MiniMax M2.5 (medium) vs Nemotron 3.5 Lightning (low)
Nemotron 3.5 Lightning (low) leads on average score with 4.8 vs 4.6. Nemotron 3.5 Lightning (low) has the lower benchmark cost at $0.173 vs $0.350. Nemotron 3.5 Lightning (low) is faster at 59.45s vs 68.27s, with pass rates of 45.5% vs 42.4%.
Last updated at:
2026-08-11
Rank
#237
Total Output Tokens
465,377
Response Time (avg)
68.27s
Total Cost
$0.350
Rank
#225
Total Output Tokens
653,448
Response Time (avg)
59.45s
Total Cost
$0.173
Recommended modelNemotron 3.5 Lightning (low)
It has the best score here (4.8), while costing about 2.0x less than MiniMax M2.5 (medium).
A test is fully passed only if every run passed for that test.Wrong answer: 14Did not follow instructions: 2Invalid tool call: 1Response Time (avg)59.45sResponse Time (max)312.21sResponse Time (total)1307.87sA test is fully passed only if every run passed for that test.…
Attempt pass rate
45.5%Attempt pass rate = passed attempts / total attempts across runs.…
42.4%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).…
9Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
Total Runs
66Total Runs…
66Total Runs…
Cost per result
8.648Shows the average cost per correct benchmark answer in cents (lower is better).…
0.000Shows the average cost per correct benchmark answer in cents (lower is better).…
Total Cost
$0.350Total Cost (Current Price)…
$0.173Total Cost (Current Price)…
Input Price
$0.220 / 1MInput Price…
$0.100 / 1MInput Price…
Output Price
$0.900 / 1MOutput Price…
$0.250 / 1MOutput Price…
Total Input Tokens
142,561Total Input Tokens…
138,783Total Input Tokens…
Output Tokens
125,442Output Tokens…
137,292Output Tokens…
Reasoning Tokens
339,935Reasoning Tokens…
516,156Reasoning Tokens…
Response Time (avg)
68.27sResponse Time (avg)…
59.45sResponse Time (avg)…
Response Time (max)
251.36sResponse Time (max)…
312.21sResponse Time (max)…
Response Time (total)
955.75sResponse Time (total)…
1307.87sResponse Time (total)…
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#237 MiniMax M2.5
medium
Invalid SVG
Cost
$0.000
Time
300.0s
Tokens
0 tok
#225 Nemotron 3.5 Lightning
low
No showcase result has been generated for this model yet.
7.9Summarizes 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).…
83.3%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.Did not follow instructions: 1Timed out: 1Response Time (avg)20.82sResponse Time (max)32.42sResponse Time (total)41.63sA test is fully passed only if every run passed for that test.…
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.Wrong answer: 2Response Time (avg)14.82sResponse Time (max)27.06sResponse Time (total)59.28sA 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.…
9.1Consistency 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: 1Timed out: 1Wrong answer: 1Response Time (avg)188.58sResponse Time (max)251.36sResponse Time (total)377.16sA 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.…
7.8Consistency 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)224.42sResponse Time (max)312.21sResponse Time (total)673.27sA 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.…
1.8Consistency 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.Invalid tool call: 1No answer: 1Response Time (avg)83.19sResponse Time (max)105.99sResponse Time (total)166.38sA 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.Invalid tool call: 1Response Time (avg)142.36sResponse Time (max)259.10sResponse Time (total)284.72sA test is fully passed only if every run passed for that test.…
4.6Summarizes 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).…
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.Wrong answer: 2Response Time (avg)7.48sResponse Time (max)7.48sResponse Time (total)7.48sA 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.…
5.8Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
16.7%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.Did not follow instructions: 1Wrong answer: 1Response Time (avg)31.32sResponse Time (max)39.86sResponse Time (total)62.64sA 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.Wrong answer: 2Timed out: 1Response Time (avg)237.27sResponse Time (max)237.27sResponse Time (total)237.27sA test is fully passed only if every run passed for that test.…
3.6Summarizes 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).…
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: 3Response Time (avg)50.01sResponse Time (max)123.93sResponse Time (total)150.04sA 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.…
2.5Consistency 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)6.63sResponse Time (max)6.63sResponse Time (total)6.63sA 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.…
9.5Consistency 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: 1Response Time (avg)4.61sResponse Time (max)4.61sResponse Time (total)4.61sA test is fully passed only if every run passed for that test.…
7.5Summarizes 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: 1Response Time (avg)621msResponse Time (max)621msResponse Time (total)621msA test is fully passed only if every run passed for that test.…
8.4Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
6.9Consistency 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)5.46sResponse Time (max)7.47sResponse Time (total)10.92sA 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.Timed out: 1Wrong answer: 1Response Time (avg)11.21sResponse Time (max)17.37sResponse Time (total)22.43sA test is fully passed only if every run passed for that test.…
3.6Summarizes 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).…
44.4%Attempt pass rate = passed attempts / total attempts across runs.…
3Flaky 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)6.21sResponse Time (max)11.28sResponse Time (total)18.64sA 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)15.35sResponse Time (max)15.35sResponse Time (total)15.35sA 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)5.08sResponse Time (max)5.08sResponse Time (total)5.08sA 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.Wrong answer: 1Response Time (avg)80.79sResponse Time (max)80.79sResponse Time (total)80.79sA 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)38.68sResponse Time (max)38.68sResponse Time (total)38.68sA test is fully passed only if every run passed for that test.…