Gemini 3 Flash Preview (low) vs GLM 5V Turbo (medium)
Gemini 3 Flash Preview (low) leads on average score with 7.4 vs 6.7. Gemini 3 Flash Preview (low) has the lower benchmark cost at $0.177 vs $0.457. Gemini 3 Flash Preview (low) is faster at 6.28s vs 23.08s, with pass rates of 75.8% vs 65.2%.
Last updated at:
2026-07-25
⋮⋮
Rank
#69
Total Output Tokens
38,090
Response Time (avg)
6.28s
Total Cost
$0.177
⋮⋮
Rank
#102
Total Output Tokens
100,762
Response Time (avg)
23.08s
Total Cost
$0.457
Recommended modelGemini 3 Flash Preview (low)
It has the best score here (7.4), while costing about 2.6x less than GLM 5V Turbo (medium).
GLM 5V TurboGLM 5V TurbomediumArchived model: this model is no longer updated or tested on new tests.Release: 2026-04-01
Score
7.4Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
6.7Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
Rank
#69
#102
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
9.2Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
7.5Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
Tests Correct
A test is fully passed only if every run passed for that test.Wrong answer: 6Response Time (avg)6.28sResponse Time (max)17.13sResponse Time (total)138.06sA 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: 7Invalid tool call: 2Did not follow instructions: 1Response Time (avg)23.08sResponse Time (max)95.88sResponse Time (total)484.63sA test is fully passed only if every run passed for that test.…
Attempt pass rate
75.8%Attempt pass rate = passed attempts / total attempts across runs.…
65.2%Attempt pass rate = passed attempts / total attempts across runs.…
Flaky tests
2Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
6Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
Total Runs
66Total Runs…
63Total Runs…
Cost per result
1.101Shows the average cost per correct benchmark answer in cents (lower is better).…
4.151Shows the average cost per correct benchmark answer in cents (lower is better).…
Total Cost
$0.177Total Cost (Current Price)…
$0.457Total Cost (Current Price)…
Input Price
$0.500 / 1MInput Price…
$1.200 / 1MInput Price…
Output Price
$3.000 / 1MOutput Price…
$4.000 / 1MOutput Price…
Total Input Tokens
123,684Total Input Tokens…
44,615Total Input Tokens…
Output Tokens
9,572Output Tokens…
2,347Output Tokens…
Reasoning Tokens
28,518Reasoning Tokens…
98,415Reasoning Tokens…
Response Time (avg)
6.28sResponse Time (avg)…
23.08sResponse Time (avg)…
Response Time (max)
17.13sResponse Time (max)…
95.88sResponse Time (max)…
Response Time (total)
138.06sResponse Time (total)…
484.63sResponse Time (total)…
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
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)3.48sResponse Time (max)4.31sResponse Time (total)13.94sA test is fully passed only if every run passed for that test.…
3.48sResponse Time (avg)…
500Total Input Tokens…
281Output Tokens…
3,082Reasoning Tokens…
GLM 5V TurboArchived model: this model is no longer updated or tested on new tests.
7.2Summarizes 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).…
75.0%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.Did not follow instructions: 1Wrong answer: 1Response Time (avg)10.76sResponse Time (max)14.40sResponse Time (total)43.02sA test is fully passed only if every run passed for that test.…
5.8Summarizes 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)6.00sResponse Time (max)6.94sResponse Time (total)18.00sA test is fully passed only if every run passed for that test.…
6.00sResponse Time (avg)…
8,122Total Input Tokens…
456Output Tokens…
7,421Reasoning Tokens…
GLM 5V TurboArchived model: this model is no longer updated or tested on new tests.
6.0Summarizes 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).…
55.6%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)63.38sResponse Time (max)95.88sResponse Time (total)190.15sA 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.Wrong answer: 2Response Time (avg)10.20sResponse Time (max)17.13sResponse Time (total)20.39sA test is fully passed only if every run passed for that test.…
10.20sResponse Time (avg)…
99,775Total Input Tokens…
7,822Output Tokens…
0Reasoning Tokens…
GLM 5V TurboArchived model: this model is no longer updated or tested on new tests.
3.4Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
1.9Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
33.3%Attempt pass rate = passed attempts / total attempts across runs.…
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)15.06sResponse Time (max)15.06sResponse Time (total)15.06sA 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)9.40sResponse Time (max)14.72sResponse Time (total)18.80sA test is fully passed only if every run passed for that test.…
9.40sResponse Time (avg)…
7,261Total Input Tokens…
279Output Tokens…
3,656Reasoning Tokens…
GLM 5V TurboArchived model: this model is no longer updated or tested on new tests.
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)9.60sResponse Time (max)9.92sResponse Time (total)19.19sA 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)8.05sResponse Time (max)14.40sResponse Time (total)24.15sA test is fully passed only if every run passed for that test.…
8.05sResponse Time (avg)…
645Total Input Tokens…
12Output Tokens…
6,410Reasoning Tokens…
GLM 5V TurboArchived model: this model is no longer updated or tested on new tests.
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)38.15sResponse Time (max)67.08sResponse Time (total)114.45sA 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)3.68sResponse Time (max)3.68sResponse Time (total)3.68sA test is fully passed only if every run passed for that test.…
3.68sResponse Time (avg)…
492Total Input Tokens…
120Output Tokens…
981Reasoning Tokens…
GLM 5V TurboArchived model: this model is no longer updated or tested on new tests.
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)11.09sResponse Time (max)11.09sResponse Time (total)11.09sA test is fully passed only if every run passed for that test.…
9.9Summarizes 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)7.02sResponse Time (max)7.35sResponse Time (total)14.03sA test is fully passed only if every run passed for that test.…
7.02sResponse Time (avg)…
621Total Input Tokens…
71Output Tokens…
2,752Reasoning Tokens…
GLM 5V TurboArchived model: this model is no longer updated or tested on new tests.
9.9Summarizes 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)3.74sResponse Time (max)5.23sResponse Time (total)7.47sA 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)5.77sResponse Time (max)10.27sResponse Time (total)17.32sA test is fully passed only if every run passed for that test.…
5.77sResponse Time (avg)…
562Total Input Tokens…
288Output Tokens…
3,168Reasoning Tokens…
GLM 5V TurboArchived model: this model is no longer updated or tested on new tests.
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)10.24sResponse Time (max)16.95sResponse Time (total)30.72sA 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)4.99sResponse Time (max)4.99sResponse Time (total)4.99sA test is fully passed only if every run passed for that test.…
4.99sResponse Time (avg)…
5,550Total Input Tokens…
234Output Tokens…
415Reasoning Tokens…
GLM 5V TurboArchived model: this model is no longer updated or tested on new tests.
7.0Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
3.7Consistency 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)12.53sResponse Time (max)12.53sResponse Time (total)12.53sA 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)2.75sResponse Time (max)2.75sResponse Time (total)2.75sA test is fully passed only if every run passed for that test.…
2.75sResponse Time (avg)…
156Total Input Tokens…
9Output Tokens…
633Reasoning Tokens…
GLM 5V TurboArchived model: this model is no longer updated or tested on new tests.
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)40.96sResponse Time (max)40.96sResponse Time (total)40.96sA test is fully passed only if every run passed for that test.…