Claude Fable 5.2 vs DeepSeek V4 Flash 0731
Claude Fable 5.2 leads DeepSeek V4 Flash 0731 on coding, 87.8 to 51.8 on the Vibe Coding Index, and DeepSeek V4 Flash 0731 costs 114.9x less per output token ($0.348 vs $40.00 per million). Updated November 14, 2026; 33 benchmarks have a result for both.
Claude Fable 5.2 or DeepSeek V4 Flash 0731: which to pick
Pick Claude Fable 5.2 for coding: it scores 87.8 on the Vibe Coding Index against 51.8 for DeepSeek V4 Flash 0731.
Pick DeepSeek V4 Flash 0731 for output tokens 114.9x cheaper ($0.348 vs $40.00 per million) and a larger context window (1.05M against 1M tokens).
- Shared results
- 33
- Claude Fable 5.2 only
- 35
- DeepSeek V4 Flash 0731 only
- 25
- 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
Claude Fable 5.2
Claude Fable 5.2 scores 87.8 against 51.8.
4 benchmarks behind each score
Intelligence
AA Intelligence Index
No call
Only Claude Fable 5.2 has a AA Intelligence Index result, 64.6.
Directional only
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
Claude Fable 5.2
Claude Fable 5.2 leads, 1351 against 1230.
Same board, both measured
General
Vals Index
No call
Only Claude Fable 5.2 has a Vals Index result, 71.3%.
Directional only
Long documents
Listed context window
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4 Flash 0731
Claude Fable 5.2 $0.028, DeepSeek V4 Flash 0731 $0.0003 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
- Claude Fable 5.2 87.8 from 4 benchmarks, DeepSeek V4 Flash 0731 51.8 from 4 benchmarks.
- Widest category
- Knowledge, 60.4 points apart on average over 1 shared benchmark.
- Widest single gap
- FrontierMath, tier 4: Claude Fable 5.2 100.0% against DeepSeek V4 Flash 0731 24.4%, 75.6 points apart on a 0 to 100 scale.
- Output price
- Claude Fable 5.2 $40.00 against DeepSeek V4 Flash 0731 $0.348 per million output tokens, 114.9x apart.
- Context window
- Claude Fable 5.2 takes 1M tokens, DeepSeek V4 Flash 0731 1.05M.
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 | Claude Fable 5.2 | Bars | DeepSeek V4 Flash 0731 | Ties |
|---|---|---|---|---|
| Coding | 6 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 4 | 0 | ||
| Reasoning | 8 | 0 | ||
| Math | 4 | 0 | ||
| Knowledge | 1 | 0 | ||
| Web design | 5 | 0 | ||
| General | 4 | 0 | ||
| All shared boards | 33 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index60
| Benchmark | Claude Fable 5.2 | DeepSeek V4 Flash 0731 | Leader |
|---|---|---|---|
| LiveBench coding | 79.2% | Not measured | Only Claude Fable 5.2 measured |
| LMArena WebDev | 1838 | Not measured | Only Claude Fable 5.2 measured |
| AA Coding Index | Not measured | 69.1 | Only DeepSeek V4 Flash 0731 measured |
| LiveCodeBench (Vals AI) | Not measured | 87.3% | Only DeepSeek V4 Flash 0731 measured |
| SWE-bench Verified (Vals AI) | Not measured | 88.8% | Only DeepSeek V4 Flash 0731 measured |
| Terminal-Bench 4 (Vals AI) | 65.2% | 18.7% | Claude Fable 5.2 |
| Vibe Code Bench (Vals AI) | 93.8% | 74.7% | Claude Fable 5.2 |
| Code migration (Vals AI) | Not measured | 38.6% | Only DeepSeek V4 Flash 0731 measured |
| ProgramBench (Vals AI) | 19.0% | 0.0% | Claude Fable 5.2 |
| IOI (Vals AI) | Not measured | 32.7% | Only DeepSeek V4 Flash 0731 measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 67.0% | Only DeepSeek V4 Flash 0731 measured |
| SWE-bench Multimodal (Vals AI) | 62.3% | Not measured | Only Claude Fable 5.2 measured |
| SkillsBench (Vals AI) | Not measured | 50.7% | Only DeepSeek V4 Flash 0731 measured |
| CyberBench (Vals AI) | Not measured | 72.1% | Only DeepSeek V4 Flash 0731 measured |
| SciCode | 67.7% | 50.3% | Claude Fable 5.2 |
| Terminal-Bench 4.0 (Artificial Analysis run) | 61.6% | 12.1% | Claude Fable 5.2 |
| FrontierCode 2.0 | 49.1% | Not measured | Only Claude Fable 5.2 measured |
| FrontierCode | Not measured | 18.8% | Only DeepSeek V4 Flash 0731 measured |
| FrontierSWE | 69.9% | Not measured | Only Claude Fable 5.2 measured |
| WeirdML | Not measured | 63.0% | Only DeepSeek V4 Flash 0731 measured |
| ALE-Bench | 2509.8 | 1306.1 | Claude Fable 5.2 |
| LMArena WebDev: React | 1915 | Not measured | Only Claude Fable 5.2 measured |
| LMArena WebDev: HTML | 1738 | Not measured | Only Claude Fable 5.2 measured |
| GameBench 2 | 99.1 | Not measured | Only Claude Fable 5.2 measured |
| CursorBench 4.0 | 60.0% | Not measured | Only Claude Fable 5.2 measured |
| Neither model has a result on the other 27 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Claude Fable 5.2 | DeepSeek V4 Flash 0731 | Leader |
|---|---|---|---|
| AA Intelligence Index | 64.6 | Not measured | Only Claude Fable 5.2 measured |
| Epoch Capabilities Index | 173.4 | 154.4 | Claude Fable 5.2 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Claude Fable 5.2 | DeepSeek V4 Flash 0731 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 41.0 | Only DeepSeek V4 Flash 0731 measured |
| Design Arena: agents building full-stack apps | 1402 | Not measured | Only Claude Fable 5.2 measured |
| Design Arena: agents building mobile apps | 1325 | Not measured | Only Claude Fable 5.2 measured |
| Design Arena: spreadsheets | 1434 | Not measured | Only Claude Fable 5.2 measured |
| LiveBench research | 94.5% | Not measured | Only Claude Fable 5.2 measured |
| LiveBench browser | 86.9% | Not measured | Only Claude Fable 5.2 measured |
| LiveBench long agentic | 82.9% | Not measured | Only Claude Fable 5.2 measured |
| Finance Agent (Vals AI) | Not measured | 49.5% | Only DeepSeek V4 Flash 0731 measured |
| Tax Agent Bench (Vals AI) | 32.1% | 28.1% | Claude Fable 5.2 |
| Legal Research Bench (Vals AI) | 46.1% | 30.3% | Claude Fable 5.2 |
| Harvey's Legal Agent Benchmark (Vals AI) | 5.0% | Not measured | Only Claude Fable 5.2 measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 57.0% | Only DeepSeek V4 Flash 0731 measured |
| BioMysteryBench (Vals AI) | 83.7% | 64.4% | Claude Fable 5.2 |
| Terminal-Bench-Science (Vals AI) | 55.7% | 4.3% | Claude Fable 5.2 |
| Vals Science Index | 63.7% | Not measured | Only Claude Fable 5.2 measured |
| APEX-Agents | 80.1% | Not measured | Only Claude Fable 5.2 measured |
| Remote Labor Index | 41.3% | Not measured | Only Claude Fable 5.2 measured |
| SpireClimb | 15.5% | Not measured | Only Claude Fable 5.2 measured |
| Toolathlon-Verified | Not measured | 70.7% | Only DeepSeek V4 Flash 0731 measured |
| Neither model has a result on the other 25 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index80
| Benchmark | Claude Fable 5.2 | DeepSeek V4 Flash 0731 | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 89.9% | Only DeepSeek V4 Flash 0731 measured |
| LiveBench reasoning | 88.8% | Not measured | Only Claude Fable 5.2 measured |
| MysteryMechanism (Vals AI) | 51.8% | Not measured | Only Claude Fable 5.2 measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 90.8% | Only DeepSeek V4 Flash 0731 measured |
| Humanity's Last Exam (Artificial Analysis run) | 74.3% | 38.6% | Claude Fable 5.2 |
| HLE-Diamond (Artificial Analysis run) | 80.2% | Not measured | Only Claude Fable 5.2 measured |
| CritPt v2, hard subset (Artificial Analysis run) | 76.5% | Not measured | Only Claude Fable 5.2 measured |
| GPQA Diamond (Epoch AI run) | 93.9% | 91.0% | Claude Fable 5.2 |
| ARC-AGI | 98.5% | 89.0% | Claude Fable 5.2 |
| ARC-AGI-2 | 93.8% | 61.4% | Claude Fable 5.2 |
| SimpleBench | 94.9% | 61.1% | Claude Fable 5.2 |
| Chess puzzles | 79.0% | 32.0% | Claude Fable 5.2 |
| Mystery game puzzles | 90.0% | 34.0% | Claude Fable 5.2 |
| EBR-bench | 90.5% | Not measured | Only Claude Fable 5.2 measured |
| Humanity's Last Exam (Scale run) | 72.4% | Not measured | Only Claude Fable 5.2 measured |
| GoBench | 2566 | 1448 | Claude Fable 5.2 |
| Neither model has a result on the other 10 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Claude Fable 5.2 | DeepSeek V4 Flash 0731 | Leader |
|---|---|---|---|
| OTIS Mock AIME | 99.7% | 94.4% | Claude Fable 5.2 |
| FrontierMath, tiers 1 to 3 | 95.1% | 57.5% | Claude Fable 5.2 |
| FrontierMath, tier 4 | 100.0% | 24.4% | Claude Fable 5.2 |
| ProofBench | 100.0% | 56.0% | Claude Fable 5.2 |
| MathArena | 82.8% | Not measured | Only Claude Fable 5.2 measured |
| Neither model has a result on the other 9 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Claude Fable 5.2 | DeepSeek V4 Flash 0731 | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 86.2% | Only DeepSeek V4 Flash 0731 measured |
| LegalBench (Vals AI) | Not measured | 77.7% | Only DeepSeek V4 Flash 0731 measured |
| CorpFin (Vals AI) | Not measured | 61.9% | Only DeepSeek V4 Flash 0731 measured |
| TaxEval (Vals AI) | Not measured | 70.7% | Only DeepSeek V4 Flash 0731 measured |
| MedCode (Vals AI) | Not measured | 41.4% | Only DeepSeek V4 Flash 0731 measured |
| AA-Omniscience | 66.8 | Not measured | Only Claude Fable 5.2 measured |
| SimpleQA Verified | 94.0% | 33.6% | Claude Fable 5.2 |
| PRBench Finance | 47.1% | Not measured | Only Claude Fable 5.2 measured |
| PRBench Legal | 49.0% | Not measured | Only Claude Fable 5.2 measured |
| Neither model has a result on the other 12 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Claude Fable 5.2 | DeepSeek V4 Flash 0731 | Leader |
|---|---|---|---|
| Design Arena: websites | 1351 | 1230 | Claude Fable 5.2 |
| Design Arena: UI components | 1371 | 1227 | Claude Fable 5.2 |
| Design Arena: game dev | 1396 | 1198 | Claude Fable 5.2 |
| Design Arena: data viz | Not measured | 1169 | Only DeepSeek V4 Flash 0731 measured |
| Design Arena: 3D | 1517 | 1187 | Claude Fable 5.2 |
| Design Arena: all code categories | 1373 | 1219 | Claude Fable 5.2 |
| Design Arena: SVG | Not measured | 1170 | Only DeepSeek V4 Flash 0731 measured |
| Design Arena: ASCII art | Not measured | 1092 | Only DeepSeek V4 Flash 0731 measured |
| LiveBench design | 85.1% | Not measured | Only Claude Fable 5.2 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Claude Fable 5.2 | DeepSeek V4 Flash 0731 | Leader |
|---|---|---|---|
| Vals Index | 71.3% | Not measured | Only Claude Fable 5.2 measured |
| LiveBench data analysis | 81.5% | Not measured | Only Claude Fable 5.2 measured |
| MedScribe (Vals AI) | Not measured | 80.4% | Only DeepSeek V4 Flash 0731 measured |
| Long context reasoning (AA-LCR) | 83.3% | 79.7% | Claude Fable 5.2 |
| GDPval-AA | 1831 | 1437 | Claude Fable 5.2 |
| DTBench | 99.2% | 90.9% | Claude Fable 5.2 |
| LMCA | 70.6% | 41.7% | Claude Fable 5.2 |
| Furniture assembly | 90.0% | Not measured | Only Claude Fable 5.2 measured |
| Neither model has a result on the other 41 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Fable 5.2 | DeepSeek V4 Flash 0731 | 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 | Anthropic Claude Fable 5.2 | DeepSeek V4 Flash 0731 |
|---|---|---|
| Maker | Anthropic | DeepSeek |
| Weights | No public weights listed | Open weights |
| Released | November 9, 2026 | July 31, 2026 |
| Context window | 1M | 1.05M |
| Input $/Mtok | $8.00 | $0.14 |
| Output $/Mtok | $40.00 | $0.348 |
| Coding index | 87.8 | 51.8 |
| Independent measurements behind it | 4 | 4 |
| Cost per solved task | Not computable | $0.01 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Fable 5.2 better than DeepSeek V4 Flash 0731 for coding?
Pick Claude Fable 5.2 for coding: it scores 87.8 on the Vibe Coding Index against 51.8 for DeepSeek V4 Flash 0731. Pick DeepSeek V4 Flash 0731 for output tokens 114.9x cheaper ($0.348 vs $40.00 per million) and a larger context window (1.05M against 1M tokens).
Which is cheaper, Claude Fable 5.2 or DeepSeek V4 Flash 0731?
Claude Fable 5.2 costs $8.00 per million input tokens and $40.00 per million output tokens; DeepSeek V4 Flash 0731 costs $0.14 and $0.348. Cost per solved task is known for DeepSeek V4 Flash 0731 only.
Which has the bigger context window, Claude Fable 5.2 or DeepSeek V4 Flash 0731?
DeepSeek V4 Flash 0731, with 1.05M tokens against 1M.
How many benchmarks is the Claude Fable 5.2 vs DeepSeek V4 Flash 0731 comparison based on?
33 benchmarks have a result for both models as of November 14, 2026. Claude Fable 5.2's coding index rests on 4 independent benchmarks and DeepSeek V4 Flash 0731's on 4. Where only one model has a result, the page says so instead of naming a winner.