KAT Coder AIR V2.5 (default) leads on average score with 4.4 vs 4.4. Mercury 2 has the lower benchmark cost at $0.033 vs $0.070. Mercury 2 is faster at 1.18s vs 11.96s, with pass rates of 23.2% vs 34.8%.
Last updated at:
2026-10-12
Compared models
Rank
#360
Total Output Tokens
9,709
Response Time (avg)
1.18s
Total Cost
$0.033
Rank
#356
Total Output Tokens
97,752
Response Time (avg)
11.96s
Total Cost
$0.070
Recommended modelMercury 2
Its score stays close to the best score here (4.4 vs 4.4), while costing about 2.1x less than KAT Coder AIR V2.5 (default).
4.4Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
4.4Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
Rank
#360
#356
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).…
7.4Consistency score reflects run-to-run stability (10 = very consistent, even if consistently wrong).…
Attempts
69/69
69/69
Tests Correct
A test is fully passed only if every run passed for that test.Wrong answer: 17Did not follow instructions: 2Response Time (avg)1.18sResponse Time (max)9.00sResponse Time (total)27.14sA 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: 13Extra formatting: 3API error: 2Response Time (avg)11.96sResponse Time (max)121.05sResponse Time (total)275.18sA test is fully passed only if every run passed for that test.…
Attempt pass rate
23.2%Attempt pass rate = passed attempts / total attempts across runs.…
34.8%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).…
7Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
Total Runs
69Total Runs…
69Total Runs…
Cost per result
0.812
1.382
Total Cost
$0.033
$0.070
Input Price
$0.250 / 1MInput Price…
$0.150 / 1MInput Price…
Output Price
$0.750 / 1MOutput Price…
$0.600 / 1MOutput Price…
Cache Read Price
$0.025 / 1MCache Read Price…
N/ACache Read Price…
Cache Write Price
N/ACache Write Price…
N/ACache Write Price…
Total Input Tokens
100,634Total Input Tokens…
69,376Total Input Tokens…
Output Tokens
9,609Output Tokens…
7,792Output Tokens…
Reasoning Tokens
100Reasoning Tokens…
89,960Reasoning Tokens…
Response Time (avg)
1.18sResponse Time (avg)…
11.96sResponse Time (avg)…
Response Time (max)
9.00sResponse Time (max)…
121.05sResponse Time (max)…
Response Time (total)
27.14sResponse Time (total)…
275.18sResponse Time (total)…
Parameters
~100B
~35B total (~3B active)
Availability
Closed
Closed
Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
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.Did not follow instructions: 1Response Time (avg)9.00sResponse Time (max)9.00sResponse Time (total)9.00sA 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)1.07sResponse Time (max)1.07sResponse Time (total)1.07sA 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: 4Response Time (avg)483msResponse Time (max)716msResponse Time (total)1.93sA 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.…
5.6Consistency 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.Wrong answer: 3Response Time (avg)2.68sResponse Time (max)5.78sResponse Time (total)10.73sA 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.…
9.6Consistency 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)1.03sResponse Time (max)1.43sResponse Time (total)3.10sA test is fully passed only if every run passed for that test.…
3.3Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
9.6Consistency 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)14.31sResponse Time (max)21.40sResponse Time (total)42.94sA 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)2.56sResponse Time (max)4.52sResponse Time (total)5.13sA 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.…
1.6Consistency 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: 1Wrong answer: 1Response Time (avg)73.00sResponse Time (max)121.05sResponse Time (total)146.00sA test is fully passed only if every run passed for that test.…
7.3Summarizes broad quality across our full private benchmark suite, so ranking reflects consistent performance.…
5.9Consistency 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.Wrong answer: 1Response Time (avg)667msResponse Time (max)819msResponse Time (total)1.33sA 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.…
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.Extra formatting: 1Response Time (avg)2.66sResponse Time (max)2.69sResponse Time (total)5.33sA test is fully passed only if every run passed for that test.…
5.9Summarizes 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).…
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)500msResponse Time (max)733msResponse Time (total)1.50sA 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)8.33sResponse Time (max)8.97sResponse Time (total)25.00sA 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.Did not follow instructions: 1Response Time (avg)628msResponse Time (max)628msResponse Time (total)628msA 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)12.02sResponse Time (max)12.02sResponse Time (total)12.02sA 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.Wrong answer: 1Response Time (avg)551msResponse Time (max)622msResponse Time (total)1.10sA 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)1.75sResponse Time (max)2.06sResponse Time (total)3.50sA test is fully passed only if every run passed for that test.…
3.1Summarizes 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)535msResponse Time (max)642msResponse Time (total)1.60sA 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: 3Response Time (avg)1.84sResponse Time (max)2.06sResponse Time (total)5.52sA 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)1.27sResponse Time (max)1.27sResponse Time (total)1.27sA 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)5.13sResponse Time (max)5.13sResponse Time (total)5.13sA 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)548msResponse Time (max)548msResponse Time (total)548msA 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)17.96sResponse Time (max)17.96sResponse Time (total)17.96sA test is fully passed only if every run passed for that test.…