23sA 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: 3Response Time (avg)8.33sResponse Time (max)8.97sResponse Time (total)25.00sA 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: 3Response Time (avg)880msResponse Time (max)959msResponse Time (total)2.64sA test is fully passed only if every run passed for that test.…
5.0Summarizes 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)12.02sResponse Time (max)12.02sResponse Time (total)12.02sA 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.…
2.5Consistency 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)1.31sResponse Time (max)1.31sResponse Time (total)1.31sA test is fully passed only if every run passed for that test.…
9.9Summarizes 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)1.75sResponse Time (max)2.06sResponse Time (total)3.50sA 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)784msResponse Time (max)859msResponse Time (total)1.57sA 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.…
4.4Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
22.2%Attempt pass rate = passed attempts / total attempts across runs.…
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: 3Response Time (avg)1.84sResponse Time (max)2.06sResponse Time (total)5.52sA test is fully passed only if every run passed for that test.…
5.4Summarizes 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.Did not follow instructions: 1Wrong answer: 1Response Time (avg)1.25sResponse Time (max)1.53sResponse Time (total)3.76sA 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)5.13sResponse Time (max)5.13sResponse Time (total)5.13sA 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)3.40sResponse Time (max)3.40sResponse Time (total)3.40sA 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)17.96sResponse Time (max)17.96sResponse Time (total)17.96sA 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)773msResponse Time (max)773msResponse Time (total)773msA test is fully passed only if every run passed for that test.…