Llama 4 Scout vs Mistral Medium 3.5
Updated October 21, 2026. 61 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Llama 4 Scout and Mistral Medium 3.5 are level for coding, 9.1 against 9.2 on the Vibe Coding Index, so price and context decide.
Pick Llama 4 Scout when output tokens cost 25.0x less, or when a solved task costs $1.276 against $6.02. Pick Mistral Medium 3.5 when what matters is AA Coding Index or SciCode, where it leads.
- Shared results
- 61
- Llama 4 Scout only
- 19
- Mistral Medium 3.5 only
- 19
- Like-for-like categories
- 8 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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, four public coding benchmarks
No call
Level: 9.1 against 9.2, inside 2 points.
One benchmark behind each score
Intelligence
AA Intelligence Index
Mistral Medium 3.5
Mistral Medium 3.5 leads, 14.2 against 6.5.
Same board, both measured
Agentic work
AA Agentic Index
Mistral Medium 3.5
Mistral Medium 3.5 leads, 7.0 against 0.5.
Same board, both measured
Reasoning
GPQA Diamond
Llama 4 Scout
Llama 4 Scout leads, 47.0% against 34.9%.
Same board, both measured
Math
AIME
No call
Only Llama 4 Scout has a AIME result, 19.0%.
Directional only
Knowledge
MMLU Pro
Mistral Medium 3.5
Mistral Medium 3.5 leads, 75.3% against 69.6%.
Same board, both measured
Web design
Design Arena: websites
Mistral Medium 3.5
Mistral Medium 3.5 leads, 1142 against 750.
Same board, both measured
Long documents
Listed context window
Llama 4 Scout
Llama 4 Scout takes 1.31M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Llama 4 Scout
Llama 4 Scout $0.0003, Mistral Medium 3.5 $0.0053 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Llama 4 Scout
Llama 4 Scout $1.276, Mistral Medium 3.5 $6.02.
Published attempt cost and pass rate
At a glance
- Coding index
- Llama 4 Scout 9.1 from 1 benchmark, Mistral Medium 3.5 9.2 from 1 benchmark.
- Widest category
- Agentic work, 42.6 points apart on average over 2 shared benchmarks.
- Widest single gap
- τ²-Bench Telecom: Llama 4 Scout 15.5% against Mistral Medium 3.5 94.2%, 78.7 points apart on a 0 to 100 scale.
- Output price
- Llama 4 Scout $0.30 against Mistral Medium 3.5 $7.50 per million output tokens, 25.0x apart.
- Context window
- Llama 4 Scout takes 1.31M tokens, Mistral Medium 3.5 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 Scout | Bars | Mistral Medium 3.5 | Ties |
|---|---|---|---|---|
| Coding | 0 | 5 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 0 | 2 | ||
| Reasoning | 1 | 7 | ||
| Math | 0 | 2 | ||
| Knowledge | 1 | 8 | ||
| Web design | 0 | 5 | ||
| General | 0 | 28 | ||
| All shared boards | 2 | 59 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index05
| Benchmark | Llama 4 Scout | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| SWE-bench Verified | 9.1% | Not measured | Only Llama 4 Scout measured |
| LMArena WebDev | Not measured | 1264 | Only Mistral Medium 3.5 measured |
| AA Coding Index | 8.2 | 46.9 | Mistral Medium 3.5 |
| LiveCodeBench (Vals AI) | 38.5% | Not measured | Only Llama 4 Scout measured |
| SWE-bench Verified (Vals AI) | Not measured | 66.4% | Only Mistral Medium 3.5 measured |
| Vibe Code Bench (Vals AI) | Not measured | 2.9% | Only Mistral Medium 3.5 measured |
| Code migration (Vals AI) | Not measured | 5.1% | Only Mistral Medium 3.5 measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 39.0% | Only Mistral Medium 3.5 measured |
| LiveCodeBench (Artificial Analysis run) | 29.9% | Not measured | Only Llama 4 Scout measured |
| SciCode | 21.3% | 40.2% | Mistral Medium 3.5 |
| Terminal-Bench Hard (Artificial Analysis run) | 1.5% | 33.3% | Mistral Medium 3.5 |
| ALE-Bench | Not measured | 764.0 | Only Mistral Medium 3.5 measured |
| LMArena Text: coding | 1286 | 1460 | Mistral Medium 3.5 |
| LMArena Text: software and IT | 1286 | 1458 | Mistral Medium 3.5 |
| LMArena WebDev: React | Not measured | 1254 | Only Mistral Medium 3.5 measured |
| LMArena WebDev: HTML | Not measured | 1308 | Only Mistral Medium 3.5 measured |
| Neither model has a result on the other 22 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Llama 4 Scout | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 6.5 | 14.2 | Mistral Medium 3.5 |
| Epoch Capabilities Index | 129.6 | 141.4 | Mistral Medium 3.5 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Llama 4 Scout | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| AA Agentic Index | 0.5 | 7.0 | Mistral Medium 3.5 |
| Finance Agent (Vals AI) | Not measured | 32.1% | Only Mistral Medium 3.5 measured |
| Tax Agent Bench (Vals AI) | Not measured | 4.5% | Only Mistral Medium 3.5 measured |
| Legal Research Bench (Vals AI) | Not measured | 9.1% | Only Mistral Medium 3.5 measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 11.2% | Only Mistral Medium 3.5 measured |
| τ²-Bench Telecom | 15.5% | 94.2% | Mistral Medium 3.5 |
| Neither model has a result on the other 33 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index17
| Benchmark | Llama 4 Scout | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| GPQA Diamond | 47.0% | 34.9% | Llama 4 Scout |
| MMMU Pro (Vals AI) | 58.8% | Not measured | Only Llama 4 Scout measured |
| GPQA Diamond (Artificial Analysis run) | 58.7% | 74.8% | Mistral Medium 3.5 |
| Humanity's Last Exam (Artificial Analysis run) | 3.8% | 13.8% | Mistral Medium 3.5 |
| GPQA Diamond (Epoch AI run) | 51.8% | Not measured | Only Llama 4 Scout measured |
| ARC-AGI | 0.5% | Not measured | Only Llama 4 Scout measured |
| ARC-AGI-2 | 0.0% | Not measured | Only Llama 4 Scout measured |
| LMArena Text: hard prompts | 1266 | 1436 | Mistral Medium 3.5 |
| LMArena Text: expert | 1235 | 1432 | Mistral Medium 3.5 |
| LMArena Text: hard prompts in English | 1293 | 1445 | Mistral Medium 3.5 |
| LMArena Vision: diagrams | 1125 | 1254 | Mistral Medium 3.5 |
| LMArena Vision: homework | 1148 | 1230 | Mistral Medium 3.5 |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Llama 4 Scout | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| AIME | 19.0% | Not measured | Only Llama 4 Scout measured |
| MATH 500 (Vals AI) | 79.2% | Not measured | Only Llama 4 Scout measured |
| MGSM (Vals AI) | 88.0% | Not measured | Only Llama 4 Scout measured |
| AA Math Index | 14.0 | Not measured | Only Llama 4 Scout measured |
| AIME 2025 (Artificial Analysis run) | 14.0% | Not measured | Only Llama 4 Scout measured |
| OTIS Mock AIME | 7.8% | Not measured | Only Llama 4 Scout measured |
| ProofBench | Not measured | 9.0% | Only Mistral Medium 3.5 measured |
| MATH level 5 | 62.3% | Not measured | Only Llama 4 Scout measured |
| LMArena Text: math | 1287 | 1431 | Mistral Medium 3.5 |
| LMArena Text: mathematical work | 1286 | 1440 | Mistral Medium 3.5 |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index18
| Benchmark | Llama 4 Scout | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| MMLU Pro | 69.6% | 75.3% | Mistral Medium 3.5 |
| LegalBench (Vals AI) | 72.0% | Not measured | Only Llama 4 Scout measured |
| CaseLaw (Vals AI) | Not measured | 44.2% | Only Mistral Medium 3.5 measured |
| CorpFin (Vals AI) | 46.8% | 58.8% | Mistral Medium 3.5 |
| TaxEval (Vals AI) | 55.2% | 68.0% | Mistral Medium 3.5 |
| MortgageTax (Vals AI) | 57.8% | 28.9% | Llama 4 Scout |
| MedQA (Vals AI) | 50.9% | Not measured | Only Llama 4 Scout measured |
| MedCode (Vals AI) | 23.3% | 33.8% | Mistral Medium 3.5 |
| MMLU Pro (Artificial Analysis run) | 75.2% | Not measured | Only Llama 4 Scout measured |
| LMArena Text: science | 1278 | 1428 | Mistral Medium 3.5 |
| LMArena Text: medicine and healthcare | 1275 | 1409 | Mistral Medium 3.5 |
| LMArena Text: legal and government | 1285 | 1437 | Mistral Medium 3.5 |
| LMArena Text: business and finance | 1257 | 1426 | Mistral Medium 3.5 |
| Neither model has a result on the other 4 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | Llama 4 Scout | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| Design Arena: websites | 750 | 1142 | Mistral Medium 3.5 |
| Design Arena: UI components | 767 | 1079 | Mistral Medium 3.5 |
| Design Arena: game dev | 773 | 1079 | Mistral Medium 3.5 |
| Design Arena: data viz | 896 | 1120 | Mistral Medium 3.5 |
| Design Arena: 3D | Not measured | 1061 | Only Mistral Medium 3.5 measured |
| Design Arena: all code categories | 790 | 1122 | Mistral Medium 3.5 |
| Design Arena: SVG | Not measured | 949 | Only Mistral Medium 3.5 measured |
| Design Arena: ASCII art | Not measured | 1062 | Only Mistral Medium 3.5 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index028
| Benchmark | Llama 4 Scout | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 34.8% | 37.6% | Mistral Medium 3.5 |
| MedScribe (Vals AI) | 50.6% | 67.7% | Mistral Medium 3.5 |
| Vals Multimodal Index | Not measured | 34.8% | Only Mistral Medium 3.5 measured |
| IFBench | 39.5% | 68.8% | Mistral Medium 3.5 |
| Long context reasoning (AA-LCR) | 27.7% | 69.3% | Mistral Medium 3.5 |
| DTBench | 57.9% | 75.5% | Mistral Medium 3.5 |
| LMCA | 12.0% | 26.1% | Mistral Medium 3.5 |
| Fiction.LiveBench | 36.0% | Not measured | Only Llama 4 Scout measured |
| Surface Evolver Bench | Not measured | 26.9% | Only Mistral Medium 3.5 measured |
| LMArena Text | 1279 | 1421 | Mistral Medium 3.5 |
| LMArena Text: instruction following | 1248 | 1415 | Mistral Medium 3.5 |
| LMArena Text: creative writing | 1249 | 1374 | Mistral Medium 3.5 |
| LMArena Vision | 1118 | 1222 | Mistral Medium 3.5 |
| LMArena Text: English | 1304 | 1433 | Mistral Medium 3.5 |
| LMArena Text: non-English | 1252 | 1404 | Mistral Medium 3.5 |
| LMArena Text: Chinese | 1255 | 1444 | Mistral Medium 3.5 |
| LMArena Text: German | 1273 | 1453 | Mistral Medium 3.5 |
| LMArena Text: Japanese | 1206 | Not measured | Only Llama 4 Scout measured |
| LMArena Text: Korean | 1207 | 1384 | Mistral Medium 3.5 |
| LMArena Text: French | 1283 | 1448 | Mistral Medium 3.5 |
| LMArena Text: Spanish | 1278 | 1411 | Mistral Medium 3.5 |
| LMArena Text: Russian | 1263 | 1395 | Mistral Medium 3.5 |
| LMArena Text: Polish | 1265 | 1430 | Mistral Medium 3.5 |
| LMArena Text: multi-turn | 1280 | 1423 | Mistral Medium 3.5 |
| LMArena Text: longer queries | 1265 | 1415 | Mistral Medium 3.5 |
| LMArena Text: writing and language | 1269 | 1384 | Mistral Medium 3.5 |
| LMArena Text: entertainment and media | 1242 | 1382 | Mistral Medium 3.5 |
| LMArena Vision: English | 1143 | 1240 | Mistral Medium 3.5 |
| LMArena Vision: Chinese | 1106 | 1244 | Mistral Medium 3.5 |
| LMArena Vision: reading text | 1117 | 1233 | Mistral Medium 3.5 |
| LMArena Vision: humor | 1102 | 1216 | Mistral Medium 3.5 |
| LMArena Vision: creative writing | 1126 | 1198 | Mistral Medium 3.5 |
| Neither model has a result on the other 14 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Llama 4 Scout | Mistral Medium 3.5 | 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 Scout costs less
Repository review
50K input + 3K output tokens
Llama 4 Scout costs less
Agent loop
200K input + 10K output tokens
Llama 4 Scout 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 Scout | Mistral Medium 3.5 |
|---|---|---|
| Maker | Meta Llama | Mistral AI |
| Weights | Open weights | No public weights listed |
| Released | April 5, 2025 | April 30, 2026 |
| Context window | 1.31M | 262K |
| Input $/Mtok | $0.10 | $1.50 |
| Output $/Mtok | $0.30 | $7.50 |
| Coding index | 9.1 | 9.2 |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | $1.276 | $6.02 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Llama 4 Scout better than Mistral Medium 3.5 for coding?
Llama 4 Scout and Mistral Medium 3.5 are level for coding, 9.1 against 9.2 on the Vibe Coding Index, so price and context decide. Pick Llama 4 Scout when output tokens cost 25.0x less, or when a solved task costs $1.276 against $6.02. Pick Mistral Medium 3.5 when what matters is AA Coding Index or SciCode, where it leads.
Which is cheaper, Llama 4 Scout or Mistral Medium 3.5?
Llama 4 Scout costs $0.10 per million input tokens and $0.30 per million output tokens; Mistral Medium 3.5 costs $1.50 and $7.50. Per solved SWE-bench Verified task, Llama 4 Scout costs $1.276 and Mistral Medium 3.5 $6.02.
Which has the bigger context window, Llama 4 Scout or Mistral Medium 3.5?
Llama 4 Scout, with 1.31M tokens against 262K.
How many benchmarks is the Llama 4 Scout vs Mistral Medium 3.5 comparison based on?
61 benchmarks have a result for both models as of October 21, 2026. Llama 4 Scout's coding index rests on 1 independent benchmark and Mistral Medium 3.5's on 1. Where only one model has a result, the page says so instead of naming a winner.