Is Hermes 4 405B better than Qwen3.5 397B A17B?

On accuracy they are statistically tied: Hermes 4 405B scored 26.2% and Qwen3.5 397B A17B 32.5% on the same 80 questions from open datasets. Similar accuracy; Hermes 4 405B costs less per question.

Which is cheaper, Hermes 4 405B or Qwen3.5 397B A17B?

Hermes 4 405B is cheaper: $0.01 per question as billed, against $0.013. List prices: Hermes 4 405B $1 in / $3 out, Qwen3.5 397B A17B $0.5 in / $3.6 out per million tokens.

Which is faster, Hermes 4 405B or Qwen3.5 397B A17B?

Qwen3.5 397B A17B is faster at 240 output tokens per second, against 41. Time to first token: 0.3 s for Hermes 4 405B, 0.6 s for Qwen3.5 397B A17B.

Which has the larger context window, Hermes 4 405B or Qwen3.5 397B A17B?

Qwen3.5 397B A17B, with 262k tokens against 131k.

Head to head · tested 27 Oct 2026

Hermes 4 405B vs Qwen3.5 397B A17B: accuracy, speed and price

Similar accuracy; Hermes 4 405B costs less per question.

NousHermes 4 405B26.2% score · #67$0.01 per question41 tok/s

QwenQwen3.5 397B A17B32.5% score · #62$0.013 per question240 tok/s

Verdict

Built from the measurements below

Accuracy is too close to call: Hermes 4 405B scored 26.2% and Qwen3.5 397B A17B 32.5% on the same 80 questions, a gap within what chance alone could produce.
Hermes 4 405B is 1.3× cheaper per question as billed ($0.01 vs $0.013), reasoning tokens included.
Qwen3.5 397B A17B generates text 5.9× faster: 240 tokens per second against 41.
Hermes 4 405B starts answering sooner: 0.3 s to the first token, against 0.6 s for Qwen3.5 397B A17B.
Qwen3.5 397B A17B accepts more context: 262k tokens against 131k.

Which should you choose?

Choose Hermes 4 405B for a quicker first token. Choose Qwen3.5 397B A17B for faster streaming, a 262k-token context window and more hosts to choose from on OpenRouter (10 against 1). The widest subject gap is in humanities & social science: Qwen3.5 397B A17B answered 8 of 9 correctly, Hermes 4 405B 6 of 9. With so few questions per subject, treat this as a lead to test on your own prompts, not a result.

Accuracy gap -6.3 points (z = -0.87). A winner is called only when z is at least 1.96, the usual 95% threshold. Speed, latency and price need a 10% margin.

Head to head

Same questions, same prompt, same API

Measure	Hermes 4 405B	Qwen3.5 397B A17B	Edge
Verification scoreHigher is better	26.2%	32.5%	Too close to call
Cost per questionLower is better	$0.01	$0.013	Hermes 4 405B
Output speedHigher is better	41	240	Qwen3.5 397B A17B
Time to first tokenLower is better	0.3 s	0.6 s	Hermes 4 405B
End-to-end response timeLower is better	17.5 s	3.5 s	Qwen3.5 397B A17B
Tokens per questionLower is better	3,223	4,010	Hermes 4 405B
Context windowHigher is better	131k	262k	Qwen3.5 397B A17B

Side by side

Bars are scaled to the larger of the two values. The winner on each measure is marked in bold.

Every measure

Hermes 4 405B first, Qwen3.5 397B A17B second

Verification scorehigher is better

Hermes 4 405B26.2%

Qwen3.5 397B A17B32.5%

Cost per questionlower is better

Hermes 4 405B$0.01

Qwen3.5 397B A17B$0.013

Output speedhigher is better

Hermes 4 405B41

Qwen3.5 397B A17B240

Time to first tokenlower is better

Hermes 4 405B0.3 s

Qwen3.5 397B A17B0.6 s

End-to-end response timelower is better

Hermes 4 405B17.5 s

Qwen3.5 397B A17B3.5 s

Tokens per questionlower is better

Hermes 4 405B3,223

Qwen3.5 397B A17B4,010

Context windowhigher is better

Hermes 4 405B131k

Qwen3.5 397B A17B262k

Score vs. cost per question

Both models in color, every other model in grey

Results by subject and dataset

Questions answered correctly. Small samples: a gap of one or two questions is noise.

Subject	Questions	Hermes 4 405B	Qwen3.5 397B A17B
Science	30	5/30	10/30
Engineering	15	0/15	0/15
Medicine	11	3/11	2/11
Economics	9	5/9	5/9
Law	6	2/6	1/6
Humanities & social science	9	6/9	8/9
SuperGPQA dataset	50	3/50	5/50
MMLU-Pro dataset	30	18/30	21/30

Specifications and pricing

From OpenRouter's catalogue, plus the leaderboard's test dates

Specification	Hermes 4 405B	Qwen3.5 397B A17B
Creator	Nous	Qwen
Released	26 Aug 2025	16 Feb 2026
Weights	Open weights	Open weights
Reasoning	Yes	Yes
Input	text	text, image, video
Output	text	text
Context window	131k tokens	262k tokens
Knowledge cutoff	31 Aug 2024	—
List price in / out per 1M	$1 / $3	$0.5 / $3.6
Blended price per 1M (3:1)	$1.50	$1.27
Cheapest host	Nebius · $1 / $3	Alibaba · $0.39 / $2.34
Hosts on OpenRouter	1	10
Last tested	27 Oct 2026	27 Oct 2026

Compare any two models →

Hermes 4 405B vs Qwen3.5 397B A17B: frequently asked questions

Is Hermes 4 405B better than Qwen3.5 397B A17B?: On accuracy they are statistically tied: Hermes 4 405B scored 26.2% and Qwen3.5 397B A17B 32.5% on the same 80 questions from open datasets. Similar accuracy; Hermes 4 405B costs less per question.
Which is cheaper, Hermes 4 405B or Qwen3.5 397B A17B?: Hermes 4 405B is cheaper: $0.01 per question as billed, against $0.013. List prices: Hermes 4 405B $1 in / $3 out, Qwen3.5 397B A17B $0.5 in / $3.6 out per million tokens.
Which is faster, Hermes 4 405B or Qwen3.5 397B A17B?: Qwen3.5 397B A17B is faster at 240 output tokens per second, against 41. Time to first token: 0.3 s for Hermes 4 405B, 0.6 s for Qwen3.5 397B A17B.
Which has the larger context window, Hermes 4 405B or Qwen3.5 397B A17B?: Qwen3.5 397B A17B, with 262k tokens against 131k.