Model comparison
Claude Fable 5.1 vs DeepSeek V4 Flash
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 53.6 on the Noometry Index. DeepSeek V4 Flash costs 76× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.
Last verified . 37 shared benchmarks.
DeepSeekSummary
- They share 37 benchmarks with published results for both. Claude Fable 5.1 scores higher in 8 categories and DeepSeek V4 Flash in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Fable 5.1 leads 89.6 to 60.3.
- The biggest single-benchmark swing is FrontierMath Tier 4: 87.8% for Claude Fable 5.1 and 24.4% for DeepSeek V4 Flash.
- DeepSeek V4 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
- DeepSeek V4 Flash has downloadable open weights; the other is API-only.
Side by side
| Claude Fable 5.1 | DeepSeek V4 Flash | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 69.0 | 53.6 |
| Released | 2026-09-01 | 2026-04-24 |
| Weights | Proprietary | Open |
| Context window | 1M | 1M |
| Max output | 128K | 393K |
| Input $ / M tokens | $10 | $0.15 |
| Output $ / M tokens | $50 | $0.60 |
| Results tracked | 52 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Fable 5.1 leads
Claude Fable 5.1: 74.7 (#1), DeepSeek V4 Flash: 47.9 (#59)
| Benchmark | Claude Fable 5.1 | DeepSeek V4 Flash |
|---|---|---|
| FrontierCode | 50.9% | 18.8% |
| LMArena WebDev | 1744 | 1582 |
| SciCode | 63.1% | 49.9% |
| WeirdML | 92.9% | 63% |
| LMArena Coding | 1528 | 1457 |
| ALE-Bench | 2,143 | 1,306 |
| CursorBench | 51.8% | — |
| FrontierSWE | 56.3% | — |
| GSO | 88.2% | — |
| MirrorCode | 73.3% | — |
Agentic & Tool Use Not comparable
Claude Fable 5.1: 50.7 (#5), DeepSeek V4 Flash: —
| Benchmark | Claude Fable 5.1 | DeepSeek V4 Flash |
|---|---|---|
| APEX-Agents | 68.6% | — |
| Remote Labor Index | 17.9% | — |
| GDP.pdf | 29.6% | — |
| Vending-Bench 2 | 5,422 | — |
Reasoning Claude Fable 5.1 leads
Claude Fable 5.1: 76.7 (#7), DeepSeek V4 Flash: 53.7 (#30)
| Benchmark | Claude Fable 5.1 | DeepSeek V4 Flash |
|---|---|---|
| ARC-AGI-2 | 90% | 61.4% |
| NYT Connections (extended) | 90% | 89.6% |
| ARC-AGI-1 | 97.5% | 89% |
| CritPt | 31.1% | 16.6% |
| Chess Puzzles | 47% | 33% |
| LMArena Hard Prompts | 1526 | 1444 |
| Mystery Game Puzzles | 58% | 34% |
| DTBench | 97.6% | 90.9% |
| LMCA | 65.5% | 41.7% |
| Epoch Capabilities Index | 164.7 | 154.49 |
| SimpleBench | — | 61.1% |
| Kagi LLM Benchmark | — | 52.2% |
| EBR-Bench | 57.1% | — |
Math Claude Fable 5.1 leads
Claude Fable 5.1: 89.6 (#4), DeepSeek V4 Flash: 60.3 (#37)
| Benchmark | Claude Fable 5.1 | DeepSeek V4 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 90.2% | 57.5% |
| FrontierMath Tier 4 | 87.8% | 24.4% |
| OTIS Mock AIME 2024-2025 | 100% | 94.4% |
| ProofBench | 100% | 56% |
| LMArena Math | 1525 | 1427 |
| MathArena Final-Answer Competitions | — | 76.5% |
| FrontierMath Erdős | 0% | — |
Knowledge Claude Fable 5.1 leads
Claude Fable 5.1: 69.6 (#6), DeepSeek V4 Flash: 55.4 (#48)
| Benchmark | Claude Fable 5.1 | DeepSeek V4 Flash |
|---|---|---|
| SimpleQA Verified | 70.8% | 33.6% |
| LMArena Expert | 1535 | 1441 |
| GPQA Diamond | — | 91% |
| Humanity's Last Exam | 46.5% | — |
Multimodal Not comparable
Claude Fable 5.1: 53.9 (#4), DeepSeek V4 Flash: —
| Benchmark | Claude Fable 5.1 | DeepSeek V4 Flash |
|---|---|---|
| LMArena Vision | 1318 | — |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
| LMArena Document | 1513 | — |
Multilingual Claude Fable 5.1 leads
Claude Fable 5.1: 59.1 (#3), DeepSeek V4 Flash: 53.0 (#72)
| Benchmark | Claude Fable 5.1 | DeepSeek V4 Flash |
|---|---|---|
| LMArena Non-English | 1507 | 1420 |
| LMArena Chinese | 1586 | 1468 |
| LMArena French | 1525 | 1439 |
| LMArena German | 1500 | 1418 |
| LMArena Japanese | 1543 | 1406 |
| LMArena Korean | 1534 | 1384 |
| LMArena Russian | 1521 | 1428 |
| LMArena Spanish | 1516 | 1436 |
Instruction Following Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#6), DeepSeek V4 Flash: 74.9 (#81)
| Benchmark | Claude Fable 5.1 | DeepSeek V4 Flash |
|---|---|---|
| LMArena Instruction Following | 1517 | 1421 |
Long Context Claude Fable 5.1 leads
Claude Fable 5.1: 46.7 (#20), DeepSeek V4 Flash: 43.8 (#85)
| Benchmark | Claude Fable 5.1 | DeepSeek V4 Flash |
|---|---|---|
| LMArena Longer Query | 1522 | 1434 |
Writing & Preference Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#2), DeepSeek V4 Flash: 63.8 (#61)
| Benchmark | Claude Fable 5.1 | DeepSeek V4 Flash |
|---|---|---|
| LMArena Text | 1510 | 1432 |
| LMArena Creative Writing | 1507 | 1403 |
| EQ-Bench Creative Writing | 2162 | 1559 |
| LMArena Multi-Turn | 1492 | 1449 |
Frequently asked questions
Is Claude Fable 5.1 better than DeepSeek V4 Flash?
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 53.6 on the Noometry Index. DeepSeek V4 Flash costs 76× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.
Which is cheaper, Claude Fable 5.1 or DeepSeek V4 Flash?
DeepSeek V4 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Claude Fable 5.1 lists at $10 and $50.
Is Claude Fable 5.1 or DeepSeek V4 Flash better for coding?
Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 47.9 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Claude Fable 5.1 and DeepSeek V4 Flash share?
37 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and DeepSeek V4 Flash has 41.