GPT-5.4 Mini (medium) leads on average score with 7.5 vs 7.3. Claude Sonnet 4.6 has the lower benchmark cost at $0.661 vs $0.786. Claude Sonnet 4.6 is faster at 7.67s vs 26.72s, with pass rates of 57.6% vs 68.2%.
Last updated at:
2026-09-21
Compared models
Rank
#126
Total Output Tokens
19,362
Response Time (avg)
7.67s
Total Cost
$0.661
Rank
#115
Total Output Tokens
158,344
Response Time (avg)
26.72s
Total Cost
$0.786
Recommended modelClaude Sonnet 4.6
Its score stays close to the best score here (7.3 vs 7.5), while responding about 3.5x faster than GPT-5.4 Mini (medium).
7.3Summarizes 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
#126
#115
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
9.7Consistency 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: 5Extra formatting: 4Did not follow instructions: 1Response Time (avg)7.67sResponse Time (max)51.18sResponse Time (total)122.78sA 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: 6Did not follow instructions: 3Invalid tool call: 1Response Time (avg)26.72sResponse Time (max)138.75sResponse Time (total)587.90sA test is fully passed only if every run passed for that test.…
Attempt pass rate
57.6%Attempt pass rate = passed attempts / total attempts across runs.…
68.2%Attempt pass rate = passed attempts / total attempts across runs.…
Flaky tests
1Flaky 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
5.503
6.546
Total Cost
$0.661
$0.786
Input Price
$3.000 / 1MInput Price…
$0.750 / 1MInput Price…
Output Price
$15.000 / 1MOutput Price…
$4.500 / 1MOutput Price…
Total Input Tokens
123,273Total Input Tokens…
97,164Total Input Tokens…
Output Tokens
19,362Output Tokens…
6,211Output Tokens…
Reasoning Tokens
0Reasoning Tokens…
152,133Reasoning Tokens…
Response Time (avg)
7.67sResponse Time (avg)…
26.72sResponse Time (avg)…
Response Time (max)
51.18sResponse Time (max)…
138.75sResponse Time (max)…
Response Time (total)
122.78sResponse Time (total)…
587.90sResponse Time (total)…
Parameters
~1T total (~100B active)
~400B 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.
4.8Summarizes 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).…
25.0%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)2.94sResponse Time (max)4.83sResponse Time (total)5.88sA test is fully passed only if every run passed for that test.…
8.6Summarizes 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).…
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)4.05sResponse Time (max)6.69sResponse Time (total)16.20sA 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.Extra formatting: 1Wrong answer: 1Response Time (avg)5.19sResponse Time (max)9.79sResponse Time (total)15.56sA test is fully passed only if every run passed for that test.…
8.4Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
7.4Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
88.9%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)57.87sResponse Time (max)138.75sResponse Time (total)173.61sA 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)37.51sResponse Time (max)51.18sResponse Time (total)75.03sA 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)59.64sResponse Time (max)101.47sResponse Time (total)119.27sA 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)3.43sResponse Time (max)3.43sResponse Time (total)3.43sA 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)2.43sResponse Time (max)3.39sResponse Time (total)4.87sA test is fully passed only if every run passed for that test.…
7.7Summarizes 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).…
66.7%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)2.27sResponse Time (max)3.54sResponse Time (total)4.54sA 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: 3Response Time (avg)71.05sResponse Time (max)102.91sResponse Time (total)213.16sA 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.Did not follow instructions: 1Response Time (avg)2.56sResponse Time (max)2.56sResponse Time (total)2.56sA 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)3.72sResponse Time (max)3.72sResponse Time (total)3.72sA 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)1.96sResponse Time (max)1.96sResponse Time (total)1.96sA 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)2.13sResponse Time (max)2.45sResponse Time (total)4.25sA test is fully passed only if every run passed for that test.…
7.7Summarizes 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).…
66.7%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: 1Response Time (avg)2.53sResponse Time (max)2.54sResponse Time (total)5.06sA test is fully passed only if every run passed for that test.…
7.8Summarizes 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).…
66.7%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)4.37sResponse Time (max)7.27sResponse Time (total)13.11sA 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)4.11sResponse Time (max)4.11sResponse Time (total)4.11sA 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.Did not follow instructions: 1Response Time (avg)9.62sResponse Time (max)9.62sResponse Time (total)9.62sA 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)4.67sResponse Time (max)4.67sResponse Time (total)4.67sA 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)30.10sResponse Time (max)30.10sResponse Time (total)30.10sA test is fully passed only if every run passed for that test.…