Side-by-side comparison · models
Claude Fable 5.1 vs Claude Fable 5.1 (batch)
What we have checked about each, line by line. Every value shows where it came from and when we last confirmed it.
Models
Claude Fable 5.1
Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors.
Models
Claude Fable 5.1 (batch)
Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors.
Checked facts
Line by line
| Measure | Claude Fable 5.1 | Claude Fable 5.1 (batch) |
|---|---|---|
| Input price | $10.00 per million tokens | Not checked yet |
| Output price | $50.00 per million tokens | Not checked yet |
| Price on amazon-bedrock | $0.250 per million cached input tokens | Not checked yet |
| Price on amazon-bedrock | $10.00 per million input tokens | Not checked yet |
| Price on amazon-bedrock | $50.00 per million output tokens | Not checked yet |
| Price on anthropic | $0.250 per million cached input tokens | Not checked yet |
| Price on anthropic | $10.00 per million input tokens | Not checked yet |
| Price on anthropic | $50.00 per million output tokens | Not checked yet |
| Price on azure | $0.250 per million cached input tokens | Not checked yet |
| Price on azure | $10.00 per million input tokens | Not checked yet |
| Price on azure | $50.00 per million output tokens | Not checked yet |
| Price on google-vertex | $0.250 per million cached input tokens | Not checked yet |
| Price on google-vertex | $10.00 per million input tokens | Not checked yet |
| Price on google-vertex | $50.00 per million output tokens | Not checked yet |
| Latest version | anthropic/claude-fable-5.1-20260831 | anthropic/claude-fable-5.1-20260831 |
| Time to first token (ms) | 97,890 | 97,890 |
| Time to first token (ms) on amazon-bedrock | 2,912 | Not checked yet |
| Time to first token (ms) on anthropic | 2,759 | Not checked yet |
| Time to first token (ms) on azure | 4,508 | Not checked yet |
| Time to first token (ms) on google-vertex | 2,529 | Not checked yet |
| Output speed (tokens a second) | 61.3 | 61.3 |
| Output speed (tokens a second) on amazon-bedrock | 54 | Not checked yet |
| Output speed (tokens a second) on anthropic | 63 | Not checked yet |
| Output speed (tokens a second) on azure | 59 | Not checked yet |
| Output speed (tokens a second) on google-vertex | 69 | Not checked yet |
| Tokens served on OpenRouter in a day | 25.9B (for 7 Nov 2026) | Not checked yet |
| Tool calls on OpenRouter in a day | 134.9K (for 7 Nov 2026) | Not checked yet |
| Artificial Analysis Intelligence Index | 50 | Not checked yet |
| Artificial Analysis Coding Index | 81.6 | Not checked yet |
| Artificial Analysis Agentic Index | 57.9 | Not checked yet |
| LMArena text rating (Elo) | 1,513 | Not checked yet |
| LMArena web development rating (Elo) | 1,746 | Not checked yet |
| LMArena vision rating (Elo) | 1,321 | Not checked yet |
| Design Arena rating (Elo) | 1,424 | Not checked yet |
| Frontiermath tiers 1 3 v2 private | 90.2% (for 1 Sept 2026) | Not checked yet |
| Simpleqa verified | 70.8% (for 1 Sept 2026) | Not checked yet |
| Arc agi 2 | 90% (for 1 Sept 2026) | Not checked yet |
| Apex agents | 68.6% (for 1 Sept 2026) | Not checked yet |
| Arc agi | 97.5% (for 1 Sept 2026) | Not checked yet |
| Chess puzzles | 48% (for 1 Sept 2026) | Not checked yet |
| Dtbench | 97.6% (for 1 Sept 2026) | Not checked yet |
| Ebr bench | 57.1% (for 1 Sept 2026) | Not checked yet |
| Frontiercode | 50.9% (for 1 Sept 2026) | Not checked yet |
| Frontiermath tier 4 v2 private | 87.8% (for 1 Sept 2026) | Not checked yet |
| Frontierswe | 56.3% (for 1 Sept 2026) | Not checked yet |
| Furniture assembly | 70% (for 1 Sept 2026) | Not checked yet |
| Gso bench | 88.2% (for 1 Sept 2026) | Not checked yet |
| Lmca | 65.5% (for 1 Sept 2026) | Not checked yet |
| Mirrorcode | 73.3% (for 1 Sept 2026) | Not checked yet |
| Mystery game puzzles | 58% (for 1 Sept 2026) | Not checked yet |
| Proofbench | 100% (for 1 Sept 2026) | Not checked yet |
| Remote labor index | 17.9% (for 1 Sept 2026) | Not checked yet |
| Spireclimb | 2% (for 1 Sept 2026) | Not checked yet |
| Weirdml | 92.9% (for 1 Sept 2026) | Not checked yet |
| Weirdml v3 | 43.5% (for 1 Sept 2026) | Not checked yet |
| Otis mock aime 2024 2025 | 100% (saturated benchmark: the top models all score near the ceiling) (for 1 Sept 2026) | Not checked yet |
A line appears only when at least one record has a value we confirmed from a source. Values we have not confirmed are left out, never guessed. Records of different types share fewer lines.
Add a third
Compare with one more record
How this works
Share it, or build your own
This page works for any two or three records in the directory, of any type. The link stays the same whichever order you name them in, so you can share it as it is. Change the records in the address, for example /directories/vs/claude-code-vs-cursor, or start from our editorial comparisons.