Compare / Qwen3.5-122B-A10B vs GPT-5.4
Qwen3.5-122B-A10B vs GPT-5.4
Which is cheaper, which is more capable, and which does better at each kind of work, from 22 results on 4 sources that measured both models.
Of the 22 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 OpenAI, every model from both labs.
Qwen3.5-122B-A10B or GPT-5.4? The short answer
Pick GPT-5.4 if quality matters most: it scores higher (Intelligence Index 39.0 against 17.7). Pick Qwen3.5-122B-A10B if cost matters more: it costs 7.9 times less per token.
- Qwen3.5-122B-A10B is cheaper: $0.72 against $5.62 per million tokens, 7.9 times less.
- GPT-5.4 scores higher on the Artificial Analysis Intelligence Index: 39.0 against 17.7.
- GPT-5.4 is newer: released 5 Mar 2026, against 24 Feb 2026 for Qwen3.5-122B-A10B.
- On third-party benchmarks, on the results both models have: GPT-5.4 does better for agents and tool use, reasoning and knowledge, writing and sticking to the facts.
Head to head
Every fact side by side
| Qwen3.5-122B-A10B | GPT-5.4 | |
|---|---|---|
| Price per million tokens | $0.26 in · $2.08 out | $2.50 in · $15.00 out |
| Blended (3 in : 1 out) | $0.72 | $5.62 |
| Cheapest host, blended | $0.72 (Alibaba) | $5.62 (Azure) |
| Cached input, per million | – | $0.25 cached input |
| Intelligence Index | 17.7 | 39.0 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | 147 | – |
| Context window | 262,144 tokens | 1,050,000 tokens |
| Released | 24 Feb 2026 | 5 Mar 2026 (newer) |
| Weights | Open | Closed |
| Developer based in | China | the 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.
From our research
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.
| Measure | Qwen3.5-122B-A10B | GPT-5.4 |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Overall · TextArena rating, higher is better 117 · 29 of 387 measured | 1,416 | 1,475high reasoning |
| Overall · Text factualityArena rating, higher is better 103 · 7 of 163 measured | 1,428 | 1,485high reasoning |
| Business, management and finance · TextArena rating, higher is better 105 · 20 of 380 measured | 1,422 | 1,482high reasoning |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 114 · 30 of 243 measured | 17.7no reasoning | 39.0xhigh reasoning |
| GPQA Diamond% of questions, higher is better 75 · 24 of 231 measured | 85.7% | 92.0%xhigh reasoning |
| Humanity's Last Exam% of questions, higher is better 92 · 23 of 242 measured | 25.2% | 43.7%xhigh reasoning |
| UGI Leaderboard reported by UGI Leaderboard · 3 results | ||
| Writing score · UGIscore out of 100, higher is better 112 · 14 of 230 measured | 39.5no reasoning | 68.8high reasoning |
| Requested-length error · UGI% off the requested word count, lower is better 33 · 166 of 230 measured | 9.0%thinking reasoning | 30.0%xhigh reasoning |
| Style adherence · UGIscore from 0 to 1, higher is better 83 · 14 of 230 measured | 0.36no reasoning | 0.40high reasoning |
| Vectara Hallucination Leaderboard reported by Vectara Hallucination Leaderboard · 2 results | ||
| Hallucination rate · Vectara% of summaries, lower is better 72 · 32 of 104 measured | 11.2% | 7.0% |
| Answer rate · Vectara% of documents, higher is better 31 · 17 of 104 measured | 99.8% | 99.9% |
Show all 22 results (11 more)
| Measure | Qwen3.5-122B-A10B | GPT-5.4 |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results | ||
| Creative writing · TextArena rating, higher is better 136 · 46 of 385 measured | 1,366 | 1,442high reasoning |
| Expert prompts · TextArena rating, higher is better 111 · 19 of 338 measured | 1,442 | 1,515high reasoning |
| Instruction following · TextArena rating, higher is better 115 · 30 of 387 measured | 1,406 | 1,471high reasoning |
| Writing, literature and language · TextArena rating, higher is better 125 · 25 of 386 measured | 1,387 | 1,465high reasoning |
| Artificial Analysis reported by Artificial Analysis · 7 results | ||
| Terminal-Bench 2.1% of tasks, higher is better 64 · 29 of 130 measured | 47.6% | 78.3%xhigh reasoning |
| τ-bench banking% of tasks, higher is better 58 · 19 of 121 measured | 15.3% | 39.6%xhigh reasoning |
| Artificial Analysis Coding Indexindex score, higher is better 65 · 26 of 131 measured | 45.7 | 71.1xhigh reasoning |
| IFBench% of instructions, higher is better 22 · 31 of 195 measured | 75.7% | 73.9%xhigh reasoning |
| Long-context reasoning (AA-LCR)% of questions, higher is better 72 · 24 of 233 measured | 76.3% | 82.0%xhigh reasoning |
| Terminal-Bench Hard% of tasks, higher is better 65 · 6 of 190 measured | 31.1% | 57.6%xhigh reasoning |
| τ²-bench telecom% of tasks, higher is better 30 · 49 of 193 measured | 93.6% | 87.1%xhigh reasoning |
Compare them with other models
Quick answers
Is Qwen3.5-122B-A10B better than GPT-5.4?
Pick GPT-5.4 if quality matters most: it scores higher (Intelligence Index 39.0 against 17.7). Pick Qwen3.5-122B-A10B if cost matters more: it costs 7.9 times less per token.
Which is cheaper, Qwen3.5-122B-A10B or GPT-5.4?
Qwen3.5-122B-A10B is cheaper: $0.72 against $5.62 per million tokens, 7.9 times less.
Which is better for agents and tool use, Qwen3.5-122B-A10B or GPT-5.4?
GPT-5.4 ranks 24 of 164 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 95 for Qwen3.5-122B-A10B.
Which is better for reasoning and knowledge, Qwen3.5-122B-A10B or GPT-5.4?
GPT-5.4 ranks 26 of 198 models on sale for hard questions across science, maths and general knowledge, against 87 for Qwen3.5-122B-A10B.
Which is better for writing, Qwen3.5-122B-A10B or GPT-5.4?
GPT-5.4 ranks 22 of 188 models on sale for what people prefer in blind comparisons, and judged writing quality, against 102 for Qwen3.5-122B-A10B.
Which is better for sticking to the facts, Qwen3.5-122B-A10B or GPT-5.4?
GPT-5.4 ranks 37 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 GPT-5.4?
GPT-5.4: 1,050,000 tokens, against 262,144 for Qwen3.5-122B-A10B.
Run Qwen3.5-122B-A10B and GPT-5.4 on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.