DeepSeek V4 Pro leads on average score with 6.9 vs 6.8. DeepSeek V4 Pro has the lower benchmark cost at $0.139 vs $0.300. Gemini 3.5 Flash (minimal) is faster at 2.65s vs 11.55s, with pass rates of 51.5% vs 65.2%.
Last updated at:
2026-08-11
Rank
#110
Total Output Tokens
35,551
Response Time (avg)
11.55s
Total Cost
$0.139
Rank
#117
Total Output Tokens
16,454
Response Time (avg)
2.65s
Total Cost
$0.300
Recommended modelGemini 3.5 Flash (minimal)
Its score stays close to the best score here (6.8 vs 6.9), while responding about 4.4x faster than DeepSeek V4 Pro.
A test is fully passed only if every run passed for that test.Wrong answer: 5Invalid tool call: 2Did not follow instructions: 1Response Time (avg)2.65sResponse Time (max)25.26sResponse Time (total)58.27sA test is fully passed only if every run passed for that test.…
Attempt pass rate
51.5%Attempt pass rate = passed attempts / total attempts across runs.…
65.2%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).…
1Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
Total Runs
66Total Runs…
66Total Runs…
Cost per result
0.954Shows the average cost per correct benchmark answer in cents (lower is better).…
2.138Shows the average cost per correct benchmark answer in cents (lower is better).…
Total Cost
$0.139Total Cost (Current Price)…
$0.300Total Cost (Current Price)…
Input Price
$0.632 / 1MInput Price…
$1.500 / 1MInput Price…
Output Price
$1.264 / 1MOutput Price…
$9.000 / 1MOutput Price…
Total Input Tokens
148,069Total Input Tokens…
100,753Total Input Tokens…
Output Tokens
35,551Output Tokens…
16,454Output Tokens…
Reasoning Tokens
0Reasoning Tokens…
0Reasoning Tokens…
Response Time (avg)
11.55sResponse Time (avg)…
2.65sResponse Time (avg)…
Response Time (max)
119.44sResponse Time (max)…
25.26sResponse Time (max)…
Response Time (total)
254.11sResponse Time (total)…
58.27sResponse Time (total)…
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
3.2Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
6.1Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
16.7%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: 2Extra formatting: 1Did not follow instructions: 1Response Time (avg)4.02sResponse Time (max)5.11sResponse Time (total)16.10sA 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: 2Response Time (avg)892msResponse Time (max)1.38sResponse Time (total)3.57sA 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.…
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)13.38sResponse Time (max)30.09sResponse Time (total)40.15sA 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.…
9.9Consistency 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)2.75sResponse Time (max)5.51sResponse Time (total)8.26sA test is fully passed only if every run passed for that test.…
7.9Summarizes 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).…
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)71.59sResponse Time (max)119.44sResponse Time (total)143.18sA 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.Invalid tool call: 2Response Time (avg)14.41sResponse Time (max)25.26sResponse Time (total)28.81sA 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)4.61sResponse Time (max)6.06sResponse Time (total)9.23sA 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)1.66sResponse Time (max)2.11sResponse Time (total)3.32sA 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)3.72sResponse Time (max)7.90sResponse Time (total)11.17sA 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)899msResponse Time (max)1.04sResponse Time (total)2.70sA 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)2.05sResponse Time (max)2.05sResponse Time (total)2.05sA 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)922msResponse Time (max)922msResponse Time (total)922msA 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.Wrong answer: 1Response Time (avg)4.12sResponse Time (max)4.37sResponse Time (total)8.24sA test is fully passed only if every run passed for that test.…
6.4Summarizes 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.Wrong answer: 1Response Time (avg)893msResponse Time (max)964msResponse Time (total)1.79sA 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)3.61sResponse Time (max)5.19sResponse Time (total)10.83sA 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)1.45sResponse Time (max)2.30sResponse Time (total)4.36sA 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)7.40sResponse Time (max)7.40sResponse Time (total)7.40sA 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)2.79sResponse Time (max)2.79sResponse Time (total)2.79sA 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)5.76sResponse Time (max)5.76sResponse Time (total)5.76sA 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)1.76sResponse Time (max)1.76sResponse Time (total)1.76sA test is fully passed only if every run passed for that test.…