Compare · ModelsLive · 2 picked · head to head
DeepSeek V4 Pro vs Gemini 3.6 Flash
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemini 3.6 Flash wins on 11/12 benchmarks
Gemini 3.6 Flash wins 11 of 12 shared benchmarks. Leads in knowledge · general · coding.
Category leads
knowledge·Gemini 3.6 Flashgeneral·Gemini 3.6 Flashcoding·Gemini 3.6 Flashmath·Gemini 3.6 Flash
Hype vs Reality
Attention vs performance
DeepSeek V4 Pro
#89 by perf·#6 by attention
Gemini 3.6 Flash
#91 by perf·#5 by attention
Best value
DeepSeek V4 Pro
7.2x better value than Gemini 3.6 Flash
DeepSeek V4 Pro
172.1 pts/$
$0.31/M
Gemini 3.6 Flash
23.9 pts/$
$2.25/M
Vendor risk
Mixed exposure
One or more vendors flagged
DeepSeek
$3.4B·Tier 1
Google DeepMind
$4.20T·Tier 1
Head to head
12 benchmarks · 2 models
DeepSeek V4 ProGemini 3.6 Flash
Chess Puzzles
Gemini 3.6 Flash leads by +24.2
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
DeepSeek V4 Pro
15.8
Gemini 3.6 Flash
40.0
Dtbench
Gemini 3.6 Flash leads by +8.0
DeepSeek V4 Pro
84.5
Gemini 3.6 Flash
92.5
Frontiercode
Gemini 3.6 Flash leads by +16.7
DeepSeek V4 Pro
17.6
Gemini 3.6 Flash
34.4
FrontierMath-Tier-4-v2-Private
Gemini 3.6 Flash leads by +19.5
DeepSeek V4 Pro
2.4
Gemini 3.6 Flash
21.9
FrontierMath-Tiers-1-3-v2-Private
Gemini 3.6 Flash leads by +13.7
DeepSeek V4 Pro
45.3
Gemini 3.6 Flash
59.0
GPQA diamond
Gemini 3.6 Flash leads by +4.3
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
DeepSeek V4 Pro
87.9
Gemini 3.6 Flash
92.2
Lmca
Gemini 3.6 Flash leads by +4.4
DeepSeek V4 Pro
48.5
Gemini 3.6 Flash
52.9
Mystery Game Puzzles
Gemini 3.6 Flash leads by +14.3
DeepSeek V4 Pro
8.6
Gemini 3.6 Flash
22.9
OTIS Mock AIME 2024-2025
DeepSeek V4 Pro leads by +2.5
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
DeepSeek V4 Pro
96.7
Gemini 3.6 Flash
94.2
Proofbench
Gemini 3.6 Flash leads by +20.0
DeepSeek V4 Pro
16.0
Gemini 3.6 Flash
36.0
SimpleQA Verified
Gemini 3.6 Flash leads by +19.2
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
DeepSeek V4 Pro
47.0
Gemini 3.6 Flash
66.2
WeirdML
Gemini 3.6 Flash leads by +7.2
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
DeepSeek V4 Pro
48.9
Gemini 3.6 Flash
56.1
Full benchmark table
| Benchmark | DeepSeek V4 Pro | Gemini 3.6 Flash |
|---|---|---|
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 15.8 | 40.0 |
Dtbench | 84.5 | 92.5 |
Frontiercode | 17.6 | 34.4 |
FrontierMath-Tier-4-v2-Private | 2.4 | 21.9 |
FrontierMath-Tiers-1-3-v2-Private | 45.3 | 59.0 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 87.9 | 92.2 |
Lmca | 48.5 | 52.9 |
Mystery Game Puzzles | 8.6 | 22.9 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 96.7 | 94.2 |
Proofbench | 16.0 | 36.0 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 47.0 | 66.2 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 48.9 | 56.1 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.21 | $0.42 | 1.0M tokens (~524 books) | $2.61 | |
| $0.75 | $3.75 | 1.0M tokens (~524 books) | $15.00 |