DeepSeek V4 Flash 0731 vs Llama 3.3 70B Instruct
DeepSeek V4 Flash 0731 leads Llama 3.3 70B Instruct on the Artificial Analysis Intelligence Index, 34.3 to 7.7, and DeepSeek V4 Flash 0731 costs 2.6x less per output token ($0.28 vs $0.72 per million). Updated October 21, 2026; 12 benchmarks have a result for both.
DeepSeek V4 Flash 0731 or Llama 3.3 70B Instruct: which to pick
Only DeepSeek V4 Flash 0731 has a coding score, 51.8 on the Vibe Coding Index; Llama 3.3 70B Instruct has none, so the two cannot be ranked on coding.
Compare them on price, context and the boards below.
- Shared results
- 12
- DeepSeek V4 Flash 0731 only
- 43
- Llama 3.3 70B Instruct only
- 40
- Like-for-like categories
- 5 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Only DeepSeek V4 Flash 0731 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 34.3 against 7.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only DeepSeek V4 Flash 0731 has a AA Agentic Index result, 41.0.
Directional only
Reasoning
GPQA Diamond
No call
Only DeepSeek V4 Flash 0731 has a GPQA Diamond result, 89.9%.
Directional only
Knowledge
MMLU Pro
No call
Only DeepSeek V4 Flash 0731 has a MMLU Pro result, 86.2%.
Directional only
Web design
Design Arena: websites
No call
Only DeepSeek V4 Flash 0731 has a Design Arena: websites result, 1238.
Directional only
Long documents
Listed context window
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 takes 1.05M tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 $0.0003, Llama 3.3 70B Instruct $0.0008 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only DeepSeek V4 Flash 0731 has the number, $0.01.
Directional only
At a glance
- Coding index
- DeepSeek V4 Flash 0731 51.8 from 4 benchmarks, Llama 3.3 70B Instruct not benchmarked.
- Widest category
- Math, 89.3 points apart on average over 1 shared benchmark.
- Widest single gap
- OTIS Mock AIME: DeepSeek V4 Flash 0731 94.4% against Llama 3.3 70B Instruct 5.1%, 89.3 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4 Flash 0731 $0.28 against Llama 3.3 70B Instruct $0.72 per million output tokens, 2.6x apart.
- Context window
- DeepSeek V4 Flash 0731 takes 1.05M tokens, Llama 3.3 70B Instruct 131K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | DeepSeek V4 Flash 0731 | Bars | Llama 3.3 70B Instruct | Ties |
|---|---|---|---|---|
| Coding | 2 | 0 | ||
| Intelligence | 2 | 0 | ||
| Reasoning | 4 | 0 | ||
| Math | 1 | 0 | ||
| General | 3 | 0 | ||
| All shared boards | 12 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
| Benchmark | DeepSeek V4 Flash 0731 | Llama 3.3 70B Instruct | Leader |
|---|---|---|---|
| AA Coding Index | 69.1 | 11.9 | DeepSeek V4 Flash 0731 |
| LiveCodeBench (Vals AI) | 87.3% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| SWE-bench Verified (Vals AI) | 88.8% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Terminal-Bench 4 (Vals AI) | 18.7% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Vibe Code Bench (Vals AI) | 74.7% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Code migration (Vals AI) | 38.6% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| IOI (Vals AI) | 32.7% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Terminal-Bench 2.1 (Vals AI) | 67.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| SkillsBench (Vals AI) | 50.7% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| CyberBench (Vals AI) | 72.1% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 28.8% | Only Llama 3.3 70B Instruct measured |
| SciCode | 50.3% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 3.0% | Only Llama 3.3 70B Instruct measured |
| FrontierCode | 18.8% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| WeirdML | 63.0% | 14.4% | DeepSeek V4 Flash 0731 |
| ALE-Bench | 1306.1 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| LMArena Text: coding | Not measured | 1268 | Only Llama 3.3 70B Instruct measured |
| LMArena Text: software and IT | Not measured | 1273 | Only Llama 3.3 70B Instruct measured |
| Neither model has a result on the other 20 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | DeepSeek V4 Flash 0731 | Llama 3.3 70B Instruct | Leader |
|---|---|---|---|
| AA Intelligence Index | 34.3 | 7.7 | DeepSeek V4 Flash 0731 |
| Epoch Capabilities Index | 154.8 | 127.3 | DeepSeek V4 Flash 0731 |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index10 boards, none shared
| Benchmark | DeepSeek V4 Flash 0731 | Llama 3.3 70B Instruct | Leader |
|---|---|---|---|
| AA Agentic Index | 41.0 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Finance Agent (Vals AI) | 49.5% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Tax Agent Bench (Vals AI) | 28.1% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Legal Research Bench (Vals AI) | 30.3% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Excel Modeling Benchmark (Vals AI) | 57.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| BioMysteryBench (Vals AI) | 64.4% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Terminal-Bench-Science (Vals AI) | 4.3% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| τ²-Bench Telecom | Not measured | 26.6% | Only Llama 3.3 70B Instruct measured |
| BALROG | Not measured | 23.0% | Only Llama 3.3 70B Instruct measured |
| Berkeley Function Calling Leaderboard (BFCL) | Not measured | 31.9% | Only Llama 3.3 70B Instruct measured |
| Neither model has a result on the other 31 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | DeepSeek V4 Flash 0731 | Llama 3.3 70B Instruct | Leader |
|---|---|---|---|
| GPQA Diamond | 89.9% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| GPQA Diamond (Artificial Analysis run) | 90.8% | 49.8% | DeepSeek V4 Flash 0731 |
| Humanity's Last Exam (Artificial Analysis run) | 38.6% | 3.6% | DeepSeek V4 Flash 0731 |
| GPQA Diamond (Epoch AI run) | 91.0% | 47.4% | DeepSeek V4 Flash 0731 |
| ARC-AGI | 89.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| ARC-AGI-2 | 61.4% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| SimpleBench | 61.1% | 19.9% | DeepSeek V4 Flash 0731 |
| Chess puzzles | 32.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Mystery game puzzles | 34.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| LMArena Text: hard prompts | Not measured | 1257 | Only Llama 3.3 70B Instruct measured |
| LMArena Text: expert | Not measured | 1225 | Only Llama 3.3 70B Instruct measured |
| LMArena Text: hard prompts in English | Not measured | 1277 | Only Llama 3.3 70B Instruct measured |
| Neither model has a result on the other 10 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V4 Flash 0731 | Llama 3.3 70B Instruct | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 7.7 | Only Llama 3.3 70B Instruct measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 7.7% | Only Llama 3.3 70B Instruct measured |
| OTIS Mock AIME | 94.4% | 5.1% | DeepSeek V4 Flash 0731 |
| FrontierMath, tiers 1 to 3 | 57.5% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| FrontierMath, tier 4 | 24.4% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| ProofBench | 56.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| MATH level 5 | Not measured | 41.6% | Only Llama 3.3 70B Instruct measured |
| LMArena Text: math | Not measured | 1267 | Only Llama 3.3 70B Instruct measured |
| LMArena Text: mathematical work | Not measured | 1267 | Only Llama 3.3 70B Instruct measured |
| Neither model has a result on the other 4 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index12 boards, none shared
| Benchmark | DeepSeek V4 Flash 0731 | Llama 3.3 70B Instruct | Leader |
|---|---|---|---|
| MMLU Pro | 86.2% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| LegalBench (Vals AI) | 77.7% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| CorpFin (Vals AI) | 61.9% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| TaxEval (Vals AI) | 70.7% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| MedCode (Vals AI) | 41.4% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 71.3% | Only Llama 3.3 70B Instruct measured |
| SimpleQA Verified | 33.6% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| MMLU | Not measured | 86.3% | Only Llama 3.3 70B Instruct measured |
| LMArena Text: science | Not measured | 1284 | Only Llama 3.3 70B Instruct measured |
| LMArena Text: medicine and healthcare | Not measured | 1275 | Only Llama 3.3 70B Instruct measured |
| LMArena Text: legal and government | Not measured | 1284 | Only Llama 3.3 70B Instruct measured |
| LMArena Text: business and finance | Not measured | 1243 | Only Llama 3.3 70B Instruct measured |
| Neither model has a result on the other 6 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | DeepSeek V4 Flash 0731 | Llama 3.3 70B Instruct | Leader |
|---|---|---|---|
| Design Arena: websites | 1238 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Design Arena: UI components | 1235 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Design Arena: game dev | 1208 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Design Arena: data viz | 1180 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Design Arena: 3D | 1209 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Design Arena: all code categories | 1230 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Design Arena: SVG | 1185 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Design Arena: ASCII art | 1090 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | DeepSeek V4 Flash 0731 | Llama 3.3 70B Instruct | Leader |
|---|---|---|---|
| MedScribe (Vals AI) | 80.4% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| IFBench | Not measured | 47.1% | Only Llama 3.3 70B Instruct measured |
| Long context reasoning (AA-LCR) | 79.7% | 15.7% | DeepSeek V4 Flash 0731 |
| DTBench | 90.9% | 59.5% | DeepSeek V4 Flash 0731 |
| LMCA | 41.7% | 17.5% | DeepSeek V4 Flash 0731 |
| Fiction.LiveBench | Not measured | 33.3% | Only Llama 3.3 70B Instruct measured |
| LMArena Text | Not measured | 1274 | Only Llama 3.3 70B Instruct measured |
| LMArena Text: instruction following | Not measured | 1242 | Only Llama 3.3 70B Instruct measured |
| LMArena Text: creative writing | Not measured | 1250 | Only Llama 3.3 70B Instruct measured |
| LMArena Text: English | Not measured | 1303 | Only Llama 3.3 70B Instruct measured |
| LMArena Text: non-English | Not measured | 1236 | Only Llama 3.3 70B Instruct measured |
| LMArena Text: Chinese | Not measured | 1217 | Only Llama 3.3 70B Instruct measured |
| LMArena Text: German | Not measured | 1251 | Only Llama 3.3 70B Instruct measured |
| LMArena Text: Japanese | Not measured | 1150 | Only Llama 3.3 70B Instruct measured |
| LMArena Text: Korean | Not measured | 1142 | Only Llama 3.3 70B Instruct measured |
| LMArena Text: French | Not measured | 1282 | Only Llama 3.3 70B Instruct measured |
| LMArena Text: Spanish | Not measured | 1269 | Only Llama 3.3 70B Instruct measured |
| LMArena Text: Russian | Not measured | 1252 | Only Llama 3.3 70B Instruct measured |
| LMArena Text: Polish | Not measured | 1259 | Only Llama 3.3 70B Instruct measured |
| LMArena Text: multi-turn | Not measured | 1280 | Only Llama 3.3 70B Instruct measured |
| LMArena Text: longer queries | Not measured | 1255 | Only Llama 3.3 70B Instruct measured |
| LMArena Text: writing and language | Not measured | 1255 | Only Llama 3.3 70B Instruct measured |
| LMArena Text: entertainment and media | Not measured | 1241 | Only Llama 3.3 70B Instruct measured |
| Neither model has a result on the other 23 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V4 Flash 0731 | Llama 3.3 70B Instruct | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
DeepSeek V4 Flash 0731 costs less
Repository review
50K input + 3K output tokens
DeepSeek V4 Flash 0731 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V4 Flash 0731 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | DeepSeek V4 Flash 0731 | Meta Llama 3.3 70B Instruct |
|---|---|---|
| Maker | DeepSeek | Meta Llama |
| Weights | Open weights | Open weights |
| Released | July 31, 2026 | December 6, 2024 |
| Context window | 1.05M | 131K |
| Input $/Mtok | $0.14 | $0.45 |
| Output $/Mtok | $0.28 | $0.72 |
| Coding index | 51.8 | Not benchmarked |
| Independent measurements behind it | 4 | 0 |
| Cost per solved task | $0.01 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4 Flash 0731 better than Llama 3.3 70B Instruct for coding?
Only DeepSeek V4 Flash 0731 has a coding score, 51.8 on the Vibe Coding Index; Llama 3.3 70B Instruct has none, so the two cannot be ranked on coding. Compare them on price, context and the boards below.
Which is cheaper, DeepSeek V4 Flash 0731 or Llama 3.3 70B Instruct?
DeepSeek V4 Flash 0731 costs $0.14 per million input tokens and $0.28 per million output tokens; Llama 3.3 70B Instruct costs $0.45 and $0.72. Cost per solved task is known for DeepSeek V4 Flash 0731 only.
Which has the bigger context window, DeepSeek V4 Flash 0731 or Llama 3.3 70B Instruct?
DeepSeek V4 Flash 0731, with 1.05M tokens against 131K.
How many benchmarks is the DeepSeek V4 Flash 0731 vs Llama 3.3 70B Instruct comparison based on?
12 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4 Flash 0731's coding index rests on 4 independent benchmarks and Llama 3.3 70B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.