Compare / Qwen3.5-122B-A10B vs Nova 2 Lite

Qwen3.5-122B-A10B vs Nova 2 Lite

Which is cheaper, which is more capable, and which does better at each kind of work, from 23 results on 4 sources that measured both models.

AlibabaQwen3.5-122B-A10B Released 24 Feb 2026 · $0.26 in · $2.08 out
AmazonNova 2 Lite Released 29 Oct 2025 · $0.30 in · $2.50 out
Qwen3.5-122B-A10B wins 20Nova 2 Lite wins 3

Of the 23 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 9 October 2026 (catalogue release 2026-10-09-dd620e778ac5). See also Alibaba vs Amazon, every model from both labs.

Qwen3.5-122B-A10B or Nova 2 Lite? The short answer

Pick Qwen3.5-122B-A10B: it scores higher (Intelligence Index 17.7 against 13.4) at about the same price. Pick Nova 2 Lite only if speed matters more: it writes faster.

  • They cost about the same: $0.72 and $0.85 per million tokens (three input to one output).
  • Qwen3.5-122B-A10B scores higher on the Artificial Analysis Intelligence Index: 17.7 against 13.4.
  • Nova 2 Lite writes faster: 217 tokens a second against 147.
  • Qwen3.5-122B-A10B is newer: released 24 Feb 2026, against 29 Oct 2025 for Nova 2 Lite.
  • On third-party benchmarks, on the results both models have: Qwen3.5-122B-A10B does better for agents and tool use, reasoning and knowledge and writing.

Head to head

17.7
Intelligence Index
13.4
$0.72
Price per million tokens, blendedlower is better
$0.85
147
Output speed, tokens a second
217
262,144
Context window, tokens
1,000,000

Every fact side by side

Qwen3.5-122B-A10BNova 2 Lite
Price per million tokens$0.26 in · $2.08 out$0.30 in · $2.50 out
Blended (3 in : 1 out)$0.72$0.85
Cheapest host, blended$0.72 (Alibaba)$0.85 (Amazon Bedrock)
Intelligence Index17.713.4
Spring Prompt overall––
Output speed, tokens a second147217
Context window262,144 tokens1,000,000 tokens
Released24 Feb 2026 (newer)29 Oct 2025
WeightsOpenClosed
Developer based inChinathe US

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.

Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 95 of 164 133 of 164
Reasoning and knowledgeHard questions across science, maths and general knowledge 87 of 198 116 of 198
WritingWhat people prefer in blind comparisons, and judged writing quality 102 of 188 169 of 188
Sticking to the factsSummarising without inventing things, and factual answers 108 of 152 73 of 152

Every shared result

Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.

MeasureQwen3.5-122B-A10BNova 2 Lite
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 117 · 214 of 387 measured 1,416 1,335
Overall · Text factualityArena rating, higher is better 103 · 143 of 163 measured 1,428 1,380
Business, management and finance · TextArena rating, higher is better 105 · 186 of 380 measured 1,422 1,351
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 114 · 138 of 243 measured 17.7no reasoning 13.4high reasoning
GPQA Diamond% of questions, higher is better 75 · 105 of 231 measured 85.7% 81.1%high reasoning
Humanity's Last Exam% of questions, higher is better 92 · 142 of 242 measured 25.2% 11.6%high reasoning
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 112 · 190 of 230 measured 39.5no reasoning 23.5no reasoning
Requested-length error · UGI% off the requested word count, lower is better 33 · 200 of 230 measured 9.0%thinking reasoning 45.0%thinking reasoning
Style adherence · UGIscore from 0 to 1, higher is better 83 · 108 of 230 measured 0.36no reasoning 0.35no reasoning
Vectara Hallucination Leaderboard reported by Vectara Hallucination Leaderboard · 2 results
Hallucination rate · Vectara% of summaries, lower is better 72 · 10 of 104 measured 11.2% 5.1%
Answer rate · Vectara% of documents, higher is better 31 · 45 of 104 measured 99.8% 99.6%
Show all 23 results (12 more)
MeasureQwen3.5-122B-A10BNova 2 Lite
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results
Creative writing · TextArena rating, higher is better 136 · 248 of 385 measured 1,366 1,269
Expert prompts · TextArena rating, higher is better 111 · 192 of 338 measured 1,442 1,352
Instruction following · TextArena rating, higher is better 115 · 199 of 387 measured 1,406 1,327
Writing, literature and language · TextArena rating, higher is better 125 · 235 of 386 measured 1,387 1,298
Artificial Analysis reported by Artificial Analysis · 8 results
Terminal-Bench 2.1% of tasks, higher is better 64 · 95 of 130 measured 47.6% 16.1%high reasoning
Artificial Analysis Coding Indexindex score, higher is better 65 · 94 of 131 measured 45.7 23.0high reasoning
IFBench% of instructions, higher is better 22 · 50 of 195 measured 75.7% 70.7%high reasoning
Long-context reasoning (AA-LCR)% of questions, higher is better 72 · 139 of 233 measured 76.3% 60.3%high reasoning
Output speedtokens per second, higher is better 21 · 10 of 74 measured 147no reasoning 217no reasoning
Terminal-Bench Hard% of tasks, higher is better 65 · 100 of 190 measured 31.1% 17.4%medium reasoning
Time to first answer tokenseconds, lower is better 29 · 22 of 74 measured 1.05no reasoning 0.90no reasoning
τ²-bench telecom% of tasks, higher is better 30 · 76 of 193 measured 93.6% 75.7%medium reasoning

Quick answers

Is Qwen3.5-122B-A10B better than Nova 2 Lite?

Pick Qwen3.5-122B-A10B: it scores higher (Intelligence Index 17.7 against 13.4) at about the same price. Pick Nova 2 Lite only if speed matters more: it writes faster.

Which is cheaper, Qwen3.5-122B-A10B or Nova 2 Lite?

They cost about the same: $0.72 and $0.85 per million tokens (three input to one output).

Which is faster, Qwen3.5-122B-A10B or Nova 2 Lite?

Nova 2 Lite writes about 217 tokens a second on its usual API, against 147 for Qwen3.5-122B-A10B (Artificial Analysis).

Which is better for agents and tool use, Qwen3.5-122B-A10B or Nova 2 Lite?

Qwen3.5-122B-A10B ranks 95 of 164 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 133 for Nova 2 Lite.

Which is better for reasoning and knowledge, Qwen3.5-122B-A10B or Nova 2 Lite?

Qwen3.5-122B-A10B ranks 87 of 198 models on sale for hard questions across science, maths and general knowledge, against 116 for Nova 2 Lite.

Which is better for writing, Qwen3.5-122B-A10B or Nova 2 Lite?

Qwen3.5-122B-A10B ranks 102 of 188 models on sale for what people prefer in blind comparisons, and judged writing quality, against 169 for Nova 2 Lite.

Which is better for sticking to the facts, Qwen3.5-122B-A10B or Nova 2 Lite?

Nova 2 Lite ranks 73 of 152 models on sale for summarising without inventing things, and factual answers, against 108 for Qwen3.5-122B-A10B.

Which has the bigger context window, Qwen3.5-122B-A10B or Nova 2 Lite?

Nova 2 Lite: 1,000,000 tokens, against 262,144 for Qwen3.5-122B-A10B.

Run Qwen3.5-122B-A10B and Nova 2 Lite on your own prompt

Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.

Try the playgroundTalk to us