GPT-5.4 leads on average score with 5.8 vs 5.6. KAT-Coder-Air V2.5 (high) has the lower benchmark cost at $0.077 vs $0.397. GPT-5.4 is faster at 2.08s vs 15.87s, with pass rates of 42.4% vs 34.9%.
Last updated at:
2026-09-10
Compared models
Rank
#234
Total Output Tokens
114,654
Response Time (avg)
15.87s
Total Cost
$0.077
Rank
#223
Total Output Tokens
8,339
Response Time (avg)
2.08s
Total Cost
$0.397
Recommended modelGPT-5.4
It has the best score here (5.8), while responding about 7.6x faster than KAT-Coder-Air V2.5 (high).
5.6Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
5.8Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
Rank
#234
#223
Reliability
9.8First-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
8.1Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
9.2Consistency 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: 9API error: 3Extra formatting: 3Response Time (avg)15.87sResponse Time (max)118.35sResponse Time (total)349.16sA 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: 14Did not follow instructions: 1Response Time (avg)2.08sResponse Time (max)15.63sResponse Time (total)45.75sA test is fully passed only if every run passed for that test.…
Attempt pass rate
42.4%Attempt pass rate = passed attempts / total attempts across runs.…
34.9%Attempt pass rate = passed attempts / total attempts across runs.…
Flaky tests
5Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
2Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
Total Runs
66Total Runs…
66Total Runs…
Cost per result
1.091
5.667
Total Cost
$0.077
$0.397
Input Price
$0.150 / 1MInput Price…
$2.500 / 1MInput Price…
Output Price
$0.600 / 1MOutput Price…
$15.000 / 1MOutput Price…
Total Input Tokens
50,423Total Input Tokens…
108,641Total Input Tokens…
Output Tokens
4,144Output Tokens…
8,339Output Tokens…
Reasoning Tokens
110,510Reasoning Tokens…
0Reasoning Tokens…
Response Time (avg)
15.87sResponse Time (avg)…
2.08sResponse Time (avg)…
Response Time (max)
118.35sResponse Time (max)…
15.63sResponse Time (max)…
Response Time (total)
349.16sResponse Time (total)…
45.75sResponse Time (total)…
Parameters
~35B total (~3B active)
~1.5T total (~100B active)
Availability
Closed
Closed
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#234 KAT-Coder-Air V2.5
high
Reached the allocated time limit (300 seconds) without receiving showcase output.
6.9Summarizes 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).…
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.API error: 1Wrong answer: 1Response Time (avg)2.49sResponse Time (max)3.97sResponse Time (total)9.97sA 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.…
8.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
8.3%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: 4Response Time (avg)1.21sResponse Time (max)2.58sResponse Time (total)4.85sA test is fully passed only if every run passed for that test.…
4.3Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
7.3Consistency 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.API error: 1Extra formatting: 1Wrong answer: 1Response Time (avg)39.07sResponse Time (max)104.98sResponse Time (total)117.21sA 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)1.62sResponse Time (max)2.95sResponse Time (total)4.85sA 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.API error: 1Response Time (avg)74.48sResponse Time (max)118.35sResponse Time (total)148.95sA 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: 2Response Time (avg)9.26sResponse Time (max)15.63sResponse Time (total)18.52sA 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)3.59sResponse Time (max)4.92sResponse Time (total)7.18sA 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)1.04sResponse Time (max)1.06sResponse Time (total)2.08sA 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.Extra formatting: 2Wrong answer: 1Response Time (avg)7.28sResponse Time (max)8.71sResponse Time (total)21.85sA 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)1.15sResponse Time (max)1.54sResponse Time (total)3.46sA 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.…
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)7.10sResponse Time (max)7.10sResponse Time (total)7.10sA test is fully passed only if every run passed for that test.…
4.4Summarizes 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.Wrong answer: 1Response Time (avg)1.78sResponse Time (max)1.78sResponse Time (total)1.78sA 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)1.51sResponse Time (max)1.91sResponse Time (total)3.01sA 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)1.07sResponse Time (max)1.17sResponse Time (total)2.15sA 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.…
4.4Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
33.3%Attempt pass rate = passed attempts / total attempts across runs.…
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)2.47sResponse Time (max)2.86sResponse Time (total)7.40sA 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)1.44sResponse Time (max)1.82sResponse Time (total)4.33sA 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)4.77sResponse Time (max)4.77sResponse Time (total)4.77sA 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)2.75sResponse Time (max)2.75sResponse Time (total)2.75sA 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)21.72sResponse Time (max)21.72sResponse Time (total)21.72sA 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)990msResponse Time (max)990msResponse Time (total)990msA test is fully passed only if every run passed for that test.…