Compare / Qwen3-235B-A22B-Instruct-2507 vs DeepSeek-V3.1-Terminus
Qwen3-235B-A22B-Instruct-2507 vs DeepSeek-V3.1-Terminus
Which is cheaper, which is more capable, and which does better at each kind of work, from 15 results on 3 sources that measured both models.
Of the 15 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 DeepSeek, every model from both labs.
Qwen3-235B-A22B-Instruct-2507 or DeepSeek-V3.1-Terminus? The short answer
Pick DeepSeek-V3.1-Terminus if quality matters most: it scores higher (Intelligence Index 14.8 against 12.0). Pick Qwen3-235B-A22B-Instruct-2507 if cost matters more: it costs 34% less per token.
- Qwen3-235B-A22B-Instruct-2507 is cheaper: $0.30 against $0.45 per million tokens, 34% less.
- DeepSeek-V3.1-Terminus scores higher on the Artificial Analysis Intelligence Index: 14.8 against 12.0.
- DeepSeek-V3.1-Terminus is newer: released 22 Sep 2025, against 21 Jul 2025 for Qwen3-235B-A22B-Instruct-2507.
- On third-party benchmarks, on the results both models have: DeepSeek-V3.1-Terminus does better for reasoning and knowledge and writing.
Head to head
Every fact side by side
| Qwen3-235B-A22B-Instruct-2507 | DeepSeek-V3.1-Terminus | |
|---|---|---|
| Price per million tokens | $0.15 in · $0.75 out | $0.27 in · $1.00 out |
| Blended (3 in : 1 out) | $0.30 | $0.45 |
| Cheapest host, blended | $0.15 (GMICloud, FP8) | $0.45 (SiliconFlow, FP8) |
| Intelligence Index | 12.0 | 14.8 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | – | – |
| Context window | 262,144 tokens | 163,840 tokens |
| Released | 21 Jul 2025 | 22 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 | DeepSeek-V3.1-Terminus |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Overall · TextArena rating, higher is better 109 · 115 of 387 measured | 1,422 | 1,417thinking reasoning |
| Business, management and finance · TextArena rating, higher is better 97 · 103 of 380 measured | 1,432 | 1,423thinking reasoning |
| Creative writing · TextArena rating, higher is better 122 · 87 of 385 measured | 1,378 | 1,405 |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 153 · 129 of 243 measured | 12.0 | 14.8thinking reasoning |
| GPQA Diamond% of questions, higher is better 136 · 112 of 231 measured | 75.3% | 79.2%thinking reasoning |
| Humanity's Last Exam% of questions, higher is better 144 · 121 of 242 measured | 11.1% | 16.4%thinking reasoning |
| UGI Leaderboard reported by UGI Leaderboard · 3 results | ||
| Writing score · UGIscore out of 100, higher is better 80 · 64 of 230 measured | 49.0 | 54.0thinking reasoning |
| Requested-length error · UGI% off the requested word count, lower is better 69 · 174 of 230 measured | 15.0% | 32.0%thinking reasoning |
| Style adherence · UGIscore from 0 to 1, higher is better 64 · 43 of 230 measured | 0.36 | 0.37thinking reasoning |
Show all 15 results (6 more)
| Measure | Qwen3-235B-A22B-Instruct-2507 | DeepSeek-V3.1-Terminus |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 2 results | ||
| Instruction following · TextArena rating, higher is better 104 · 93 of 387 measured | 1,414 | 1,420thinking reasoning |
| Writing, literature and language · TextArena rating, higher is better 115 · 88 of 386 measured | 1,396 | 1,412thinking reasoning |
| Artificial Analysis reported by Artificial Analysis · 4 results | ||
| IFBench% of instructions, higher is better 113 · 86 of 195 measured | 46.1% | 57.0%thinking reasoning |
| Long-context reasoning (AA-LCR)% of questions, higher is better 177 · 113 of 233 measured | 33.9% | 69.3%thinking reasoning |
| Terminal-Bench Hard% of tasks, higher is better 110 · 63 of 190 measured | 15.2% | 31.8%no reasoning |
| τ²-bench telecom% of tasks, higher is better 127 · 118 of 193 measured | 33.3% | 37.1%no reasoning |
Compare them with other models
Quick answers
Is Qwen3-235B-A22B-Instruct-2507 better than DeepSeek-V3.1-Terminus?
Pick DeepSeek-V3.1-Terminus if quality matters most: it scores higher (Intelligence Index 14.8 against 12.0). Pick Qwen3-235B-A22B-Instruct-2507 if cost matters more: it costs 34% less per token.
Which is cheaper, Qwen3-235B-A22B-Instruct-2507 or DeepSeek-V3.1-Terminus?
Qwen3-235B-A22B-Instruct-2507 is cheaper: $0.30 against $0.45 per million tokens, 34% less.
Which is better for agents and tool use, Qwen3-235B-A22B-Instruct-2507 or DeepSeek-V3.1-Terminus?
Qwen3-235B-A22B-Instruct-2507 ranks 51 of 164 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 88 for DeepSeek-V3.1-Terminus.
Which is better for reasoning and knowledge, Qwen3-235B-A22B-Instruct-2507 or DeepSeek-V3.1-Terminus?
DeepSeek-V3.1-Terminus ranks 109 of 198 models on sale for hard questions across science, maths and general knowledge, against 129 for Qwen3-235B-A22B-Instruct-2507.
Which is better for writing, Qwen3-235B-A22B-Instruct-2507 or DeepSeek-V3.1-Terminus?
DeepSeek-V3.1-Terminus ranks 81 of 188 models on sale for what people prefer in blind comparisons, and judged writing quality, against 85 for Qwen3-235B-A22B-Instruct-2507.
Which has the bigger context window, Qwen3-235B-A22B-Instruct-2507 or DeepSeek-V3.1-Terminus?
Qwen3-235B-A22B-Instruct-2507: 262,144 tokens, against 163,840 for DeepSeek-V3.1-Terminus.
Run Qwen3-235B-A22B-Instruct-2507 and DeepSeek-V3.1-Terminus on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.