Compare / DeepSeek-V3.2 vs DeepSeek-V4-Flash (0423)
DeepSeek-V3.2 vs DeepSeek-V4-Flash (0423)
Which is cheaper, which is more capable, and which does better at each kind of work, from 19 results on 3 sources that measured both models.
Of the 19 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.
Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee).
DeepSeek-V3.2 or DeepSeek-V4-Flash (0423)? The short answer
Pick DeepSeek-V4-Flash (0423): it scores higher (Intelligence Index 24.4 against 21.5) and costs less.
- DeepSeek-V4-Flash (0423) is cheaper: $0.15 against $0.32 per million tokens, 2.1 times less.
- DeepSeek-V4-Flash (0423) scores higher on the Artificial Analysis Intelligence Index: 24.4 against 21.5.
- DeepSeek-V4-Flash (0423) is newer: released 24 Apr 2026, against 1 Dec 2025 for DeepSeek-V3.2.
- On third-party benchmarks, on the results both models have: DeepSeek-V4-Flash (0423) does better for agents and tool use and reasoning and knowledge.
Head to head
Every fact side by side
| DeepSeek-V3.2 | DeepSeek-V4-Flash (0423) | |
|---|---|---|
| Price per million tokens | $0.28 in · $0.42 out | $0.050 in · $0.45 out |
| Blended (3 in : 1 out) | $0.32 | $0.15 |
| Cheapest host, blended | $0.23 (GMICloud, FP8) | $0.10 (StreamLake, FP8) |
| Intelligence Index | 21.5 | 24.4 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | – | – |
| Context window | 163,840 tokens | 1,048,576 tokens |
| Released | 1 Dec 2025 | 24 Apr 2026 (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 | DeepSeek-V3.2 | DeepSeek-V4-Flash (0423) |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Overall · TextArena rating, higher is better 106 · 85 of 387 measured | 1,425 | 1,438high reasoning |
| Overall · Text factualityArena rating, higher is better 85 · 81 of 163 measured | 1,437 | 1,439 |
| Business, management and finance · TextArena rating, higher is better 102 · 91 of 380 measured | 1,423thinking reasoning | 1,439 |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 102 · 85 of 249 measured | 21.5thinking reasoning | 24.4high reasoning |
| GPQA Diamond% of questions, higher is better 90 · 52 of 232 measured | 84.0%thinking reasoning | 89.4%max reasoning |
| Humanity's Last Exam% of questions, higher is better 101 · 67 of 250 measured | 24.6%thinking reasoning | 34.8%max reasoning |
| UGI Leaderboard reported by UGI Leaderboard · 3 results | ||
| Writing score · UGIscore out of 100, higher is better 54 · 60 of 230 measured | 57.3thinking reasoning | 54.6no reasoning |
| Requested-length error · UGI% off the requested word count, lower is better 151 · 54 of 230 measured | 26.0%no reasoning | 12.0%thinking reasoning |
| Style adherence · UGIscore from 0 to 1, higher is better 55 · 55 of 230 measured | 0.37thinking reasoning | 0.37thinking reasoning |
Show all 19 results (10 more)
| Measure | DeepSeek-V3.2 | DeepSeek-V4-Flash (0423) |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results | ||
| Creative writing · TextArena rating, higher is better 93 · 78 of 385 measured | 1,401 | 1,410high reasoning |
| Expert prompts · TextArena rating, higher is better 94 · 83 of 338 measured | 1,452thinking reasoning | 1,466high reasoning |
| Instruction following · TextArena rating, higher is better 94 · 79 of 387 measured | 1,420 | 1,433high reasoning |
| Writing, literature and language · TextArena rating, higher is better 91 · 78 of 386 measured | 1,410 | 1,422high reasoning |
| Artificial Analysis reported by Artificial Analysis · 6 results | ||
| Terminal-Bench 2.1% of tasks, higher is better 66 · 46 of 131 measured | 46.8%thinking reasoning | 61.8%max reasoning |
| Artificial Analysis Coding Indexindex score, higher is better 66 · 45 of 130 measured | 44.2thinking reasoning | 56.2max reasoning |
| IFBench% of instructions, higher is better 79 · 7 of 195 measured | 60.7%thinking reasoning | 79.2%max reasoning |
| Long-context reasoning (AA-LCR)% of questions, higher is better 98 · 89 of 241 measured | 73.3%thinking reasoning | 74.3%max reasoning |
| Terminal-Bench Hard% of tasks, higher is better 47 · 37 of 190 measured | 35.6%thinking reasoning | 38.6%high reasoning |
| τ²-bench telecom% of tasks, higher is better 40 · 16 of 193 measured | 90.6%thinking reasoning | 95.6%high reasoning |
Quick answers
Is DeepSeek-V3.2 better than DeepSeek-V4-Flash (0423)?
Pick DeepSeek-V4-Flash (0423): it scores higher (Intelligence Index 24.4 against 21.5) and costs less.
Which is cheaper, DeepSeek-V3.2 or DeepSeek-V4-Flash (0423)?
DeepSeek-V4-Flash (0423) is cheaper: $0.15 against $0.32 per million tokens, 2.1 times less.
Which is better for agents and tool use, DeepSeek-V3.2 or DeepSeek-V4-Flash (0423)?
DeepSeek-V4-Flash (0423) ranks 59 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 93 for DeepSeek-V3.2.
Which is better for reasoning and knowledge, DeepSeek-V3.2 or DeepSeek-V4-Flash (0423)?
DeepSeek-V4-Flash (0423) ranks 69 of 187 models on sale for hard questions across science, maths and general knowledge, against 93 for DeepSeek-V3.2.
Which is better for writing, DeepSeek-V3.2 or DeepSeek-V4-Flash (0423)?
DeepSeek-V4-Flash (0423) ranks 63 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 65 for DeepSeek-V3.2.
Which is better for sticking to the facts, DeepSeek-V3.2 or DeepSeek-V4-Flash (0423)?
DeepSeek-V3.2 ranks 58 of 139 models on sale for summarising without inventing things, and factual answers, against 81 for DeepSeek-V4-Flash (0423).
Which has the bigger context window, DeepSeek-V3.2 or DeepSeek-V4-Flash (0423)?
DeepSeek-V4-Flash (0423): 1,048,576 tokens, against 163,840 for DeepSeek-V3.2.
Run DeepSeek-V3.2 and DeepSeek-V4-Flash (0423) on your own prompt.
Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.