DeepSeek V3.2 vs Mistral Medium 3.5 128B
At a Glance
| Compare |  DeepSeek V3.2DeepSeek |  Mistral Medium 3.5 128BMistral AI |
|---|---|---|
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | $0.26Deepinfra ↗ · Sep 23, 2026 | Not reported |
| Output priceFrom · USD / 1M tokens | $0.38Deepinfra ↗ · Sep 23, 2026 | Not reported |
| Context windowMaximum documented tokens | 164K | 262K |
| Model facts checked | Aug 28, 2026View model evidence → | Aug 28, 2026View model evidence → |
Token prices are the lowest available sourced USD rates; input and output may use different providers. Cost ranking estimates output spend on LiveBench, not a full request bill. Ranking methodology →
Available Benchmarks
| Benchmark | DeepSeek-V3.2 | Mistral-Medium-3.5-128B |
|---|---|---|
| LMArena Text Arenatext-2026-09-13-d25aabda0010 · arena_rating · statistical tie | 1,424.80100% of row best · rating · deepseek-v3.2; 95% CI [1421.27271719, 1428.32733406]; votes 46458; rank 96 | 1,420.58100% of row best · rating · mistral-medium-3.5; 95% CI [1414.04225396, 1427.11615611]; votes 10996; rank 104 |
| Overall ResultCounted from the protocol-matched rows above · 1 tie | 0 benchmark winsNo overall winner | 0 benchmark winsNo overall winner |
Third-party benchmark Only like-for-like primary-publisher results are shown; raw scores, relative scores, configuration, and token spend remain visible.
Side-by-Side Facts
| Field | DeepSeek-V3.2 | Mistral-Medium-3.5-128B |
|---|---|---|
| Developer | DeepSeek | Mistral AI |
| Family | Deepseek V3 2 | Mistral Medium 3 5 128b |
| Model | DeepSeek-V3.2 | Mistral-Medium-3.5-128B |
| Version | DeepSeek-V3.2 | Mistral-Medium-3.5-128B |
| Lifecycle | active | active |
| Released | 2025-12-01 | Unknown |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text | Text, Image |
| Output modalities | Text | Text |
| Context window | 164K | 262K |
| Total parameters | 685.4B | 127.7B |
| Active parameters | Unknown | Unknown |
| License | mit | other |
| Open weights | Yes | Yes |
| API available | Yes | Unknown |
| Self-hostable | Yes | Yes |
| Provider access | Deepinfra (Standard), Hugging Face (Standard), Openrouter (Standard) | Unknown |
| Capabilities | chat, generation, reasoning | chat, generation, reasoning, tools |
DeepSeek V3.2 Capabilities
Mistral Medium 3.5 128B Capabilities
Related Comparisons
All text comparisons →| A | Pair | B | Context |
|---|---|---|---|
DeepSeek-V3.2DeepSeek | vs |  GPT-6 AstraOpenAI | cross-developer peerstext |
Claude Fable 5.1Anthropic | vs | DeepSeek-V3.2DeepSeek | cross-developer peerstext |
DeepSeek-V3.2DeepSeek | vs |  Gemini 3.1 ProGoogle DeepMind | cross-developer peerstext |
DeepSeek-V3.2DeepSeek | vs | DeepSeek-V4.1-FlashDeepSeek | family variantstext |
DeepSeek-V3.2DeepSeek | vs | Grok 4.6xAI | cross-developer peerstext |
DeepSeek-V3.2DeepSeek | vs |  Qwen3.8-MaxQwen | cross-developer peerstext |
DeepSeek-V3.2DeepSeek | vs |  Kimi-K3Moonshot AI | cross-developer peerstext |
 MiniMax-M3MiniMax | vs | DeepSeek-V3.2DeepSeek | cross-developer peerstext |
DeepSeek-V3.2DeepSeek | vs |  GLM-5.3Z.ai | cross-developer peerstext |
DeepSeek-V3.2DeepSeek | vs |  Hy4 previewTencent | cross-developer peerstext |
Seed 2.1 ProByteDance Seed | vs | DeepSeek-V3.2DeepSeek | cross-developer peerstext |
DeepSeek-V3.2DeepSeek | vs | Mistral Large 3Mistral AI | cross-developer peerstext |
Primary Evidence
Sources and Freshness
Questions
DeepSeek V3.2 vs Mistral Medium 3.5 128B FAQs
Is DeepSeek V3.2 or Mistral Medium 3.5 128B better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both DeepSeek V3.2 and Mistral Medium 3.5 128B, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, DeepSeek V3.2 or Mistral Medium 3.5 128B?+
Only DeepSeek V3.2 has a directly sourced input price: $0.26 per million tokens. Only DeepSeek V3.2 has a directly sourced output price: $0.38 per million tokens.
Which has a larger context window, DeepSeek V3.2 or Mistral Medium 3.5 128B?+
Mistral Medium 3.5 128B has the larger sourced context window. DeepSeek V3.2 supports 164K and Mistral Medium 3.5 128B supports 262K.
Which performs better in benchmarks, DeepSeek V3.2 or Mistral Medium 3.5 128B?+
There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.
Can DeepSeek V3.2 or Mistral Medium 3.5 128B be self-hosted?+
Both models have the same recorded self-hosting status: supported. DeepSeek V3.2 is open weight; Mistral Medium 3.5 128B is open weight.
Can DeepSeek V3.2 and Mistral Medium 3.5 128B understand images?+
DeepSeek V3.2 is not documented with image input; Mistral Medium 3.5 128B is documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, DeepSeek V3.2 or Mistral Medium 3.5 128B?+
Neither has a larger sourced maximum output. DeepSeek V3.2 is — and Mistral Medium 3.5 128B is —.
Do DeepSeek V3.2 and Mistral Medium 3.5 128B support reasoning and tool use?+
DeepSeek V3.2: reasoning. Mistral Medium 3.5 128B: reasoning, tool calling, and image input. Feature support does not establish relative quality.
Which is available from more inference providers, DeepSeek V3.2 or Mistral Medium 3.5 128B?+
DeepSeek V3.2 has 3 sourced provider routes; Mistral Medium 3.5 128B has 0, so DeepSeek V3.2 has broader tracked availability.
Which offers better value, DeepSeek V3.2 or Mistral Medium 3.5 128B?+
There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.