Claude Sonnet 5.5 (xhigh) vs DeepSeek V4.1 Flash (high)
DeepSeek V4.1 Flash (high) leads on average score with 8.7 vs 8.6. DeepSeek V4.1 Flash (high) has the lower benchmark cost at $0.617 vs $1.516. Claude Sonnet 5.5 (xhigh) is faster at 14.98s vs 33.27s, with pass rates of 79.7% vs 75.4%.
Last updated at:
2026-10-24
Compared models
Rank
#75
Total Output Tokens
83,041
Response Time (avg)
14.98s
Total Cost
$1.516
Rank
#64
Total Output Tokens
464,156
Response Time (avg)
33.27s
Total Cost
$0.617
Recommended modelDeepSeek V4.1 Flash (high)
It has the best score here (8.7), while costing about 2.5x less than Claude Sonnet 5.5 (xhigh).
A test is fully passed only if every run passed for that test.Wrong answer: 5API error: 1Did not follow instructions: 1Response Time (avg)33.27sResponse Time (max)205.53sResponse Time (total)765.12sA test is fully passed only if every run passed for that test.…
Attempt pass rate
79.7%Attempt pass rate = passed attempts / total attempts across runs.…
75.4%Attempt pass rate = passed attempts / total attempts across runs.…
Flaky tests
4Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
3Flaky tests had mixed outcomes across runs (at least one pass and one fail).…
Total Runs
69Total Runs…
69Total Runs…
Cost per result
9.473
1.843
Total Cost
$1.516
$0.617
Input Price
$2.000 / 1MInput Price…
$0.013 / 1MInput Price…
Output Price
$10.000 / 1MOutput Price…
$1.320 / 1MOutput Price…
Cache Read Price
$0.200 / 1MCache Read Price…
$0.013 / 1MCache Read Price…
Cache Write Price
$2.500 / 1MCache Write Price…
N/ACache Write Price…
Total Input Tokens
342,579Total Input Tokens…
282,490Total Input Tokens…
Output Tokens
12,848Output Tokens…
8,621Output Tokens…
Reasoning Tokens
70,193Reasoning Tokens…
455,535Reasoning Tokens…
Response Time (avg)
14.98sResponse Time (avg)…
33.27sResponse Time (avg)…
Response Time (max)
54.92sResponse Time (max)…
205.53sResponse Time (max)…
Response Time (total)
344.60sResponse Time (total)…
765.12sResponse Time (total)…
Parameters
~1T total (~100B active)
748B total (16B active)
Availability
Closed
Open source
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.
#75 Claude Sonnet 5.5
xhigh
Cost
$0.319
Time
258.6s
Tokens
31,969 tok
#64 DeepSeek V4.1 Flash
high
Cost
$0.035
Time
111.0s
Tokens
29,201 tok
Rank
-
Cost
-
Time
-
Tokens
-
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Category Breakdown
Agentic
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Input Tokens
Output Tokens
Reasoning Tokens
Claude Sonnet 5.5Archived 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)54.92sResponse Time (max)54.92sResponse Time (total)54.92sA 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)43.97sResponse Time (max)43.97sResponse Time (total)43.97sA test is fully passed only if every run passed for that test.…
43.97sResponse Time (avg)…
182,379Total Input Tokens…
1,979Output Tokens…
9,237Reasoning Tokens…
Anti-AI Tricks
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Input Tokens
Output Tokens
Reasoning Tokens
Claude Sonnet 5.5Archived 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)4.21sResponse Time (max)5.12sResponse Time (total)16.83sA test is fully passed only if every run passed for that test.…
8.3Summarizes 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).…
75.0%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)3.42sResponse Time (max)7.12sResponse Time (total)13.66sA test is fully passed only if every run passed for that test.…
3.42sResponse Time (avg)…
852Total Input Tokens…
170Output Tokens…
5,348Reasoning Tokens…
Coding
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Input Tokens
Output Tokens
Reasoning Tokens
Claude Sonnet 5.5Archived model: this model is no longer updated or tested on new tests.
8.2Summarizes 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).…
88.9%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)11.90sResponse Time (max)15.48sResponse Time (total)35.70sA 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)49.19sResponse Time (max)89.20sResponse Time (total)147.57sA test is fully passed only if every run passed for that test.…
49.19sResponse Time (avg)…
7,509Total Input Tokens…
376Output Tokens…
108,285Reasoning Tokens…
Combined
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Input Tokens
Output Tokens
Reasoning Tokens
Claude Sonnet 5.5Archived model: this model is no longer updated or tested on new tests.
8.7Summarizes 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.Invalid tool call: 1Response Time (avg)30.37sResponse Time (max)37.90sResponse Time (total)60.75sA 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)27.63sResponse Time (max)39.63sResponse Time (total)55.26sA test is fully passed only if every run passed for that test.…
27.63sResponse Time (avg)…
77,764Total Input Tokens…
5,152Output Tokens…
31,635Reasoning Tokens…
Data parsing and extraction
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Input Tokens
Output Tokens
Reasoning Tokens
Claude Sonnet 5.5Archived 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)4.96sResponse Time (max)6.16sResponse Time (total)9.92sA 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)4.19sResponse Time (max)8.15sResponse Time (total)8.37sA test is fully passed only if every run passed for that test.…
4.19sResponse Time (avg)…
2,397Total Input Tokens…
120Output Tokens…
1,584Reasoning Tokens…
Domain specific
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Input Tokens
Output Tokens
Reasoning Tokens
Claude Sonnet 5.5Archived model: this model is no longer updated or tested on new tests.
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: 3Response Time (avg)35.33sResponse Time (max)54.91sResponse Time (total)106.00sA 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)127.30sResponse Time (max)205.53sResponse Time (total)381.89sA test is fully passed only if every run passed for that test.…
127.30sResponse Time (avg)…
909Total Input Tokens…
28Output Tokens…
249,623Reasoning Tokens…
General Intelligence
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Input Tokens
Output Tokens
Reasoning Tokens
Claude Sonnet 5.5Archived model: this model is no longer updated or tested on new tests.
6.5Summarizes 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).…
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.Did not follow instructions: 1Response Time (avg)9.10sResponse Time (max)9.10sResponse Time (total)9.10sA 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)4.16sResponse Time (max)4.16sResponse Time (total)4.16sA test is fully passed only if every run passed for that test.…
4.16sResponse Time (avg)…
549Total Input Tokens…
120Output Tokens…
1,130Reasoning Tokens…
Instructions following
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Input Tokens
Output Tokens
Reasoning Tokens
Claude Sonnet 5.5Archived 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)4.58sResponse Time (max)4.79sResponse Time (total)9.15sA 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)7.06sResponse Time (max)11.51sResponse Time (total)14.12sA test is fully passed only if every run passed for that test.…
7.06sResponse Time (avg)…
783Total Input Tokens…
63Output Tokens…
1,972Reasoning Tokens…
Puzzle Solving
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Input Tokens
Output Tokens
Reasoning Tokens
Claude Sonnet 5.5Archived 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)4.88sResponse Time (max)5.32sResponse Time (total)14.63sA 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.…
4.9Consistency 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.Did not follow instructions: 1Wrong answer: 1Response Time (avg)14.27sResponse Time (max)33.25sResponse Time (total)42.80sA test is fully passed only if every run passed for that test.…
14.27sResponse Time (avg)…
828Total Input Tokens…
339Output Tokens…
23,969Reasoning Tokens…
Tool Calling
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Input Tokens
Output Tokens
Reasoning Tokens
Claude Sonnet 5.5Archived 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)10.29sResponse Time (max)10.29sResponse Time (total)10.29sA 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)15.28sResponse Time (max)15.28sResponse Time (total)15.28sA test is fully passed only if every run passed for that test.…
15.28sResponse Time (avg)…
8,259Total Input Tokens…
258Output Tokens…
506Reasoning Tokens…
Trivia
Score
Consistency
Attempt pass rate
Flaky tests
Tests Correct
Response Time (avg)
Input Tokens
Output Tokens
Reasoning Tokens
Claude Sonnet 5.5Archived 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.No answer: 1Response Time (avg)17.31sResponse Time (max)17.31sResponse Time (total)17.31sA 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)38.05sResponse Time (max)38.05sResponse Time (total)38.05sA test is fully passed only if every run passed for that test.…