Llama 4 Maverick vs Mistral Large 3 2512
Llama 4 Maverick and Mistral Large 3 2512 tie on the Artificial Analysis Intelligence Index at 9.3, and Llama 4 Maverick costs 1.5x less per output token ($1.00 vs $1.50 per million). Updated October 21, 2026; 24 benchmarks have a result for both.
Llama 4 Maverick 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 4 Maverick for output tokens 1.5x cheaper ($1.00 vs $1.50 per million) and a larger context window (524K against 262K tokens).
- Shared results
- 24
- Llama 4 Maverick only
- 61
- Mistral Large 3 2512 only
- 4
- Like-for-like categories
- 8 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
No call
Tied at 9.3.
Same board, both measured
Agentic work
AA Agentic Index
Mistral Large 3 2512
Mistral Large 3 2512 leads, 1.0 against 0.6.
Same board, both measured
Reasoning
GPQA Diamond
Llama 4 Maverick
Llama 4 Maverick leads, 69.4% against 68.4%.
Same board, both measured
Math
AIME
Mistral Large 3 2512
Mistral Large 3 2512 leads, 42.9% against 25.2%.
Same board, both measured
Knowledge
MMLU Pro
Mistral Large 3 2512
Mistral Large 3 2512 leads, 79.8% against 79.4%.
Same board, both measured
Web design
Design Arena: websites
Mistral Large 3 2512
Mistral Large 3 2512 leads, 1162 against 871.
Same board, both measured
Long documents
Listed context window
Llama 4 Maverick
Llama 4 Maverick takes 524K tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Llama 4 Maverick
Llama 4 Maverick $0.0008, Mistral Large 3 2512 $0.0013 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Mistral Large 3 2512
Llama 4 Maverick $1.491, Mistral Large 3 2512 $0.77.
Published attempt cost and pass rate
At a glance
- Coding index
- Llama 4 Maverick not benchmarked, Mistral Large 3 2512 not benchmarked.
- Widest category
- Web design, 30.2 points apart on average over 6 shared benchmarks.
- Widest single gap
- MedQA (Vals AI): Llama 4 Maverick 43.3% against Mistral Large 3 2512 82.2%, 38.9 points apart on a 0 to 100 scale.
- Output price
- Llama 4 Maverick $1.00 against Mistral Large 3 2512 $1.50 per million output tokens, 1.5x apart.
- Context window
- Llama 4 Maverick takes 524K 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 4 Maverick | Bars | Mistral Large 3 2512 | Ties |
|---|---|---|---|---|
| Coding | 0 | 3 | ||
| Intelligence | 0 | 0 | 1 tie | |
| Agentic work | 0 | 1 | ||
| Reasoning | 2 | 0 | ||
| Math | 1 | 1 | ||
| Knowledge | 1 | 5 | ||
| Web design | 0 | 6 | ||
| General | 1 | 2 | ||
| All shared boards | 5 | 18 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
| Benchmark | Llama 4 Maverick | Mistral Large 3 2512 | Leader |
|---|---|---|---|
| Aider polyglot | 15.6% | Not measured | Only Llama 4 Maverick measured |
| SWE-bench Verified | 21.0% | Not measured | Only Llama 4 Maverick measured |
| AA Coding Index | 16.3 | 20.1 | Mistral Large 3 2512 |
| LiveCodeBench (Vals AI) | 47.3% | 55.3% | Mistral Large 3 2512 |
| SWE-bench Verified (Vals AI) | Not measured | 41.4% | Only Mistral Large 3 2512 measured |
| LiveCodeBench (Artificial Analysis run) | 39.7% | Not measured | Only Llama 4 Maverick measured |
| SciCode | 31.7% | Not measured | Only Llama 4 Maverick measured |
| Terminal-Bench Hard (Artificial Analysis run) | 6.8% | Not measured | Only Llama 4 Maverick measured |
| WeirdML | 24.5% | Not measured | Only Llama 4 Maverick measured |
| ALE-Bench | 173.0 | 264.7 | Mistral Large 3 2512 |
| LMArena Text: coding | 1301 | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: software and IT | 1299 | Not measured | Only Llama 4 Maverick measured |
| Neither model has a result on the other 27 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index00
| Benchmark | Llama 4 Maverick | Mistral Large 3 2512 | Leader |
|---|---|---|---|
| AA Intelligence Index | 9.3 | 9.3 | Tie |
| Epoch Capabilities Index | 132.2 | Not measured | Only Llama 4 Maverick measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Llama 4 Maverick | Mistral Large 3 2512 | Leader |
|---|---|---|---|
| AA Agentic Index | 0.6 | 1.0 | Mistral Large 3 2512 |
| τ²-Bench Telecom | 17.8% | Not measured | Only Llama 4 Maverick measured |
| Neither model has a result on the other 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Llama 4 Maverick | Mistral Large 3 2512 | Leader |
|---|---|---|---|
| GPQA Diamond | 69.4% | 68.4% | Llama 4 Maverick |
| MMMU Pro (Vals AI) | 71.7% | 66.2% | Llama 4 Maverick |
| GPQA Diamond (Artificial Analysis run) | 67.1% | Not measured | Only Llama 4 Maverick measured |
| Humanity's Last Exam (Artificial Analysis run) | 4.9% | Not measured | Only Llama 4 Maverick measured |
| ARC-AGI | 4.4% | Not measured | Only Llama 4 Maverick measured |
| ARC-AGI-2 | 0.0% | Not measured | Only Llama 4 Maverick measured |
| SimpleBench | 27.7% | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: hard prompts | 1281 | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: expert | 1259 | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: hard prompts in English | 1295 | Not measured | Only Llama 4 Maverick measured |
| LMArena Vision: diagrams | 1134 | Not measured | Only Llama 4 Maverick measured |
| LMArena Vision: homework | 1164 | Not measured | Only Llama 4 Maverick measured |
| Kagi LLM Benchmark | 55.9% | Not measured | Only Llama 4 Maverick measured |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Llama 4 Maverick | Mistral Large 3 2512 | Leader |
|---|---|---|---|
| AIME | 25.2% | 42.9% | Mistral Large 3 2512 |
| MATH 500 (Vals AI) | 85.2% | Not measured | Only Llama 4 Maverick measured |
| MGSM (Vals AI) | 92.4% | 85.4% | Llama 4 Maverick |
| AA Math Index | 19.3 | Not measured | Only Llama 4 Maverick measured |
| AIME 2025 (Artificial Analysis run) | 19.3% | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: math | 1299 | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: mathematical work | 1295 | Not measured | Only Llama 4 Maverick measured |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index15
| Benchmark | Llama 4 Maverick | Mistral Large 3 2512 | Leader |
|---|---|---|---|
| MMLU Pro | 79.4% | 79.8% | Mistral Large 3 2512 |
| LegalBench (Vals AI) | 77.8% | 79.1% | Mistral Large 3 2512 |
| CaseLaw (Vals AI) | Not measured | 61.4% | Only Mistral Large 3 2512 measured |
| CorpFin (Vals AI) | 49.7% | 61.0% | Mistral Large 3 2512 |
| TaxEval (Vals AI) | 66.6% | 73.1% | Mistral Large 3 2512 |
| MortgageTax (Vals AI) | 58.5% | 52.1% | Llama 4 Maverick |
| MedQA (Vals AI) | 43.3% | 82.2% | Mistral Large 3 2512 |
| MedCode (Vals AI) | 36.5% | Not measured | Only Llama 4 Maverick measured |
| MMLU Pro (Artificial Analysis run) | 80.9% | Not measured | Only Llama 4 Maverick measured |
| GeoBench | 52.0% | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: science | 1288 | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: medicine and healthcare | 1275 | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: legal and government | 1286 | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: business and finance | 1260 | Not measured | Only Llama 4 Maverick measured |
| Neither model has a result on the other 4 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | Llama 4 Maverick | Mistral Large 3 2512 | Leader |
|---|---|---|---|
| Design Arena: websites | 871 | 1162 | Mistral Large 3 2512 |
| Design Arena: UI components | 899 | 1102 | Mistral Large 3 2512 |
| Design Arena: game dev | 838 | 1080 | Mistral Large 3 2512 |
| Design Arena: data viz | 882 | 1136 | Mistral Large 3 2512 |
| Design Arena: 3D | 901 | 1100 | Mistral Large 3 2512 |
| Design Arena: all code categories | 880 | 1142 | Mistral Large 3 2512 |
| 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 index12
| Benchmark | Llama 4 Maverick | Mistral Large 3 2512 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 35.7% | 24.6% | Llama 4 Maverick |
| MedScribe (Vals AI) | 54.2% | Not measured | Only Llama 4 Maverick measured |
| IFBench | 43.0% | Not measured | Only Llama 4 Maverick measured |
| Long context reasoning (AA-LCR) | 50.0% | Not measured | Only Llama 4 Maverick measured |
| DTBench | 61.9% | 65.1% | Mistral Large 3 2512 |
| LMCA | 15.9% | 16.7% | Mistral Large 3 2512 |
| Fiction.LiveBench | 46.2% | Not measured | Only Llama 4 Maverick measured |
| Creative writing (Lech Mazur) | 62.0% | Not measured | Only Llama 4 Maverick measured |
| LMArena Text | 1287 | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: instruction following | 1267 | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: creative writing | 1266 | Not measured | Only Llama 4 Maverick measured |
| LMArena Vision | 1142 | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: English | 1303 | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: non-English | 1269 | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: Chinese | 1277 | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: German | 1291 | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: Japanese | 1206 | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: Korean | 1203 | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: French | 1259 | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: Spanish | 1293 | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: Russian | 1286 | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: Polish | 1275 | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: multi-turn | 1289 | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: longer queries | 1280 | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: writing and language | 1277 | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: entertainment and media | 1250 | Not measured | Only Llama 4 Maverick measured |
| LMArena Vision: English | 1150 | Not measured | Only Llama 4 Maverick measured |
| LMArena Vision: Chinese | 1141 | Not measured | Only Llama 4 Maverick measured |
| LMArena Vision: reading text | 1143 | Not measured | Only Llama 4 Maverick measured |
| LMArena Vision: humor | 1100 | Not measured | Only Llama 4 Maverick measured |
| LMArena Vision: creative writing | 1099 | Not measured | Only Llama 4 Maverick measured |
| Neither model has a result on the other 15 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Llama 4 Maverick | 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 4 Maverick costs less
Repository review
50K input + 3K output tokens
Llama 4 Maverick costs less
Agent loop
200K input + 10K output tokens
Llama 4 Maverick 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 4 Maverick | Mistral Large 3 2512 |
|---|---|---|
| Maker | Meta Llama | Mistral AI |
| Weights | Open weights | No public weights listed |
| Released | April 5, 2025 | December 1, 2025 |
| Context window | 524K | 262K |
| Input $/Mtok | $0.35 | $0.50 |
| Output $/Mtok | $1.00 | $1.50 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 1 |
| Cost per solved task | $1.491 | $0.77 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Llama 4 Maverick 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 4 Maverick for output tokens 1.5x cheaper ($1.00 vs $1.50 per million) and a larger context window (524K against 262K tokens).
Which is cheaper, Llama 4 Maverick or Mistral Large 3 2512?
Llama 4 Maverick costs $0.35 per million input tokens and $1.00 per million output tokens; Mistral Large 3 2512 costs $0.50 and $1.50. Per solved SWE-bench Verified task, Llama 4 Maverick costs $1.491 and Mistral Large 3 2512 $0.77.
Which has the bigger context window, Llama 4 Maverick or Mistral Large 3 2512?
Llama 4 Maverick, with 524K tokens against 262K.
How many benchmarks is the Llama 4 Maverick vs Mistral Large 3 2512 comparison based on?
24 benchmarks have a result for both models as of October 21, 2026. Llama 4 Maverick'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.