GPT-5.6 Luna (low) leads on average score with 6.2 vs 6.1. Gemini 3.1 Flash Lite has the lower benchmark cost at $0.046 vs $0.051. Gemini 3.1 Flash Lite is faster at 1.75s vs 5.20s, with pass rates of 50.0% vs 54.5%.
Last updated at:
2026-08-20
Rank
#173
Total Output Tokens
10,723
Response Time (avg)
1.75s
Total Cost
$0.046
Rank
#167
Total Output Tokens
26,286
Response Time (avg)
5.20s
Total Cost
$0.051
Recommended modelGemini 3.1 Flash Lite
Its score stays close to the best score here (6.1 vs 6.2), while responding about 3.0x faster than GPT-5.6 Luna (low).
6.1Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
6.2Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
Rank
#173
#167
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).…
8.2Consistency 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: 11Did not follow instructions: 1No answer: 1Response Time (avg)1.75sResponse Time (max)16.25sResponse Time (total)38.42sA 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: 10Did not follow instructions: 1Invalid tool call: 1Response Time (avg)5.20sResponse Time (max)19.44sResponse Time (total)114.46sA test is fully passed only if every run passed for that test.…
Attempt pass rate
50.0%Attempt pass rate = passed attempts / total attempts across runs.…
54.5%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
0.507
2.437
Total Cost
$0.046
$0.051
Input Price
$0.250 / 1MInput Price…
$0.200 / 1MInput Price…
Output Price
$1.500 / 1MOutput Price…
$1.200 / 1MOutput Price…
Total Input Tokens
118,059Total Input Tokens…
96,355Total Input Tokens…
Output Tokens
10,723Output Tokens…
8,213Output Tokens…
Reasoning Tokens
0Reasoning Tokens…
18,073Reasoning Tokens…
Response Time (avg)
1.75sResponse Time (avg)…
5.20sResponse Time (avg)…
Response Time (max)
16.25sResponse Time (max)…
19.44sResponse Time (max)…
Response Time (total)
38.42sResponse Time (total)…
114.46sResponse Time (total)…
Parameters
~150B total (~10B 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.
7.5Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
8.4Consistency 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: 2Response Time (avg)1.07sResponse Time (max)1.91sResponse Time (total)4.27sA test is fully passed only if every run passed for that test.…
8.3Summarizes 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).…
75.0%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)2.21sResponse Time (max)2.87sResponse Time (total)8.84sA 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)938msResponse Time (max)1.59sResponse Time (total)2.81sA 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)4.61sResponse Time (max)5.18sResponse Time (total)13.83sA 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)9.49sResponse Time (max)16.25sResponse Time (total)18.98sA test is fully passed only if every run passed for that test.…
2.8Summarizes 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).…
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.Invalid tool call: 1Wrong answer: 1Response Time (avg)13.71sResponse Time (max)19.44sResponse Time (total)27.43sA 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)843msResponse Time (max)907msResponse Time (total)1.69sA 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)2.14sResponse Time (max)2.49sResponse Time (total)4.28sA 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)701msResponse Time (max)814msResponse Time (total)2.10sA 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)11.24sResponse Time (max)18.06sResponse Time (total)33.71sA test is fully passed only if every run passed for that test.…
4.0Summarizes 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)992msResponse Time (max)992msResponse Time (total)992msA 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)2.25sResponse Time (max)2.25sResponse Time (total)2.25sA 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)859msResponse Time (max)975msResponse Time (total)1.72sA test is fully passed only if every run passed for that test.…
8.5Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
6.8Consistency 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.Did not follow instructions: 1Response Time (avg)2.04sResponse Time (max)2.18sResponse Time (total)4.07sA 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.…
4.8Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
66.7%Attempt pass rate = passed attempts / total attempts across runs.…
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.Did not follow instructions: 1Wrong answer: 1Response Time (avg)720msResponse Time (max)826msResponse Time (total)2.16sA test is fully passed only if every run passed for that test.…
7.6Summarizes 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).…
77.8%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)3.59sResponse Time (max)4.55sResponse Time (total)10.77sA 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)2.97sResponse Time (max)2.97sResponse Time (total)2.97sA 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)4.43sResponse Time (max)4.43sResponse Time (total)4.43sA 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)733msResponse Time (max)733msResponse Time (total)733msA 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)4.86sResponse Time (max)4.86sResponse Time (total)4.86sA test is fully passed only if every run passed for that test.…