Llama 3.3 70B Instruct vs Mistral Large 3 2512
Mistral Large 3 2512 leads Llama 3.3 70B Instruct on the Artificial Analysis Intelligence Index, 9.3 to 7.7, and Llama 3.3 70B Instruct costs 2.1x less per output token ($0.72 vs $1.50 per million). Updated October 21, 2026; 4 benchmarks have a result for both.
Llama 3.3 70B Instruct or Mistral Large 3 2512: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Llama 3.3 70B Instruct for output tokens 2.1x cheaper ($0.72 vs $1.50 per million) and work measured by AA Coding Index or AA Intelligence Index, where it leads.
- Shared results
- 4
- Llama 3.3 70B Instruct only
- 48
- Mistral Large 3 2512 only
- 24
- Like-for-like categories
- 3 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
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Mistral Large 3 2512
Mistral Large 3 2512 leads, 9.3 against 7.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Mistral Large 3 2512 has a AA Agentic Index result, 1.0.
Directional only
Reasoning
GPQA Diamond
No call
Only Mistral Large 3 2512 has a GPQA Diamond result, 68.4%.
Directional only
Math
AIME
No call
Only Mistral Large 3 2512 has a AIME result, 42.9%.
Directional only
Knowledge
MMLU Pro
No call
Only Mistral Large 3 2512 has a MMLU Pro result, 79.8%.
Directional only
Web design
Design Arena: websites
No call
Only Mistral Large 3 2512 has a Design Arena: websites result, 1162.
Directional only
Long documents
Listed context window
Mistral Large 3 2512
Mistral Large 3 2512 takes 262K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Llama 3.3 70B Instruct
Llama 3.3 70B Instruct $0.0008, Mistral Large 3 2512 $0.0013 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Mistral Large 3 2512 has the number, $0.77.
Directional only
At a glance
- Coding index
- Llama 3.3 70B Instruct not benchmarked, Mistral Large 3 2512 not benchmarked.
- Widest category
- Coding, 8.2 points apart on average over 1 shared benchmark.
- Widest single gap
- AA Coding Index: Llama 3.3 70B Instruct 11.9 against Mistral Large 3 2512 20.1, 8.2 points apart on a 0 to 100 scale.
- Output price
- Llama 3.3 70B Instruct $0.72 against Mistral Large 3 2512 $1.50 per million output tokens, 2.1x apart.
- Context window
- Llama 3.3 70B Instruct takes 131K tokens, Mistral Large 3 2512 262K.
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 | Llama 3.3 70B Instruct | Bars | Mistral Large 3 2512 | Ties |
|---|---|---|---|---|
| Coding | 0 | 1 | ||
| Intelligence | 0 | 1 | ||
| General | 1 | 1 | ||
| All shared boards | 1 | 3 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index01
| Benchmark | Llama 3.3 70B Instruct | Mistral Large 3 2512 | Leader |
|---|---|---|---|
| AA Coding Index | 11.9 | 20.1 | Mistral Large 3 2512 |
| LiveCodeBench (Vals AI) | Not measured | 55.3% | Only Mistral Large 3 2512 measured |
| SWE-bench Verified (Vals AI) | Not measured | 41.4% | Only Mistral Large 3 2512 measured |
| LiveCodeBench (Artificial Analysis run) | 28.8% | Not measured | Only Llama 3.3 70B Instruct measured |
| Terminal-Bench Hard (Artificial Analysis run) | 3.0% | Not measured | Only Llama 3.3 70B Instruct measured |
| WeirdML | 14.4% | Not measured | Only Llama 3.3 70B Instruct measured |
| ALE-Bench | Not measured | 264.7 | Only Mistral Large 3 2512 measured |
| LMArena Text: coding | 1268 | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: software and IT | 1273 | Not measured | Only Llama 3.3 70B Instruct measured |
| Neither model has a result on the other 30 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Llama 3.3 70B Instruct | Mistral Large 3 2512 | Leader |
|---|---|---|---|
| AA Intelligence Index | 7.7 | 9.3 | Mistral Large 3 2512 |
| Epoch Capabilities Index | 127.3 | Not measured | Only Llama 3.3 70B Instruct measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | Llama 3.3 70B Instruct | Mistral Large 3 2512 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 1.0 | Only Mistral Large 3 2512 measured |
| τ²-Bench Telecom | 26.6% | Not measured | Only Llama 3.3 70B Instruct measured |
| BALROG | 23.0% | Not measured | Only Llama 3.3 70B Instruct measured |
| Berkeley Function Calling Leaderboard (BFCL) | 31.9% | Not measured | Only Llama 3.3 70B Instruct measured |
| Neither model has a result on the other 37 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | Llama 3.3 70B Instruct | Mistral Large 3 2512 | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 68.4% | Only Mistral Large 3 2512 measured |
| MMMU Pro (Vals AI) | Not measured | 66.2% | Only Mistral Large 3 2512 measured |
| GPQA Diamond (Artificial Analysis run) | 49.8% | Not measured | Only Llama 3.3 70B Instruct measured |
| Humanity's Last Exam (Artificial Analysis run) | 3.6% | Not measured | Only Llama 3.3 70B Instruct measured |
| GPQA Diamond (Epoch AI run) | 47.4% | Not measured | Only Llama 3.3 70B Instruct measured |
| SimpleBench | 19.9% | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: hard prompts | 1257 | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: expert | 1225 | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: hard prompts in English | 1277 | Not measured | Only Llama 3.3 70B Instruct measured |
| Neither model has a result on the other 13 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Llama 3.3 70B Instruct | Mistral Large 3 2512 | Leader |
|---|---|---|---|
| AIME | Not measured | 42.9% | Only Mistral Large 3 2512 measured |
| MGSM (Vals AI) | Not measured | 85.4% | Only Mistral Large 3 2512 measured |
| AA Math Index | 7.7 | Not measured | Only Llama 3.3 70B Instruct measured |
| AIME 2025 (Artificial Analysis run) | 7.7% | Not measured | Only Llama 3.3 70B Instruct measured |
| OTIS Mock AIME | 5.1% | Not measured | Only Llama 3.3 70B Instruct measured |
| MATH level 5 | 41.6% | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: math | 1267 | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: mathematical work | 1267 | Not measured | Only Llama 3.3 70B Instruct measured |
| Neither model has a result on the other 5 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index13 boards, none shared
| Benchmark | Llama 3.3 70B Instruct | Mistral Large 3 2512 | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 79.8% | Only Mistral Large 3 2512 measured |
| LegalBench (Vals AI) | Not measured | 79.1% | Only Mistral Large 3 2512 measured |
| CaseLaw (Vals AI) | Not measured | 61.4% | Only Mistral Large 3 2512 measured |
| CorpFin (Vals AI) | Not measured | 61.0% | Only Mistral Large 3 2512 measured |
| TaxEval (Vals AI) | Not measured | 73.1% | Only Mistral Large 3 2512 measured |
| MortgageTax (Vals AI) | Not measured | 52.1% | Only Mistral Large 3 2512 measured |
| MedQA (Vals AI) | Not measured | 82.2% | Only Mistral Large 3 2512 measured |
| MMLU Pro (Artificial Analysis run) | 71.3% | Not measured | Only Llama 3.3 70B Instruct measured |
| MMLU | 86.3% | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: science | 1284 | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: medicine and healthcare | 1275 | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: legal and government | 1284 | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: business and finance | 1243 | Not measured | Only Llama 3.3 70B Instruct measured |
| Neither model has a result on the other 5 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Llama 3.3 70B Instruct | Mistral Large 3 2512 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1162 | Only Mistral Large 3 2512 measured |
| Design Arena: UI components | Not measured | 1102 | Only Mistral Large 3 2512 measured |
| Design Arena: game dev | Not measured | 1080 | Only Mistral Large 3 2512 measured |
| Design Arena: data viz | Not measured | 1136 | Only Mistral Large 3 2512 measured |
| Design Arena: 3D | Not measured | 1100 | Only Mistral Large 3 2512 measured |
| Design Arena: all code categories | Not measured | 1142 | Only Mistral Large 3 2512 measured |
| Design Arena: SVG | Not measured | 993 | Only Mistral Large 3 2512 measured |
| Design Arena: ASCII art | Not measured | 1069 | Only Mistral Large 3 2512 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Llama 3.3 70B Instruct | Mistral Large 3 2512 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 24.6% | Only Mistral Large 3 2512 measured |
| IFBench | 47.1% | Not measured | Only Llama 3.3 70B Instruct measured |
| Long context reasoning (AA-LCR) | 15.7% | Not measured | Only Llama 3.3 70B Instruct measured |
| DTBench | 59.5% | 65.1% | Mistral Large 3 2512 |
| LMCA | 17.5% | 16.7% | Llama 3.3 70B Instruct |
| Fiction.LiveBench | 33.3% | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text | 1274 | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: instruction following | 1242 | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: creative writing | 1250 | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: English | 1303 | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: non-English | 1236 | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: Chinese | 1217 | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: German | 1251 | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: Japanese | 1150 | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: Korean | 1142 | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: French | 1282 | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: Spanish | 1269 | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: Russian | 1252 | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: Polish | 1259 | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: multi-turn | 1280 | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: longer queries | 1255 | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: writing and language | 1255 | Not measured | Only Llama 3.3 70B Instruct measured |
| LMArena Text: entertainment and media | 1241 | Not measured | 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 | Llama 3.3 70B Instruct | Mistral Large 3 2512 | 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
Llama 3.3 70B Instruct costs less
Repository review
50K input + 3K output tokens
Llama 3.3 70B Instruct costs less
Agent loop
200K input + 10K output tokens
Llama 3.3 70B Instruct 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 | Meta Llama 3.3 70B Instruct | Mistral Large 3 2512 |
|---|---|---|
| Maker | Meta Llama | Mistral AI |
| Weights | Open weights | No public weights listed |
| Released | December 6, 2024 | December 1, 2025 |
| Context window | 131K | 262K |
| Input $/Mtok | $0.45 | $0.50 |
| Output $/Mtok | $0.72 | $1.50 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 1 |
| Cost per solved task | Not computable | $0.77 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Llama 3.3 70B Instruct better than Mistral Large 3 2512 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Llama 3.3 70B Instruct for output tokens 2.1x cheaper ($0.72 vs $1.50 per million) and work measured by AA Coding Index or AA Intelligence Index, where it leads.
Which is cheaper, Llama 3.3 70B Instruct or Mistral Large 3 2512?
Llama 3.3 70B Instruct costs $0.45 per million input tokens and $0.72 per million output tokens; Mistral Large 3 2512 costs $0.50 and $1.50. Cost per solved task is known for Mistral Large 3 2512 only.
Which has the bigger context window, Llama 3.3 70B Instruct or Mistral Large 3 2512?
Mistral Large 3 2512, with 262K tokens against 131K.
How many benchmarks is the Llama 3.3 70B Instruct vs Mistral Large 3 2512 comparison based on?
4 benchmarks have a result for both models as of October 21, 2026. Llama 3.3 70B Instruct's coding index rests on 0 independent benchmarks and Mistral Large 3 2512's on 1. Where only one model has a result, the page says so instead of naming a winner.