DeepSeek V4 Flash 0731 vs Mistral Medium 3.5
DeepSeek V4 Flash 0731 leads Mistral Medium 3.5 on coding, 51.8 to 25.5 on the Vibe Coding Index, and DeepSeek V4 Flash 0731 costs 26.8x less per output token ($0.28 vs $7.50 per million). Updated October 21, 2026; 34 benchmarks have a result for both.
DeepSeek V4 Flash 0731 or Mistral Medium 3.5: which to pick
Pick DeepSeek V4 Flash 0731 for coding: it scores 51.8 on the Vibe Coding Index against 25.5 for Mistral Medium 3.5.
Mistral Medium 3.5 is neither cheaper nor larger in context, and leads no benchmark both models were measured on.
- Shared results
- 34
- DeepSeek V4 Flash 0731 only
- 21
- Mistral Medium 3.5 only
- 47
- 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
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 scores 51.8 against 25.5.
4 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 34.3 against 14.2.
Same board, both measured
Agentic work
AA Agentic Index
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 41.0 against 7.0.
Same board, both measured
Reasoning
GPQA Diamond
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 89.9% against 34.9%.
Same board, both measured
Knowledge
MMLU Pro
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 86.2% against 75.3%.
Same board, both measured
Web design
Design Arena: websites
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 1238 against 1142.
Same board, both measured
Long documents
Listed context window
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 takes 1.05M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 $0.0003, Mistral Medium 3.5 $0.0053 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 $0.01, Mistral Medium 3.5 $6.02.
Published attempt cost and pass rate
At a glance
- Coding index
- DeepSeek V4 Flash 0731 51.8 from 4 benchmarks, Mistral Medium 3.5 25.5 from 3 benchmarks.
- Widest category
- Math, 47.0 points apart on average over 1 shared benchmark.
- Widest single gap
- Vibe Code Bench (Vals AI): DeepSeek V4 Flash 0731 74.7% against Mistral Medium 3.5 2.9%, 71.8 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4 Flash 0731 $0.28 against Mistral Medium 3.5 $7.50 per million output tokens, 26.8x apart.
- Context window
- DeepSeek V4 Flash 0731 takes 1.05M 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 | DeepSeek V4 Flash 0731 | Bars | Mistral Medium 3.5 | Ties |
|---|---|---|---|---|
| Coding | 7 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 5 | 0 | ||
| Reasoning | 3 | 0 | ||
| Math | 1 | 0 | ||
| Knowledge | 4 | 0 | ||
| Web design | 8 | 0 | ||
| General | 4 | 0 | ||
| All shared boards | 34 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index70
| Benchmark | DeepSeek V4 Flash 0731 | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| LMArena WebDev | Not measured | 1264 | Only Mistral Medium 3.5 measured |
| AA Coding Index | 69.1 | 46.9 | DeepSeek V4 Flash 0731 |
| LiveCodeBench (Vals AI) | 87.3% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| SWE-bench Verified (Vals AI) | 88.8% | 66.4% | DeepSeek V4 Flash 0731 |
| Terminal-Bench 4 (Vals AI) | 18.7% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Vibe Code Bench (Vals AI) | 74.7% | 2.9% | DeepSeek V4 Flash 0731 |
| Code migration (Vals AI) | 38.6% | 5.1% | DeepSeek V4 Flash 0731 |
| 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% | 39.0% | DeepSeek V4 Flash 0731 |
| 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 |
| SciCode | 50.3% | 40.2% | DeepSeek V4 Flash 0731 |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 33.3% | Only Mistral Medium 3.5 measured |
| FrontierCode | 18.8% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| WeirdML | 63.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| ALE-Bench | 1306.1 | 764.0 | DeepSeek V4 Flash 0731 |
| LMArena Text: coding | Not measured | 1460 | Only Mistral Medium 3.5 measured |
| LMArena Text: software and IT | Not measured | 1458 | Only Mistral Medium 3.5 measured |
| 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 18 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | DeepSeek V4 Flash 0731 | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 34.3 | 14.2 | DeepSeek V4 Flash 0731 |
| Epoch Capabilities Index | 154.8 | 141.4 | DeepSeek V4 Flash 0731 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | DeepSeek V4 Flash 0731 | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| AA Agentic Index | 41.0 | 7.0 | DeepSeek V4 Flash 0731 |
| Finance Agent (Vals AI) | 49.5% | 32.1% | DeepSeek V4 Flash 0731 |
| Tax Agent Bench (Vals AI) | 28.1% | 4.5% | DeepSeek V4 Flash 0731 |
| Legal Research Bench (Vals AI) | 30.3% | 9.1% | DeepSeek V4 Flash 0731 |
| Excel Modeling Benchmark (Vals AI) | 57.0% | 11.2% | DeepSeek V4 Flash 0731 |
| 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 | 94.2% | Only Mistral Medium 3.5 measured |
| Neither model has a result on the other 33 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | DeepSeek V4 Flash 0731 | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| GPQA Diamond | 89.9% | 34.9% | DeepSeek V4 Flash 0731 |
| GPQA Diamond (Artificial Analysis run) | 90.8% | 74.8% | DeepSeek V4 Flash 0731 |
| Humanity's Last Exam (Artificial Analysis run) | 38.6% | 13.8% | DeepSeek V4 Flash 0731 |
| GPQA Diamond (Epoch AI run) | 91.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| 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% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| 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 | 1436 | Only Mistral Medium 3.5 measured |
| LMArena Text: expert | Not measured | 1432 | Only Mistral Medium 3.5 measured |
| LMArena Text: hard prompts in English | Not measured | 1445 | Only Mistral Medium 3.5 measured |
| LMArena Vision: diagrams | Not measured | 1254 | Only Mistral Medium 3.5 measured |
| LMArena Vision: homework | Not measured | 1230 | Only Mistral Medium 3.5 measured |
| Kagi LLM Benchmark | Not measured | 41.4% | Only Mistral Medium 3.5 measured |
| Neither model has a result on the other 7 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V4 Flash 0731 | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| OTIS Mock AIME | 94.4% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| 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% | 9.0% | DeepSeek V4 Flash 0731 |
| LMArena Text: math | Not measured | 1431 | Only Mistral Medium 3.5 measured |
| LMArena Text: mathematical work | Not measured | 1440 | Only Mistral Medium 3.5 measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | DeepSeek V4 Flash 0731 | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| MMLU Pro | 86.2% | 75.3% | DeepSeek V4 Flash 0731 |
| LegalBench (Vals AI) | 77.7% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| CaseLaw (Vals AI) | Not measured | 44.2% | Only Mistral Medium 3.5 measured |
| CorpFin (Vals AI) | 61.9% | 58.8% | DeepSeek V4 Flash 0731 |
| TaxEval (Vals AI) | 70.7% | 68.0% | DeepSeek V4 Flash 0731 |
| MortgageTax (Vals AI) | Not measured | 28.9% | Only Mistral Medium 3.5 measured |
| MedCode (Vals AI) | 41.4% | 33.8% | DeepSeek V4 Flash 0731 |
| SimpleQA Verified | 33.6% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| LMArena Text: science | Not measured | 1428 | Only Mistral Medium 3.5 measured |
| LMArena Text: medicine and healthcare | Not measured | 1409 | Only Mistral Medium 3.5 measured |
| LMArena Text: legal and government | Not measured | 1437 | Only Mistral Medium 3.5 measured |
| LMArena Text: business and finance | Not measured | 1426 | Only Mistral Medium 3.5 measured |
| Neither model has a result on the other 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index80
| Benchmark | DeepSeek V4 Flash 0731 | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| Design Arena: websites | 1238 | 1142 | DeepSeek V4 Flash 0731 |
| Design Arena: UI components | 1235 | 1079 | DeepSeek V4 Flash 0731 |
| Design Arena: game dev | 1208 | 1079 | DeepSeek V4 Flash 0731 |
| Design Arena: data viz | 1180 | 1120 | DeepSeek V4 Flash 0731 |
| Design Arena: 3D | 1209 | 1061 | DeepSeek V4 Flash 0731 |
| Design Arena: all code categories | 1230 | 1121 | DeepSeek V4 Flash 0731 |
| Design Arena: SVG | 1185 | 950 | DeepSeek V4 Flash 0731 |
| Design Arena: ASCII art | 1090 | 1063 | DeepSeek V4 Flash 0731 |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | DeepSeek V4 Flash 0731 | Mistral Medium 3.5 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 37.6% | Only Mistral Medium 3.5 measured |
| MedScribe (Vals AI) | 80.4% | 67.7% | DeepSeek V4 Flash 0731 |
| Vals Multimodal Index | Not measured | 34.8% | Only Mistral Medium 3.5 measured |
| IFBench | Not measured | 68.8% | Only Mistral Medium 3.5 measured |
| Long context reasoning (AA-LCR) | 79.7% | 69.3% | DeepSeek V4 Flash 0731 |
| DTBench | 90.9% | 75.5% | DeepSeek V4 Flash 0731 |
| LMCA | 41.7% | 26.1% | DeepSeek V4 Flash 0731 |
| Surface Evolver Bench | Not measured | 26.9% | Only Mistral Medium 3.5 measured |
| LMArena Text | Not measured | 1421 | Only Mistral Medium 3.5 measured |
| LMArena Text: instruction following | Not measured | 1415 | Only Mistral Medium 3.5 measured |
| LMArena Text: creative writing | Not measured | 1374 | Only Mistral Medium 3.5 measured |
| LMArena Vision | Not measured | 1222 | Only Mistral Medium 3.5 measured |
| LMArena Text: English | Not measured | 1433 | Only Mistral Medium 3.5 measured |
| LMArena Text: non-English | Not measured | 1404 | Only Mistral Medium 3.5 measured |
| LMArena Text: Chinese | Not measured | 1444 | Only Mistral Medium 3.5 measured |
| LMArena Text: German | Not measured | 1453 | Only Mistral Medium 3.5 measured |
| LMArena Text: Korean | Not measured | 1384 | Only Mistral Medium 3.5 measured |
| LMArena Text: French | Not measured | 1448 | Only Mistral Medium 3.5 measured |
| LMArena Text: Spanish | Not measured | 1411 | Only Mistral Medium 3.5 measured |
| LMArena Text: Russian | Not measured | 1395 | Only Mistral Medium 3.5 measured |
| LMArena Text: Polish | Not measured | 1430 | Only Mistral Medium 3.5 measured |
| LMArena Text: multi-turn | Not measured | 1423 | Only Mistral Medium 3.5 measured |
| LMArena Text: longer queries | Not measured | 1415 | Only Mistral Medium 3.5 measured |
| LMArena Text: writing and language | Not measured | 1384 | Only Mistral Medium 3.5 measured |
| LMArena Text: entertainment and media | Not measured | 1382 | Only Mistral Medium 3.5 measured |
| LMArena Vision: English | Not measured | 1240 | Only Mistral Medium 3.5 measured |
| LMArena Vision: Chinese | Not measured | 1244 | Only Mistral Medium 3.5 measured |
| LMArena Vision: reading text | Not measured | 1233 | Only Mistral Medium 3.5 measured |
| LMArena Vision: humor | Not measured | 1216 | Only Mistral Medium 3.5 measured |
| LMArena Vision: creative writing | Not measured | 1198 | Only Mistral Medium 3.5 measured |
| Neither model has a result on the other 16 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V4 Flash 0731 | 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
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 | Mistral Medium 3.5 |
|---|---|---|
| Maker | DeepSeek | Mistral AI |
| Weights | Open weights | No public weights listed |
| Released | July 31, 2026 | April 30, 2026 |
| Context window | 1.05M | 262K |
| Input $/Mtok | $0.14 | $1.50 |
| Output $/Mtok | $0.28 | $7.50 |
| Coding index | 51.8 | 25.5 |
| Independent measurements behind it | 4 | 3 |
| Cost per solved task | $0.01 | $6.02 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4 Flash 0731 better than Mistral Medium 3.5 for coding?
Pick DeepSeek V4 Flash 0731 for coding: it scores 51.8 on the Vibe Coding Index against 25.5 for Mistral Medium 3.5. Mistral Medium 3.5 is neither cheaper nor larger in context, and leads no benchmark both models were measured on.
Which is cheaper, DeepSeek V4 Flash 0731 or Mistral Medium 3.5?
DeepSeek V4 Flash 0731 costs $0.14 per million input tokens and $0.28 per million output tokens; Mistral Medium 3.5 costs $1.50 and $7.50. Per solved SWE-bench Verified task, DeepSeek V4 Flash 0731 costs $0.01 and Mistral Medium 3.5 $6.02.
Which has the bigger context window, DeepSeek V4 Flash 0731 or Mistral Medium 3.5?
DeepSeek V4 Flash 0731, with 1.05M tokens against 262K.
How many benchmarks is the DeepSeek V4 Flash 0731 vs Mistral Medium 3.5 comparison based on?
34 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 Mistral Medium 3.5's on 3. Where only one model has a result, the page says so instead of naming a winner.