Claude Sonnet 5.5 (medium) leads on average score with 5.7 vs 5.7. GLM 5.1 has the lower benchmark cost at $0.164 vs $0.672. Claude Sonnet 5.5 (medium) is faster at 6.07s vs 6.74s, with pass rates of 37.9% vs 45.5%.
Last updated at:
2026-09-29
Compared models
Rank
#266
Total Output Tokens
32,980
Response Time (avg)
6.07s
Total Cost
$0.672
Rank
#271
Total Output Tokens
14,393
Response Time (avg)
6.74s
Total Cost
$0.164
Recommended modelGLM 5.1
Its score stays close to the best score here (5.7 vs 5.7), while costing about 4.1x less than Claude Sonnet 5.5 (medium).
A test is fully passed only if every run passed for that test.Wrong answer: 12Invalid tool call: 1No answer: 1Response Time (avg)6.74sResponse Time (max)61.20sResponse Time (total)148.20sA test is fully passed only if every run passed for that test.…
Attempt pass rate
37.9%Attempt pass rate = passed attempts / total attempts across runs.…
45.5%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
8.392
2.073
Total Cost
$0.672
$0.164
Input Price
$2.000 / 1MInput Price…
$0.965 / 1MInput Price…
Output Price
$10.000 / 1MOutput Price…
$3.032 / 1MOutput Price…
Total Input Tokens
170,771Total Input Tokens…
124,219Total Input Tokens…
Output Tokens
23,185Output Tokens…
14,393Output Tokens…
Reasoning Tokens
9,795Reasoning Tokens…
0Reasoning Tokens…
Response Time (avg)
6.07sResponse Time (avg)…
6.74sResponse Time (avg)…
Response Time (max)
26.16sResponse Time (max)…
61.20sResponse Time (max)…
Response Time (total)
133.62sResponse Time (total)…
148.20sResponse Time (total)…
Parameters
~1T total (~100B active)
744B total (40B active)
Availability
Closed
Open source
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#266 Claude Sonnet 5.5
medium
Cost
$0.024
Time
17.4s
Tokens
2,525 tok
#271 GLM 5.1
none
Reached the allocated time limit (300 seconds) without receiving showcase output.
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.Extra formatting: 2Response Time (avg)2.54sResponse Time (max)4.30sResponse Time (total)10.16sA 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.…
6.3Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
25.0%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.Wrong answer: 4Response Time (avg)2.11sResponse Time (max)3.94sResponse Time (total)8.46sA test is fully passed only if every run passed for that test.…
3.4Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
9.7Consistency 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.Did not follow instructions: 2Extra formatting: 1Response Time (avg)6.07sResponse Time (max)7.23sResponse Time (total)18.20sA test is fully passed only if every run passed for that test.…
3.9Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
9.7Consistency 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: 3Response Time (avg)4.96sResponse Time (max)9.79sResponse Time (total)14.89sA 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.…
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.Invalid tool call: 1Response Time (avg)23.58sResponse Time (max)26.16sResponse Time (total)47.16sA 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.…
1.8Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
33.3%Attempt pass rate = passed attempts / total attempts across runs.…
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: 1No answer: 1Response Time (avg)46.88sResponse Time (max)61.20sResponse Time (total)93.77sA 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.Extra formatting: 1Response Time (avg)2.56sResponse Time (max)2.88sResponse Time (total)5.13sA 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)1.08sResponse Time (max)1.62sResponse Time (total)2.15sA 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)8.78sResponse Time (max)11.55sResponse Time (total)26.33sA 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)2.27sResponse Time (max)3.99sResponse Time (total)6.80sA 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.…
3.4Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
33.3%Attempt pass rate = passed attempts / total attempts across runs.…
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)2.27sResponse Time (max)2.27sResponse Time (total)2.27sA 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)790msResponse Time (max)790msResponse Time (total)790msA 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.…
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.Extra formatting: 1Response Time (avg)1.88sResponse Time (max)2.03sResponse Time (total)3.76sA 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)1.98sResponse Time (max)2.28sResponse Time (total)3.97sA 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)2.43sResponse Time (max)2.70sResponse Time (total)7.29sA 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)1.45sResponse Time (max)2.09sResponse 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)4.75sResponse Time (max)4.75sResponse Time (total)4.75sA 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)10.68sResponse Time (max)10.68sResponse Time (total)10.68sA 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: 1Response Time (avg)8.57sResponse Time (max)8.57sResponse Time (total)8.57sA 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)2.34sResponse Time (max)2.34sResponse Time (total)2.34sA test is fully passed only if every run passed for that test.…