Compare / Qwen3-235B-A22B-Instruct-2507 vs Qwen3-Next-80B-A3B-Instruct
Qwen3-235B-A22B-Instruct-2507 vs Qwen3-Next-80B-A3B-Instruct
Which is cheaper, which is more capable, and which does better at each kind of work, from 17 results on 3 sources that measured both models.
Of the 17 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).
Qwen3-235B-A22B-Instruct-2507 or Qwen3-Next-80B-A3B-Instruct? The short answer
Pick Qwen3-235B-A22B-Instruct-2507: it scores higher (Intelligence Index 12.0 against 9.6) at about the same price.
- They cost about the same: $0.30 and $0.35 per million tokens (three input to one output).
- Qwen3-235B-A22B-Instruct-2507 scores higher on the Artificial Analysis Intelligence Index: 12.0 against 9.6.
- Qwen3-Next-80B-A3B-Instruct is newer: released 11 Sep 2025, against 21 Jul 2025 for Qwen3-235B-A22B-Instruct-2507.
- On third-party benchmarks, on the results both models have: Qwen3-235B-A22B-Instruct-2507 does better for reasoning and knowledge, writing and sticking to the facts.
Head to head
Every fact side by side
| Qwen3-235B-A22B-Instruct-2507 | Qwen3-Next-80B-A3B-Instruct | |
|---|---|---|
| Price per million tokens | $0.15 in · $0.75 out | $0.10 in · $1.10 out |
| Blended (3 in : 1 out) | $0.30 | $0.35 |
| Cheapest host, blended | $0.15 (GMICloud, FP8) | $0.27 (Alibaba) |
| Intelligence Index | 12.0 | 9.6 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | – | 179 |
| Context window | 262,144 tokens | 262,144 tokens |
| Released | 21 Jul 2025 | 11 Sep 2025 (newer) |
| Weights | Open | Open |
| Developer based in | China | China |
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.
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 | Qwen3-235B-A22B-Instruct-2507 | Qwen3-Next-80B-A3B-Instruct |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Overall · TextArena rating, higher is better 109 · 140 of 387 measured | 1,422 | 1,399 |
| Overall · Text factualityArena rating, higher is better 94 · 114 of 163 measured | 1,431 | 1,419 |
| Business, management and finance · TextArena rating, higher is better 97 · 122 of 380 measured | 1,432 | 1,412 |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 153 · 175 of 243 measured | 12.0 | 9.6 |
| GPQA Diamond% of questions, higher is better 136 · 143 of 231 measured | 75.3% | 73.8% |
| Humanity's Last Exam% of questions, higher is better 144 · 164 of 242 measured | 11.1% | 7.6% |
| UGI Leaderboard reported by UGI Leaderboard · 3 results | ||
| Writing score · UGIscore out of 100, higher is better 80 · 102 of 230 measured | 49.0 | 41.8 |
| Requested-length error · UGI% off the requested word count, lower is better 69 · 21 of 230 measured | 15.0% | 7.0% |
| Style adherence · UGIscore from 0 to 1, higher is better 64 · 196 of 230 measured | 0.36 | 0.31 |
Show all 17 results (8 more)
| Measure | Qwen3-235B-A22B-Instruct-2507 | Qwen3-Next-80B-A3B-Instruct |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results | ||
| Creative writing · TextArena rating, higher is better 122 · 190 of 385 measured | 1,378 | 1,313 |
| Expert prompts · TextArena rating, higher is better 103 · 155 of 338 measured | 1,447 | 1,400 |
| Instruction following · TextArena rating, higher is better 104 · 155 of 387 measured | 1,414 | 1,376 |
| Writing, literature and language · TextArena rating, higher is better 115 · 174 of 386 measured | 1,396 | 1,342 |
| Artificial Analysis reported by Artificial Analysis · 4 results | ||
| IFBench% of instructions, higher is better 113 · 136 of 195 measured | 46.1% | 39.7% |
| Long-context reasoning (AA-LCR)% of questions, higher is better 177 · 150 of 233 measured | 33.9% | 52.7% |
| Terminal-Bench Hard% of tasks, higher is better 110 · 135 of 190 measured | 15.2% | 7.6% |
| τ²-bench telecom% of tasks, higher is better 127 · 163 of 193 measured | 33.3% | 21.6% |
Quick answers
Is Qwen3-235B-A22B-Instruct-2507 better than Qwen3-Next-80B-A3B-Instruct?
Pick Qwen3-235B-A22B-Instruct-2507: it scores higher (Intelligence Index 12.0 against 9.6) at about the same price.
Which is cheaper, Qwen3-235B-A22B-Instruct-2507 or Qwen3-Next-80B-A3B-Instruct?
They cost about the same: $0.30 and $0.35 per million tokens (three input to one output).
Which is better for reasoning and knowledge, Qwen3-235B-A22B-Instruct-2507 or Qwen3-Next-80B-A3B-Instruct?
Qwen3-235B-A22B-Instruct-2507 ranks 129 of 198 models on sale for hard questions across science, maths and general knowledge, against 143 for Qwen3-Next-80B-A3B-Instruct.
Which is better for writing, Qwen3-235B-A22B-Instruct-2507 or Qwen3-Next-80B-A3B-Instruct?
Qwen3-235B-A22B-Instruct-2507 ranks 85 of 188 models on sale for what people prefer in blind comparisons, and judged writing quality, against 107 for Qwen3-Next-80B-A3B-Instruct.
Which is better for sticking to the facts, Qwen3-235B-A22B-Instruct-2507 or Qwen3-Next-80B-A3B-Instruct?
Qwen3-235B-A22B-Instruct-2507 ranks 98 of 152 models on sale for summarising without inventing things, and factual answers, against 118 for Qwen3-Next-80B-A3B-Instruct.
Run Qwen3-235B-A22B-Instruct-2507 and Qwen3-Next-80B-A3B-Instruct on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.