Mercury 2 (medium) vs Kimi K2.5 (medium)

Recommended model Mercury 2 (medium)

It has the best score here (7.0), while costing about 6.5x less than Kimi K2.5 (medium).

Detailed comparison

Metric	Mercury 2 Mercury 2 medium Release: 2026-02-24	Kimi K2.5 Kimi K2.5 medium Release: 2026-01-27

Metric	Mercury 2 Mercury 2 medium Release: 2026-02-24	Kimi K2.5 Kimi K2.5 medium Release: 2026-01-27
Score	7.0	7.0
Rank	#119	#122
Reliability	10.0	10.0
Consistency	8.4	7.0
Attempts	66/66	66/66
Tests Correct
Attempt pass rate	53.0%	63.6%
Flaky tests	4	8
Total Runs	66	66
Cost per result	0.933	4.849
Total Cost	$0.094	$0.607
Input Price	$0.250 / 1M	$0.571 / 1M
Output Price	$0.750 / 1M	$2.850 / 1M
Total Input Tokens	110,515	118,496
Output Tokens	10,325	53,522
Reasoning Tokens	77,229	167,420
Response Time (avg)	2.95s	98.19s
Response Time (max)	14.63s	281.00s
Response Time (total)	61.89s	1571.05s
Parameters	~100B	1T total (32B active)
Availability	Closed	Weights available

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

medium

medium

Category:

Anti-AI Tricks	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Mercury 2	6.9	9.9	50.0%	0		1.12s	554	2,546	2,609
Kimi K2.5	7.3	5.8	83.3%	2		51.38s	634	2,789	8,880

Coding	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Mercury 2	8.2	7.7	77.8%	1		2.04s	7,065	296	11,328
Kimi K2.5	6.1	4.6	66.7%	2		217.49s	6,935	5,705	74,693

Combined	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Mercury 2	6.7	9.1	50.0%	0		7.84s	87,365	6,533	20,474
Kimi K2.5	6.7	9.1	50.0%	0		89.19s	95,416	14,448	11,209

Data parsing and extraction	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Mercury 2	7.3	5.9	83.3%	1		1.11s	6,234	183	1,656
Kimi K2.5	10.0	10.0	100.0%	0		49.78s	7,020	563	7,940

Domain specific	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Mercury 2	2.9	4.4	22.2%	2		8.06s	1,638	53	31,177
Kimi K2.5	2.9	4.4	22.2%	2		111.65s	533	12,151	32,741

General Intelligence	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Mercury 2	4.8	10.0	0.0%	0		821ms	456	137	542
Kimi K2.5	6.5	3.4	66.7%	1		69.73s	480	3,815	4,262

Instructions following	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Mercury 2	10.0	10.0	100.0%	0		1.07s	340	14	958
Kimi K2.5	10.0	10.0	100.0%	0		92.47s	675	5,371	6,547

Puzzle Solving	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Mercury 2	5.4	10.0	33.3%	0		949ms	601	361	2,781
Kimi K2.5	5.3	7.3	44.4%	1		43.23s	659	8,426	12,692

Tool Calling	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Mercury 2	10.0	10.0	100.0%	0		1.89s	6,080	180	1,956
Kimi K2.5	10.0	10.0	100.0%	0		31.74s	5,933	242	812

Trivia	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Mercury 2	3.0	10.0	0.0%	0		2.58s	182	22	3,748
Kimi K2.5	3.0	10.0	0.0%	0		83.95s	211	12	7,644

Switch Comparison Pair