What is the best Qwen model?

Qwen3.8 Max (0902) has the highest verification score of the Qwen models we tested: 75.0% (60 of 80 correct) in our 2026-10-27 run.

What is the fastest Qwen model?

Qwen3.5 397B A17B is the fastest Qwen model we tested, at a median 240 output tokens per second.

What is the cheapest Qwen model?

Qwen3 Coder Next has the lowest billed cost per question of the Qwen models we tested: $0.0017.

Which Qwen models do you test?

Qwen3.8 Max (0902), Qwen3.8 27B, Qwen3 Coder Next, Qwen3.7 Plus, Qwen3.8 2.4T A95B, Qwen3.6 35B A3B, Qwen3.5 397B A17B, Qwen3.5-122B-A10B, Qwen3 Next 80B A3B Thinking.

Provider

Qwen AI models

9 models tested, compared with 69 models from other labs.

Best verification score75.0Qwen3.8 Max (0902) · #15 of 78 Best output speed240Qwen3.5 397B A17B · #5 of 78 Best time to first token0.4 sQwen3.6 35B A3B · #6 of 78 Best cost per question$0.0017Qwen3 Coder Next · #33 of 78

Qwen#15Qwen3.8 Max (0902)75.0% verification score46 tok/s1.2 s first token$0.011 / question

Qwen#34Qwen3.8 27B63.8% verification score49 tok/s0.5 s first token$0.0043 / question

Qwen#36Qwen3 Coder Next62.5% verification score106 tok/s0.4 s first token$0.0017 / question

Qwen#38Qwen3.7 Plus60.0% verification score62 tok/s1.1 s first token$0.0033 / question

Qwen#44Qwen3.8 2.4T A95B57.5% verification score44 tok/s3.1 s first token$0.015 / question

Qwen#59Qwen3.6 35B A3B37.5% verification score135 tok/s0.4 s first token$0.0037 / question

Qwen#62Qwen3.5 397B A17B32.5% verification score240 tok/s0.6 s first token$0.013 / question

Score vs. cost per question

Qwen models in color, every other model in grey

Output speed vs. cost per question

Qwen models in color, every other model in grey

Verification score

Qwen models highlighted against every model in this run · higher is better

55 more models · see the full leaderboard

Output speed

Qwen models highlighted against every model in this run · higher is better

55 more models · see the full leaderboard

Time to first token

Qwen models highlighted against every model in this run · lower is better

58 more models · see the full leaderboard

Cost per question

Qwen models highlighted against every model in this run · lower is better

1Granite 4.0 Micro$0.000051
2gpt-oss-20b$0.000066
3Granite 4.2 8B$0.000077
4Nova Micro 1.0$0.000087
5Mercury 2.5$0.00011
6Phi 4$0.00012
7gpt-oss-120b$0.00013
8GLM 5.3 Flash$0.00015
9Ministral 3 3B 2512$0.00019
10GPT-6 Luna$0.00025
33Qwen3 Coder Next$0.0017
42Qwen3.7 Plus$0.0033
46Qwen3.6 35B A3B$0.0037
47Qwen3.8 27B$0.0043
61Qwen3.8 Max (0902)$0.011
65Qwen3.5 397B A17B$0.013
67Qwen3.8 2.4T A95B$0.015

55 more models · see the full leaderboard

End-to-end response time

Qwen models highlighted against every model in this run · lower is better

57 more models · see the full leaderboard

Context window

Qwen models highlighted against every model in this run · higher is better

59 more models · see the full leaderboard

All Qwen results

Leaderboard
#
1	Qwen3.8 Max (0902) Qwen · served by Alibaba	75.0	60 / 80	46	1.2 s	$0.011	$2 / $6	1M
2	Qwen3.8 27B Qwen · served by Modal	63.8	51 / 80	49	0.5 s	$0.0043	$0.2 / $2.5	1M
3	Qwen3 Coder Next Qwen · served by Parasail	62.5	50 / 80	106	0.4 s	$0.0017	$0.12 / $0.8	262k
4	Qwen3.7 Plus Qwen · served by Alibaba	60.0	48 / 80	62	1.1 s	$0.0033	$0.32 / $1.28	1M
5	Qwen3.8 2.4T A95B Qwen · served by Venice	57.5	46 / 80	44	3.1 s	$0.015	$2 / $6	1M
6	Qwen3.6 35B A3B Qwen · served by DeepInfra	37.5	30 / 80	135	0.4 s	$0.0037	$0.1 / $0.95	262k
7	Qwen3.5 397B A17B Qwen · served by Phala	32.5	26 / 80	240	0.6 s	$0.013	$0.5 / $3.6	262k
8	Qwen3.5-122B-A10B Qwen · served by SiliconFlow	—	0 / 0	108	1.2 s	—	$0.4 / $3.2	262k
9	Qwen3 Next 80B A3B Thinking Qwen	—	0 / 0	—	—	—	$0.15 / $1.2	262k

Qwen: quick answers

What is the best Qwen model?: Qwen3.8 Max (0902) has the highest verification score of the Qwen models we tested: 75.0% (60 of 80 correct) in our 2026-10-27 run.
What is the fastest Qwen model?: Qwen3.5 397B A17B is the fastest Qwen model we tested, at a median 240 output tokens per second.
What is the cheapest Qwen model?: Qwen3 Coder Next has the lowest billed cost per question of the Qwen models we tested: $0.0017.
Which Qwen models do you test?: Qwen3.8 Max (0902), Qwen3.8 27B, Qwen3 Coder Next, Qwen3.7 Plus, Qwen3.8 2.4T A95B, Qwen3.6 35B A3B, Qwen3.5 397B A17B, Qwen3.5-122B-A10B, Qwen3 Next 80B A3B Thinking.

Provider

Qwen AI models

9 models tested, compared with 69 models from other labs.

Qwen#15Qwen3.8 Max (0902)75.0% verification score46 tok/s1.2 s first token$0.011 / question

Qwen#34Qwen3.8 27B63.8% verification score49 tok/s0.5 s first token$0.0043 / question

Qwen#36Qwen3 Coder Next62.5% verification score106 tok/s0.4 s first token$0.0017 / question

Qwen#38Qwen3.7 Plus60.0% verification score62 tok/s1.1 s first token$0.0033 / question

Qwen#44Qwen3.8 2.4T A95B57.5% verification score44 tok/s3.1 s first token$0.015 / question

Qwen#59Qwen3.6 35B A3B37.5% verification score135 tok/s0.4 s first token$0.0037 / question

Qwen#62Qwen3.5 397B A17B32.5% verification score240 tok/s0.6 s first token$0.013 / question

Score vs. cost per question

Qwen models in color, every other model in grey

Output speed vs. cost per question

Qwen models in color, every other model in grey

Verification score

Qwen models highlighted against every model in this run · higher is better

55 more models · see the full leaderboard

Output speed

Qwen models highlighted against every model in this run · higher is better

55 more models · see the full leaderboard

Time to first token

Qwen models highlighted against every model in this run · lower is better

58 more models · see the full leaderboard

Cost per question

Qwen models highlighted against every model in this run · lower is better

1Granite 4.0 Micro$0.000051
2gpt-oss-20b$0.000066
3Granite 4.2 8B$0.000077
4Nova Micro 1.0$0.000087
5Mercury 2.5$0.00011
6Phi 4$0.00012
7gpt-oss-120b$0.00013
8GLM 5.3 Flash$0.00015
9Ministral 3 3B 2512$0.00019
10GPT-6 Luna$0.00025
33Qwen3 Coder Next$0.0017
42Qwen3.7 Plus$0.0033
46Qwen3.6 35B A3B$0.0037
47Qwen3.8 27B$0.0043
61Qwen3.8 Max (0902)$0.011
65Qwen3.5 397B A17B$0.013
67Qwen3.8 2.4T A95B$0.015

55 more models · see the full leaderboard

End-to-end response time

Qwen models highlighted against every model in this run · lower is better

57 more models · see the full leaderboard

Context window

Qwen models highlighted against every model in this run · higher is better

59 more models · see the full leaderboard

All Qwen results

Leaderboard
#
1	Qwen3.8 Max (0902) Qwen · served by Alibaba	75.0	60 / 80	46	1.2 s	$0.011	$2 / $6	1M
2	Qwen3.8 27B Qwen · served by Modal	63.8	51 / 80	49	0.5 s	$0.0043	$0.2 / $2.5	1M
3	Qwen3 Coder Next Qwen · served by Parasail	62.5	50 / 80	106	0.4 s	$0.0017	$0.12 / $0.8	262k
4	Qwen3.7 Plus Qwen · served by Alibaba	60.0	48 / 80	62	1.1 s	$0.0033	$0.32 / $1.28	1M
5	Qwen3.8 2.4T A95B Qwen · served by Venice	57.5	46 / 80	44	3.1 s	$0.015	$2 / $6	1M
6	Qwen3.6 35B A3B Qwen · served by DeepInfra	37.5	30 / 80	135	0.4 s	$0.0037	$0.1 / $0.95	262k
7	Qwen3.5 397B A17B Qwen · served by Phala	32.5	26 / 80	240	0.6 s	$0.013	$0.5 / $3.6	262k
8	Qwen3.5-122B-A10B Qwen · served by SiliconFlow	—	0 / 0	108	1.2 s	—	$0.4 / $3.2	262k
9	Qwen3 Next 80B A3B Thinking Qwen	—	0 / 0	—	—	—	$0.15 / $1.2	262k

Qwen: quick answers

What is the best Qwen model?: Qwen3.8 Max (0902) has the highest verification score of the Qwen models we tested: 75.0% (60 of 80 correct) in our 2026-10-27 run.
What is the fastest Qwen model?: Qwen3.5 397B A17B is the fastest Qwen model we tested, at a median 240 output tokens per second.
What is the cheapest Qwen model?: Qwen3 Coder Next has the lowest billed cost per question of the Qwen models we tested: $0.0017.
Which Qwen models do you test?: Qwen3.8 Max (0902), Qwen3.8 27B, Qwen3 Coder Next, Qwen3.7 Plus, Qwen3.8 2.4T A95B, Qwen3.6 35B A3B, Qwen3.5 397B A17B, Qwen3.5-122B-A10B, Qwen3 Next 80B A3B Thinking.