Claude Fable 5 vs Deepseek v4 Pro
Claude Fable 5 
Deepseek v4 Pro Verdict
- Claude Fable 5 leads on quality: 70.5 vs 60.4.
- Claude Fable 5 is stronger in agents & tools, coding, composite, human preference, instruction following, knowledge, long context, multimodal, reasoning.
- Deepseek v4 Pro (high) is stronger in maths.
| Metric | Claude Fable 5 | Deepseek v4 Pro (high) |
|---|---|---|
| BenchLeader Index | 70.5 | 60.4 |
| Agents & tools score | 74.4 | – |
| Coding score | 70.5 | 59.4 |
| Composite score | 91.8 | – |
| Human preference score | 71.6 | 65.8 |
| Instruction following score | 62.9 | – |
| Knowledge score | 71.4 | – |
| Long context score | 67.8 | – |
| Multimodal score | 69.7 | – |
| Reasoning score | 75.9 | 66.0 |
| Maths score | – | 66.2 |
| Blended price $/M | $20.00 | – |
| Output speed | 63 tok/s | – |
| Time to first answer | 102.3 s | – |
| Context window | 1M | – |
| GPQA Diamond | – | 90.9% |
| OTIS Mock AIME | – | 95.6% |
| SciCode | – | 46.4% |
| Remote Labor Index | 16.1% | – |
| WeirdML | – | 46.5% |
| APEX-Agents | 45.0% | – |
| FrontierCode | 53.5% | – |
| Epoch Capabilities Index | 163.4 | – |
| LMArena Text | 1507 | 1460 |
| LMArena Hard Prompts | 1533 | 1482 |
| LMArena Coding | 1551 | 1505 |
| LMArena WebDev | 1628 | 1580 |
| LMArena Vision | 1330 | – |
| AA Intelligence Index | 49.7 | – |
| IFBench | 63.5% | – |
| AA-LCR | 82.3% | – |
| AA-Omniscience | 43.3 | – |
| Terminal-Bench Hard | 62.9% | – |
| GPQA Diamond (AA) | 92.6% | – |
| Humanity's Last Exam (AA) | 55.5% | – |
| SciCode (AA) | 61.0% | – |
| τ²-Bench Telecom (AA) | 98.5% | – |
| LiveCodeBench | 89.8% | – |
| MMLU-Pro | 91.5% | – |
| IOI | 72.3% | – |
| LegalBench | 88.6% | – |
| CorpFin | 71.8% | – |
| TaxEval | 76.9% | – |
| Terminal-Bench 2.1 (Vals) | 80.5% | – |
| SWE-bench (Vals) | 95.0% | – |
| GPQA Diamond (Vals) | 93.2% | – |
| Vals Index | 66.0 | – |
| MCP Atlas | 83.3% | – |
| PRBench Finance | 53.9% | – |
| PRBench Legal | 52.6% | – |
| HiL-Bench | 56.3% | – |
| EQ-Bench 4 | 1340 | – |
| Kagi LLM Benchmark | 88.8% | – |
Data as of 2026-09-10. Best configuration of each model; every score links to its source on the model pages.
Claude Fable 5 vs Deepseek v4 Pro: questions
- Is Claude Fable 5 better than Deepseek v4 Pro?
- Claude Fable 5 leads on quality: 70.5 vs 60.4. The BenchLeader Index combines every independent quality benchmark; Claude Fable 5 is ahead overall as of 2026-09-10, but check the category scores for your use.
- Is Claude Fable 5 better than Deepseek v4 Pro for coding?
- Claude Fable 5 scores higher in coding (71 vs 59 on the category index, where 50 is average).