Mammoth 1 (default) vs GPT-6 Luna Decisions (default)
GPT-6 Luna Decisions (default) leads on average score with 2.4 vs 2.2. Mammoth 1 (default) has the lower benchmark cost at $0.000 vs $0.005. GPT-6 Luna Decisions (default) is faster at 495ms vs 1.80s, with pass rates of 18.8% vs 13.0%.
Last updated at:
2026-10-24
Compared models
Rank
#442
Total Output Tokens
54
Response Time (avg)
1.80s
Total Cost
$0.000
Rank
#439
Total Output Tokens
0
Response Time (avg)
495ms
Total Cost
$0.005
Recommended modelGPT-6 Luna Decisions (default)
It has the best score here (2.4), while responding about 3.6x faster than Mammoth 1 (default).
Detailed comparison
Metric
Mammoth 1Mammoth 1default36/69 attempts. Choices supplied by adapters. Supports 12/23 tests. Other tests are unsupported, not failed. Score uses the full suite.Release: 2026-10-24Free Available
GPT-6 Luna DecisionsGPT-6 Luna Decisionsdefault36/69 attempts. Choices supplied by adapters. Supports 12/23 tests. Other tests are unsupported, not failed. Score uses the full suite.Release: 2026-10-07
Metric
Mammoth 1Mammoth 1default36/69 attempts. Choices supplied by adapters. Supports 12/23 tests. Other tests are unsupported, not failed. Score uses the full suite.Release: 2026-10-24Free Available
GPT-6 Luna DecisionsGPT-6 Luna Decisionsdefault36/69 attempts. Choices supplied by adapters. Supports 12/23 tests. Other tests are unsupported, not failed. Score uses the full suite.Release: 2026-10-07
Score
2.2Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
2.4Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
Rank
#442
#439
Reliability
8.9First-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
4.2Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
5.2Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
Attempts
36/69
36/69
Tests Correct
A test is fully passed only if every run passed for that test.Wrong answer: 6API error: 2Did not follow instructions: 1Response Time (avg)1.80sResponse Time (max)8.17sResponse Time (total)21.63sA 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: 8Did not follow instructions: 1Response Time (avg)495msResponse Time (max)842msResponse Time (total)5.94sA test is fully passed only if every run passed for that test.…
Attempt pass rate
18.8%Attempt pass rate = passed attempts / total attempts across runs.…
13.0%Attempt pass rate = passed attempts / total attempts across runs.…
Flaky tests
3Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
0Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
Total Runs
36Total Runs…
36Total Runs…
Cost per result
0.000
0.159
Total Cost
$0.000
$0.005
Input Price
$0.000 / 1MInput Price…
$0.100 / 1MInput Price…
Output Price
$0.000 / 1MOutput Price…
$0.000 / 1MOutput Price…
Cache Read Price
N/ACache Read Price…
$0.000 / 1MCache Read Price…
Cache Write Price
N/ACache Write Price…
$0.000 / 1MCache Write Price…
Total Input Tokens
45,468Total Input Tokens…
47,583Total Input Tokens…
Output Tokens
54Output Tokens…
0Output Tokens…
Reasoning Tokens
0Reasoning Tokens…
0Reasoning Tokens…
Response Time (avg)
1.80sResponse Time (avg)…
495msResponse Time (avg)…
Response Time (max)
8.17sResponse Time (max)…
842msResponse Time (max)…
Response Time (total)
21.63sResponse Time (total)…
5.94sResponse Time (total)…
Parameters
27B
~400B total (~17B active)
Availability
Open source
Closed
Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.
0.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
0.0Consistency 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 failed answers.Response Time (avg)0msResponse Time (max)0msResponse Time (total)0msA test is fully passed only if every run passed for that test.…
0.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
0.0Consistency 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 failed answers.Response Time (avg)0msResponse Time (max)0msResponse Time (total)0msA 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.…
7.5Consistency 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.Wrong answer: 2Response Time (avg)530msResponse Time (max)662msResponse Time (total)1.59sA test is fully passed only if every run passed for that test.…
2.3Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
7.5Consistency 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)436msResponse Time (max)476msResponse Time (total)1.31sA test is fully passed only if every run passed for that test.…
4.9Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
6.7Consistency 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: 1Response Time (avg)951msResponse Time (max)1.17sResponse Time (total)1.90sA test is fully passed only if every run passed for that test.…
2.5Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
6.7Consistency 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)447msResponse Time (max)454msResponse Time (total)894msA test is fully passed only if every run passed for that test.…
0.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
0.0Consistency 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 failed answers.Response Time (avg)0msResponse Time (max)0msResponse Time (total)0msA test is fully passed only if every run passed for that test.…
0.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
0.0Consistency 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 failed answers.Response Time (avg)0msResponse Time (max)0msResponse Time (total)0msA test is fully passed only if every run passed for that test.…
3.7Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
1.7Consistency 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: 2Response Time (avg)6.10sResponse Time (max)8.17sResponse Time (total)12.20sA 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)411msResponse Time (max)431msResponse Time (total)822msA 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)531msResponse Time (max)714msResponse Time (total)1.59sA 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)554msResponse Time (max)683msResponse Time (total)1.66sA test is fully passed only if every run passed for that test.…
0.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
0.0Consistency 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 failed answers.Response Time (avg)0msResponse Time (max)0msResponse Time (total)0msA test is fully passed only if every run passed for that test.…
0.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
0.0Consistency 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 failed answers.Response Time (avg)0msResponse Time (max)0msResponse Time (total)0msA test is fully passed only if every run passed for that test.…
1.5Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
5.0Consistency 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)4.04sResponse Time (max)4.04sResponse Time (total)4.04sA test is fully passed only if every run passed for that test.…
1.5Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
5.0Consistency 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)842msResponse Time (max)842msResponse Time (total)842msA test is fully passed only if every run passed for that test.…
1.6Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
1.0Consistency 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.Did not follow instructions: 1Response Time (avg)298msResponse Time (max)298msResponse Time (total)298msA test is fully passed only if every run passed for that test.…
1.7Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
3.3Consistency 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)414msResponse Time (max)414msResponse Time (total)414msA test is fully passed only if every run passed for that test.…
0.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
0.0Consistency 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 failed answers.Response Time (avg)0msResponse Time (max)0msResponse Time (total)0msA test is fully passed only if every run passed for that test.…
0.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
0.0Consistency 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 failed answers.Response Time (avg)0msResponse Time (max)0msResponse Time (total)0msA test is fully passed only if every run passed for that test.…
0.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
0.0Consistency 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 failed answers.Response Time (avg)0msResponse Time (max)0msResponse Time (total)0msA test is fully passed only if every run passed for that test.…
0.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
0.0Consistency 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 failed answers.Response Time (avg)0msResponse Time (max)0msResponse Time (total)0msA test is fully passed only if every run passed for that test.…