Granite 4.2 8B (high) leads on average score with 4.6 vs 3.7. gpt-oss-120b has the lower benchmark cost at $0.033 vs $0.135. gpt-oss-120b is faster at 21.61s vs 235.89s, with pass rates of 39.4% vs 33.3%.
Last updated at:
2026-09-18
Compared models
Rank
#299
Total Output Tokens
612,215
Response Time (avg)
235.89s
Total Cost
$0.135
Rank
#325
Total Output Tokens
51,664
Response Time (avg)
21.61s
Total Cost
$0.033
Recommended modelgpt-oss-120b
It offers the best overall trade-off: a competitive score (3.7), lower cost than Granite 4.2 8B (high), and balanced response time.
gpt-oss-120bgpt-oss-120bnone57/66 attempts (Target: 3 repeats per test)Release: 2025-08-05Free Available
Score
4.6Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
3.7Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
Rank
#299
#325
Reliability
7.6First-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
6.3Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
7.8Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
Attempts
66/66
57/66
Tests Correct
A test is fully passed only if every run passed for that test.Timed out: 10Wrong answer: 6Invalid tool call: 1No answer: 1Response Time (avg)235.89sResponse Time (max)685.87sResponse Time (total)5189.64sA 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: 8API error: 3Did not follow instructions: 2Response Time (avg)21.61sResponse Time (max)113.71sResponse Time (total)345.79sA test is fully passed only if every run passed for that test.…
Attempt pass rate
39.4%Attempt pass rate = passed attempts / total attempts across runs.…
33.3%Attempt pass rate = passed attempts / total attempts across runs.…
Flaky tests
10Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
2Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
Total Runs
66Total Runs…
57Total Runs…
Cost per result
2.085
0.168
Total Cost
$0.135
$0.033
Input Price
$0.060 / 1MInput Price…
$0.150 / 1MInput Price…
Output Price
$0.250 / 1MOutput Price…
$0.600 / 1MOutput Price…
Total Input Tokens
43,278Total Input Tokens…
9,081Total Input Tokens…
Output Tokens
181,083Output Tokens…
51,664Output Tokens…
Reasoning Tokens
431,132Reasoning Tokens…
0Reasoning Tokens…
Response Time (avg)
235.89sResponse Time (avg)…
21.61sResponse Time (avg)…
Response Time (max)
685.87sResponse Time (max)…
113.71sResponse Time (max)…
Response Time (total)
5189.64sResponse Time (total)…
345.79sResponse Time (total)…
Parameters
8B
117B total (5.1B active)
Availability
Open source
Open source
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#299 IBM: Granite 4.2 8B
high
Provider returned error
Cost
$0.000
Time
0.2s
Tokens
0 tok
#325 gpt-oss-120b
none
No showcase result has been generated for this model yet.
6.9Summarizes 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).…
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.Timed out: 2Response Time (avg)205.31sResponse Time (max)413.57sResponse Time (total)821.25sA 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.Did not follow instructions: 1Wrong answer: 1Response Time (avg)32.84sResponse Time (max)113.71sResponse Time (total)131.35sA test is fully passed only if every run passed for that test.…
3.8Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
4.3Consistency 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.Timed out: 2Wrong answer: 1Response Time (avg)515.34sResponse Time (max)567.74sResponse Time (total)1546.02sA 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.…
4.0Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
22.2%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)9.57sResponse Time (max)9.57sResponse Time (total)9.57sA 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.…
6.8Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
33.3%Attempt pass rate = passed attempts / total attempts across runs.…
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: 1Timed out: 1Response Time (avg)570.43sResponse Time (max)685.87sResponse Time (total)1140.86sA 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.API error: 1Response Time (avg)0msResponse Time (max)0msResponse Time (total)0msA test is fully passed only if every run passed for that test.…
3.8Summarizes 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).…
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.Timed out: 1Wrong answer: 1Response Time (avg)56.55sResponse Time (max)112.47sResponse Time (total)113.10sA 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.API error: 1Response Time (avg)7.12sResponse Time (max)7.12sResponse Time (total)7.12sA 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: 2Timed out: 1Response Time (avg)167.15sResponse Time (max)183.96sResponse Time (total)501.46sA 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: 3Response Time (avg)34.98sResponse Time (max)68.97sResponse Time (total)104.94sA 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).…
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)16.37sResponse Time (max)16.37sResponse Time (total)16.37sA test is fully passed only if every run passed for that test.…
4.8Summarizes 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).…
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)10.79sResponse Time (max)10.79sResponse Time (total)10.79sA 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.Timed out: 1Response Time (avg)87.47sResponse Time (max)150.79sResponse Time (total)174.94sA 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)5.06sResponse Time (max)5.85sResponse Time (total)10.12sA 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.…
4.4Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
22.2%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.Timed out: 2No answer: 1Response Time (avg)202.69sResponse Time (max)252.93sResponse Time (total)608.07sA test is fully passed only if every run passed for that test.…
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.Did not follow instructions: 1Wrong answer: 1Response Time (avg)8.21sResponse Time (max)11.82sResponse Time (total)24.62sA 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)15.08sResponse Time (max)15.08sResponse Time (total)15.08sA 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.API error: 1Response Time (avg)0msResponse Time (max)0msResponse Time (total)0msA 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)252.49sResponse Time (max)252.49sResponse Time (total)252.49sA 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)47.29sResponse Time (max)47.29sResponse Time (total)47.29sA test is fully passed only if every run passed for that test.…