Model comparison
Claude Fable 5 vs DeepSeek-V3.1
Claude Fable 5 is the stronger model overall, scoring 66.8 to 42.8 on the Noometry Index. DeepSeek-V3.1 costs 47× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.
Last verified . 24 shared benchmarks.
DeepSeekSummary
- They share 24 benchmarks with published results for both. Claude Fable 5 scores higher in 8 categories and DeepSeek-V3.1 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Fable 5 leads 88.5 to 38.9.
- The biggest single-benchmark swing is WeirdML: 91.9% for Claude Fable 5 and 38.4% for DeepSeek-V3.1.
- DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $10 / $50 for Claude Fable 5.
- Claude Fable 5 accepts more context: 1M tokens versus 164K.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.
Side by side
| Claude Fable 5 | DeepSeek-V3.1 | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 66.8 | 42.8 |
| Released | 2026-06-07 | 2025-08-21 |
| Weights | Proprietary | Open |
| Context window | 1M | 164K |
| Max output | 128K | 8K |
| Input $ / M tokens | $10 | $0.25 |
| Output $ / M tokens | $50 | $0.95 |
| Results tracked | 62 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Fable 5 leads
Claude Fable 5: 70.6 (#4), DeepSeek-V3.1: 40.3 (#144)
| Benchmark | Claude Fable 5 | DeepSeek-V3.1 |
|---|---|---|
| WeirdML | 91.9% | 38.4% |
| LMArena Coding | 1519 | 1417 |
| DeepSWE | 69.9% | — |
| FrontierCode | 53.5% | — |
| LMArena WebDev | 1625 | — |
| FrontierSWE | 47% | — |
| SciCode | 61% | — |
| GSO | 78.4% | — |
| MirrorCode | 63.9% | — |
| ALE-Bench | 2,041 | — |
Agentic & Tool Use Not comparable
Claude Fable 5: 54.0 (#2), DeepSeek-V3.1: —
| Benchmark | Claude Fable 5 | DeepSeek-V3.1 |
|---|---|---|
| APEX-Agents | 63.6% | — |
| Remote Labor Index | 16.1% | — |
| τ²-bench Banking | 39.7% | — |
| PostTrainBench | 41.8% | — |
| GBAEval | 74.5% | — |
| GDP.pdf | 30% | — |
| LMArena Search | 1230 | — |
| Vending-Bench 2 | 5,680 | — |
Reasoning Claude Fable 5 leads
Claude Fable 5: 76.8 (#6), DeepSeek-V3.1: 27.9 (#110)
| Benchmark | Claude Fable 5 | DeepSeek-V3.1 |
|---|---|---|
| SimpleBench | 81.9% | 40% |
| Kagi LLM Benchmark | 91.4% | 53.2% |
| LMArena Hard Prompts | 1508 | 1417 |
| DTBench | 98.4% | 82.7% |
| LMCA | 61.1% | 24.3% |
| Epoch Capabilities Index | 162.06 | 139.92 |
| ARC-AGI-2 | 89.2% | — |
| NYT Connections (extended) | 92.7% | — |
| ARC-AGI-1 | 98.5% | — |
| CritPt | 28.6% | — |
| Chess Puzzles | 41% | — |
| EnigmaEval | 39.3% | — |
| EBR-Bench | 39.5% | — |
| Mystery Game Puzzles | 52% | — |
| Surface Evolver Bench | 95% | — |
| Bench to the Future 3 | 0.13 | — |
| ForecastBench | — | 58 |
Math Claude Fable 5 leads
Claude Fable 5: 88.5 (#5), DeepSeek-V3.1: 38.9 (#122)
| Benchmark | Claude Fable 5 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Math | 1519 | 1420 |
| FrontierMath (Tiers 1-3) | 87% | — |
| FrontierMath Tier 4 | 90.2% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 95% | — |
| FrontierMath Erdős | 0% | — |
Knowledge Claude Fable 5 leads
Claude Fable 5: 62.2 (#25), DeepSeek-V3.1: 43.7 (#90)
| Benchmark | Claude Fable 5 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Expert | 1534 | 1405 |
| GPQA Diamond | 85.9% | — |
| SimpleQA Verified | 70.7% | — |
| Vectara Hallucination Rate | — | 5.5% |
Multimodal Not comparable
Claude Fable 5: 45.3 (#17), DeepSeek-V3.1: —
| Benchmark | Claude Fable 5 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Vision | 1324 | — |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 35.8% | — |
| LMArena Document | 1496 | — |
Multilingual Claude Fable 5 leads
Claude Fable 5: 57.3 (#9), DeepSeek-V3.1: 51.6 (#106)
| Benchmark | Claude Fable 5 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Non-English | 1481 | 1400 |
| LMArena Chinese | 1543 | 1469 |
| LMArena French | 1505 | 1447 |
| LMArena German | 1486 | 1411 |
| LMArena Japanese | 1506 | 1378 |
| LMArena Korean | 1488 | 1337 |
| LMArena Russian | 1504 | 1405 |
| LMArena Spanish | 1498 | 1431 |
Instruction Following Claude Fable 5 leads
Claude Fable 5: 78.6 (#8), DeepSeek-V3.1: 73.9 (#110)
| Benchmark | Claude Fable 5 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Instruction Following | 1502 | 1400 |
Long Context Claude Fable 5 leads
Claude Fable 5: 46.3 (#23), DeepSeek-V3.1: 36.3 (#232)
| Benchmark | Claude Fable 5 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Longer Query | 1509 | 1422 |
| Fiction.LiveBench | — | 52.8% |
Writing & Preference Claude Fable 5 leads
Claude Fable 5: 75.9 (#5), DeepSeek-V3.1: 60.3 (#98)
| Benchmark | Claude Fable 5 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Text | 1491 | 1420 |
| LMArena Creative Writing | 1494 | 1401 |
| EQ-Bench Creative Writing | 1943 | 1436 |
| LMArena Multi-Turn | 1504 | 1408 |
| EQ-Bench 4 | 1340 | — |
Frequently asked questions
Is Claude Fable 5 better than DeepSeek-V3.1?
Claude Fable 5 is the stronger model overall, scoring 66.8 to 42.8 on the Noometry Index. DeepSeek-V3.1 costs 47× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.
Which is cheaper, Claude Fable 5 or DeepSeek-V3.1?
DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; Claude Fable 5 lists at $10 and $50.
Is Claude Fable 5 or DeepSeek-V3.1 better for coding?
Claude Fable 5 scores higher on coding benchmarks: 70.6 versus 40.3 in the Noometry coding category.
Which has the bigger context window?
Claude Fable 5 does, with 1M tokens against 164K.
How many benchmarks do Claude Fable 5 and DeepSeek-V3.1 share?
24 benchmarks have published results for both models. Claude Fable 5 has 62 scored results on Noometry and DeepSeek-V3.1 has 27.