Compare · ModelsLive · 2 picked · head to head
DeepSeek-V2 (MoE-236B, May 2024) vs phi-3-mini 3.8B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
DeepSeek-V2 (MoE-236B, May 2024) wins on 6/6 benchmarks
DeepSeek-V2 (MoE-236B, May 2024) wins 6 of 6 shared benchmarks. Leads in knowledge · reasoning.
Category leads
knowledge·DeepSeek-V2 (MoE-236B, May 2024)reasoning·DeepSeek-V2 (MoE-236B, May 2024)
Hype vs Reality
Attention vs performance
DeepSeek-V2 (MoE-236B, May 2024)
#8 by perf·no signal
phi-3-mini 3.8B
#34 by perf·no signal
Best value
Pricing unknown
DeepSeek-V2 (MoE-236B, May 2024)
—
no price
phi-3-mini 3.8B
—
no price
Vendor risk
Mixed exposure
One or more vendors flagged
DeepSeek
$3.4B·Tier 1
Microsoft
$3.00T·Big Tech
Head to head
6 benchmarks · 2 models
DeepSeek-V2 (MoE-236B, May 2024)phi-3-mini 3.8B
ARC AI2
DeepSeek-V2 (MoE-236B, May 2024) leads by +9.7
AI2 Reasoning Challenge · tests grade-school level science knowledge with multiple-choice questions requiring reasoning beyond simple retrieval.
DeepSeek-V2 (MoE-236B, May 2024)
89.6
phi-3-mini 3.8B
79.9
BBH
DeepSeek-V2 (MoE-236B, May 2024) leads by +9.5
BIG-Bench Hard · a curated subset of 23 challenging tasks from BIG-Bench where language models previously failed to outperform average humans.
DeepSeek-V2 (MoE-236B, May 2024)
71.7
phi-3-mini 3.8B
62.3
HellaSwag
DeepSeek-V2 (MoE-236B, May 2024) leads by +13.9
HellaSwag · tests commonsense reasoning by asking models to predict the most plausible continuation of everyday scenarios.
DeepSeek-V2 (MoE-236B, May 2024)
82.8
phi-3-mini 3.8B
68.9
MMLU
DeepSeek-V2 (MoE-236B, May 2024) leads by +12.8
Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.
DeepSeek-V2 (MoE-236B, May 2024)
71.2
phi-3-mini 3.8B
58.4
TriviaQA
DeepSeek-V2 (MoE-236B, May 2024) leads by +16.0
TriviaQA · reading comprehension benchmark with trivia questions, requiring models to find and reason over evidence from provided documents.
DeepSeek-V2 (MoE-236B, May 2024)
80.0
phi-3-mini 3.8B
64.0
Winogrande
DeepSeek-V2 (MoE-236B, May 2024) leads by +31.0
WinoGrande · large-scale commonsense reasoning benchmark where models must resolve ambiguous pronouns in carefully constructed sentence pairs.
DeepSeek-V2 (MoE-236B, May 2024)
72.6
phi-3-mini 3.8B
41.6
Full benchmark table
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | phi-3-mini 3.8B |
|---|---|---|
ARC AI2 AI2 Reasoning Challenge · tests grade-school level science knowledge with multiple-choice questions requiring reasoning beyond simple retrieval. | 89.6 | 79.9 |
BBH BIG-Bench Hard · a curated subset of 23 challenging tasks from BIG-Bench where language models previously failed to outperform average humans. | 71.7 | 62.3 |
HellaSwag HellaSwag · tests commonsense reasoning by asking models to predict the most plausible continuation of everyday scenarios. | 82.8 | 68.9 |
MMLU Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge. | 71.2 | 58.4 |
TriviaQA TriviaQA · reading comprehension benchmark with trivia questions, requiring models to find and reason over evidence from provided documents. | 80.0 | 64.0 |
Winogrande WinoGrande · large-scale commonsense reasoning benchmark where models must resolve ambiguous pronouns in carefully constructed sentence pairs. | 72.6 | 41.6 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| DeepSeek-V2 (MoE-236B, May 2024) | — | — | — | — |
| phi-3-mini 3.8B | — | — | — | — |
People also compared
DeepSeek-V2 (MoE-236B, May 2024) vs GPT-5 ChatClaude Mythos Preview vs DeepSeek-V2 (MoE-236B, May 2024)DeepSeek-V2 (MoE-236B, May 2024) vs Qwen3.5 397B A17BDeepSeek-V2 (MoE-236B, May 2024) vs DeepSeek V3.2 SpecialeClaude Instant vs DeepSeek-V2 (MoE-236B, May 2024)DeepSeek-V2 (MoE-236B, May 2024) vs Step 3.5 FlashDeepSeek-V2 (MoE-236B, May 2024) vs MiMo-V2-FlashDeepSeek-V2 (MoE-236B, May 2024) vs GPT-5.1-Codex-Max