Mercury 2.5 (high) vs Qwen3.6 35B A3B (medium)

Compared models

Recommended model Mercury 2.5 (high)

It has the best score here (6.5), while costing about 18.7x less than Qwen3.6 35B A3B (medium).

Metric	Mercury 2.5 Mercury 2.5 high Release: 2026-09-08	Qwen3.6 35B A3B Qwen3.6 35B A3B medium Release: 2026-04-20

Metric	Mercury 2.5 Mercury 2.5 high Release: 2026-09-08	Qwen3.6 35B A3B Qwen3.6 35B A3B medium Release: 2026-04-20
Score	6.5	6.5
Rank	#195	#193
Reliability	9.8	10.0
Consistency	8.7	9.0
Attempts	69/69	69/69
Tests Correct
Attempt pass rate	59.4%	58.0%
Flaky tests	4	3
Total Runs	69	69
Cost per result	0.362	6.732
Total Cost	$0.044	$0.812
Input Price	$0.040 / 1M	$0.150 / 1M
Output Price	$0.150 / 1M	$1.000 / 1M
Total Input Tokens	358,562	282,192
Output Tokens	4,266	75,306
Reasoning Tokens	189,410	700,868
Response Time (avg)	7.62s	59.92s
Response Time (max)	80.30s	817.57s
Response Time (total)	175.36s	1258.32s
Parameters	~100B	35B total (3B active)
Availability	Closed	Open source

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

high

medium

Reached the allocated time limit (300 seconds) without receiving showcase output.

Category:

Agentic	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Mercury 2.5	3.9	9.6	0.0%	0		80.30s	238,494	864	18,265
Qwen3.6 35B A3B	6.1	3.1	66.7%	1		88.48s	197,044	13,570	19,312

Anti-AI Tricks	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Mercury 2.5	10.0	10.0	100.0%	0		1.33s	782	218	7,913
Qwen3.6 35B A3B	10.0	10.0	100.0%	0		6.02s	672	1,154	12,385

Coding	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Mercury 2.5	6.4	7.8	44.4%	1		6.58s	7,757	415	44,012
Qwen3.6 35B A3B	7.7	10.0	66.7%	0		50.55s	5,051	7,929	37,223

Combined	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Mercury 2.5	6.4	5.8	66.7%	1		16.00s	91,255	1,478	62,200
Qwen3.6 35B A3B	3.0	10.0	0.0%	0		817.57s	68,754	42,187	548,547

Data parsing and extraction	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Mercury 2.5	10.0	10.0	100.0%	0		3.08s	8,355	557	9,430
Qwen3.6 35B A3B	10.0	10.0	100.0%	0		12.99s	7,776	2,591	9,968

Domain specific	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Mercury 2.5	2.9	7.2	11.1%	1		4.86s	857	78	22,452
Qwen3.6 35B A3B	2.9	4.4	22.2%	2		25.39s	780	6,110	41,906

General Intelligence	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Mercury 2.5	5.0	10.0	0.0%	0		2.69s	528	93	3,609
Qwen3.6 35B A3B	4.4	9.9	0.0%	0		8.66s	516	129	4,569

Instructions following	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Mercury 2.5	6.5	10.0	50.0%	0		934ms	401	27	1,770
Qwen3.6 35B A3B	10.0	10.0	100.0%	0		7.50s	699	219	7,404

Puzzle Solving	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Mercury 2.5	8.7	7.7	88.9%	1		1.39s	771	227	5,812
Qwen3.6 35B A3B	8.0	10.0	66.7%	0		5.95s	696	655	9,228

Tool Calling	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Mercury 2.5	10.0	10.0	100.0%	0		3.06s	9,130	283	4,484
Qwen3.6 35B A3B	3.0	10.0	0.0%	0		0ms	0	0	0

Trivia	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Mercury 2.5	3.0	10.0	0.0%	0		5.48s	232	26	9,463
Qwen3.6 35B A3B	3.0	10.0	0.0%	0		32.90s	204	762	10,326

Switch Comparison Pair