Claude Fable 5 Max
| Released | 2026-06-09 |
|---|---|
| Price per 1M | $10.00 in · $50.00 out |
| Overall score | 63.4 · rank 41 |
| Context window | 1,000,000 tokens |
| Provider | Anthropic |
| Weights | Proprietary |
| Configuration | Max |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 63.4 | 41 | 28 |
| Overall: Coding | 62.7 | 45 | 21 |
| Overall: Reasoning | 65.3 | 29 | 13 |
| Overall: Agentic work | 62.4 | 56 | 20 |
| Overall: Frontend | 62.8 | 39 | 9 |
| Coding | 62.5 | 48 | 7 |
| Agents | 61.5 | 47 | 6 |
| Reasoning | 65.7 | 36 | 7 |
| Math | 65.2 | 19 | 4 |
| Knowledge | 64.5 | 9 | 2 |
| Frontend | 63.0 | 18 | 1 |
| Multimodal | 62.8 | 5 | 1 |
| Value vs price | +4.7 | 135 |
Buzz
| Posts on X | About 154 a day |
|---|---|
| Mood | 31% positive, 15% negative |
| Hacker News | 29 mentions this week |
| Checked | 2026-11-11 |
- Qwen 4 is announcement now & Beats GPT-6, Fable 5. and match Opus 5.5. - Qwen4-Max is already in preview. - 27B weight variants land first. - Alibaba confirmed Qwen 4 will heavily use RSI week ago. - across the entire lineup Max, Plus, Flash, and 27B. - leak say the first sampl…
- @lennox_saint Been doing this since Fable 5, or even since Opus 4.5-Sonnet 4.5. Though Opus 5.5 is just too good that I thought you didn't need Fable anymore. I'm using Opus 5.5 xhigh as the main session, Opus 5.5 high for read agents, and Opus 5.5 medium for write agents. May…
- This is a f*cking goldmine One free repo + Fable 5.2 just turned into an entire hedge fund desk (121k stars) Someone open-sourced a whole trading firm. Not a chatbot. A desk of AI agents that argue, size and veto trades like real people. It’s called TradingAgents, and with Fa…
Evidence
Coding 62.5 ±1.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierSWE | 47.0% | Epoch AI | 2026-11-11 |
| DeepSWE | 69.7% | Epoch AI | 2026-11-11 |
| MirrorCode | 70.0% | Epoch AI | 2026-10-30 |
| SWE-bench Verified (Vals run) | 95.0% | Vals AI | 2026-09-01 |
| SciCode | 61.0% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 89.8% | Vals AI | 2026-09-01 |
| ProgramBench | 2.0% | Vals AI | 2026-11-09 |
Agents 61.5 ±1.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench-Science | 15.7% | Vals AI | 2026-11-09 |
| Terminal-Bench 4 | 44.9% | Terminal-Bench | 2026-06-09 |
| Terminal-Bench 4.0 (Vals run) | 41.4% | Vals AI | 2026-11-09 |
| Terminal-Bench 2.1 (Vals run) | 80.5% | Vals AI | 2026-10-01 |
| tau2-bench Banking Knowledge | 39.7% | tau2-bench | 2026-07-23 |
| Tax Agent Bench | 38.3% | Vals AI | 2026-11-09 |
| Vending-Bench 2 | $4,967 | Epoch AI | 2026-11-11 |
Reasoning 65.7 ±2.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 89.2% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 89.2% | ARC Prize | 2026-11-11 |
| CritPt | 28.6% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 98.5% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 98.5% | Epoch AI | 2026-11-11 |
| SimpleBench | 81.9% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 85.9% | Epoch AI | 2026-08-06 |
| GPQA Diamond (Vals run) | 93.2% | Vals AI | 2026-09-01 |
| Chess Puzzles | 47.0% | Epoch AI | 2026-10-13 |
| Mystery Game Puzzles | 52.0% | Epoch AI | 2026-07-31 |
Math 65.2 ±1.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 87.0% | Epoch AI | 2026-06-09 |
| FrontierMath Tier 4 | 90.2% | Epoch AI | 2026-06-09 |
| OTIS Mock AIME 2024-2025 | 99.7% | Epoch AI | 2026-06-10 |
| ProofBench v1.1 | 95.0% | Vals AI | 2026-11-09 |
| ProofBench | 95.0% | Epoch AI | 2026-11-11 |
Knowledge 64.5 ±3.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMLU-Pro (Vals run) | 91.5% | Vals AI | 2026-09-01 |
| Legal Research Bench | 49.5% | Vals AI | 2026-11-09 |
Frontend 63.0 ±0.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 90.4% | Vals AI | 2026-11-09 |
Multimodal 62.8 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 89.3% | Vals AI | 2026-09-01 |
Names matched to this model
claude-fable-5-max