Leaderboard / Model
Claude Fable 5.1
Anthropic · Closed weights · Released Sep 1, 2026 · $10 in · $50 out per 1M tokens
92Overall · rank 1
Score by job
Coding
Not enough data · 2 of 5 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| FrontierCode | 50.9% | claude-fable-5-1_medium | 1.18 |
| LMArena Coding | 1511 rating | claude-fable-5.1-max | 0.99 |
Agents
99 · rank 2 · 2 of 4 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| APEX-Agents | 68.6% | claude-fable-5-1_unknown | 1.55 |
| Remote Labor Index | 17.9% | claude-fable-5-1_unknown | 1.40 |
Reasoning
82 · rank 5 · 2 of 4 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| ARC-AGI-2 | 90.0% | claude-fable-5-1_max | 1.20 |
| Humanity’s Last Exam | 46.5% | claude-fable-5-1_xhigh | 1.00 |
Math
95 · rank 2 · 5 of 5 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| FrontierMath Tiers 1–3 | 90.2% | claude-fable-5-1_max | 1.53 |
| FrontierMath Tier 4 | 87.8% | claude-fable-5-1_max | 1.96 |
| OTIS Mock AIME | 100.0% | claude-fable-5-1_max | 1.09 |
| ProofBench | 100.0% | claude-fable-5-1_max | 2.06 |
| LMArena Math | 1522 rating | claude-fable-5.1-max | 1.55 |
Writing
97 · rank 2 · 2 of 2 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| LMArena Creative Writing | 1508 rating | claude-fable-5.1-max | 1.70 |
| LMArena Instruction Following | 1513 rating | claude-fable-5.1-max | 1.82 |
Design
86 · rank 3 · 1 of 1 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| LMArena WebDev | 1755 rating | claude-fable-5.1-max | 1.95 |