Compare · ModelsLive · 3 picked · head to head
DeepSeek V3 vs Claude 3.5 Sonnet vs GPT-4 (older v0314)
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
DeepSeek V3 wins on 8/17 benchmarks
DeepSeek V3 wins 8 of 17 shared benchmarks. Leads in math · reasoning.
Category leads
arena·Claude 3.5 Sonnetknowledge·Claude 3.5 Sonnetmath·DeepSeek V3coding·Claude 3.5 Sonnetlanguage·Claude 3.5 Sonnetreasoning·DeepSeek V3
Hype vs Reality
Attention vs performance
DeepSeek V3
#45 by perf·no signal
Claude 3.5 Sonnet
#129 by perf·no signal
GPT-4 (older v0314)
#72 by perf·no signal
Best value
DeepSeek V3
79.8x better value than GPT-4 (older v0314)
DeepSeek V3
97.5 pts/$
$0.60/M
Claude 3.5 Sonnet
—
no price
GPT-4 (older v0314)
1.2 pts/$
$45.00/M
Vendor risk
Mixed exposure
One or more vendors flagged
DeepSeek
$3.4B·Tier 1
Anthropic
$380.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
17 benchmarks · 3 models
DeepSeek V3Claude 3.5 SonnetGPT-4 (older v0314)
Chatbot Arena Elo · Overall
Claude 3.5 Sonnet leads by +13.2
DeepSeek V3
1358.2
Claude 3.5 Sonnet
1371.4
GPT-4 (older v0314)
1285.8
GPQA diamond
DeepSeek V3 leads by +3.3
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
DeepSeek V3
42.0
Claude 3.5 Sonnet
38.7
GPT-4 (older v0314)
14.3
MMLU
DeepSeek V3 leads by +0.9
Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.
DeepSeek V3
82.9
Claude 3.5 Sonnet
82.0
GPT-4 (older v0314)
81.9
OTIS Mock AIME 2024-2025
DeepSeek V3 leads by +9.3
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
DeepSeek V3
15.8
Claude 3.5 Sonnet
6.4
GPT-4 (older v0314)
0.5
Aider · Code Editing
Claude 3.5 Sonnet leads by +18.0
Claude 3.5 Sonnet
84.2
GPT-4 (older v0314)
66.2
Aider polyglot
Claude 3.5 Sonnet leads by +3.2
Aider Polyglot · measures how well AI models can edit code across multiple programming languages using the Aider coding assistant framework.
DeepSeek V3
48.4
Claude 3.5 Sonnet
51.6
FrontierMath-2025-02-28-Private
DeepSeek V3 leads by +0.7
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
DeepSeek V3
1.7
Claude 3.5 Sonnet
1.0
HELM · GPQA
Claude 3.5 Sonnet leads by +2.7
DeepSeek V3
53.8
Claude 3.5 Sonnet
56.5
HELM · IFEval
Claude 3.5 Sonnet leads by +2.4
DeepSeek V3
83.2
Claude 3.5 Sonnet
85.6
HELM · MMLU-Pro
Claude 3.5 Sonnet leads by +5.4
DeepSeek V3
72.3
Claude 3.5 Sonnet
77.7
HELM · Omni-MATH
DeepSeek V3 leads by +12.7
DeepSeek V3
40.3
Claude 3.5 Sonnet
27.6
HELM · WildBench
DeepSeek V3 leads by +3.9
DeepSeek V3
83.1
Claude 3.5 Sonnet
79.2
Lech Mazur Writing
Claude 3.5 Sonnet leads by +3.3
Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication.
DeepSeek V3
77.0
Claude 3.5 Sonnet
80.3
MATH level 5
DeepSeek V3 leads by +13.2
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
DeepSeek V3
64.8
Claude 3.5 Sonnet
51.7
SimpleBench
Claude 3.5 Sonnet leads by +10.3
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
DeepSeek V3
2.7
Claude 3.5 Sonnet
13.0
WeirdML
DeepSeek V3 leads by +5.1
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
DeepSeek V3
36.1
Claude 3.5 Sonnet
31.0
Winogrande
GPT-4 (older v0314) leads by +4.6
WinoGrande · large-scale commonsense reasoning benchmark where models must resolve ambiguous pronouns in carefully constructed sentence pairs.
DeepSeek V3
70.4
GPT-4 (older v0314)
75.0
Full benchmark table
| Benchmark | DeepSeek V3 | Claude 3.5 Sonnet | GPT-4 (older v0314) |
|---|---|---|---|
Chatbot Arena Elo · Overall | 1358.2 | 1371.4 | 1285.8 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 42.0 | 38.7 | 14.3 |
MMLU Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge. | 82.9 | 82.0 | 81.9 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 15.8 | 6.4 | 0.5 |
Aider · Code Editing | — | 84.2 | 66.2 |
Aider polyglot Aider Polyglot · measures how well AI models can edit code across multiple programming languages using the Aider coding assistant framework. | 48.4 | 51.6 | — |
FrontierMath-2025-02-28-Private FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning. | 1.7 | 1.0 | — |
HELM · GPQA | 53.8 | 56.5 | — |
HELM · IFEval | 83.2 | 85.6 | — |
HELM · MMLU-Pro | 72.3 | 77.7 | — |
HELM · Omni-MATH | 40.3 | 27.6 | — |
HELM · WildBench | 83.1 | 79.2 | — |
Lech Mazur Writing Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication. | 77.0 | 80.3 | — |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 64.8 | 51.7 | — |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 2.7 | 13.0 | — |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 36.1 | 31.0 | — |
Winogrande WinoGrande · large-scale commonsense reasoning benchmark where models must resolve ambiguous pronouns in carefully constructed sentence pairs. | 70.4 | — | 75.0 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.32 | $0.89 | 164K tokens (~82 books) | $4.63 | |
| — | — | — | — | |
| $30.00 | $60.00 | 8K tokens (~4 books) | $375.00 |