Side-by-side comparison · models
Claude Fable 5 vs Claude Fable 5 (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
Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding.
Models
Claude Fable 5 (batch)
Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding.
Checked facts
Line by line
| Measure | Claude Fable 5 | Claude Fable 5 (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 | $1.00 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 | $1.00 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 | $1.00 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 claude-on-aws | $1.00 per million cached input tokens | Not checked yet |
| Price on claude-on-aws | $10.00 per million input tokens | Not checked yet |
| Price on claude-on-aws | $50.00 per million output tokens | Not checked yet |
| Price on google-vertex | $1.00 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-5-fable-20260609 | anthropic/claude-5-fable-20260609 |
| Time to first token (ms) | 115,760 | 115,760 |
| Time to first token (ms) on amazon-bedrock | 4,485 | Not checked yet |
| Time to first token (ms) on anthropic | 3,508 | Not checked yet |
| Time to first token (ms) on azure | 5,491 | Not checked yet |
| Time to first token (ms) on claude-on-aws | 3,449 | Not checked yet |
| Time to first token (ms) on google-vertex | 2,784 | Not checked yet |
| Output speed (tokens a second) | 66.3 | 66.3 |
| Output speed (tokens a second) on amazon-bedrock | 42 | Not checked yet |
| Output speed (tokens a second) on anthropic | 56 | Not checked yet |
| Output speed (tokens a second) on azure | 61 | Not checked yet |
| Output speed (tokens a second) on claude-on-aws | 50 | Not checked yet |
| Output speed (tokens a second) on google-vertex | 57 | Not checked yet |
| Tokens served on OpenRouter in a day | 4.6B (for 10 Nov 2026) | Not checked yet |
| Tool calls on OpenRouter in a day | 23.1K (for 10 Nov 2026) | Not checked yet |
| Artificial Analysis Intelligence Index | 49.6 | Not checked yet |
| Artificial Analysis Coding Index | 76.5 | Not checked yet |
| Artificial Analysis Agentic Index | 50.7 | Not checked yet |
| LMArena text rating (Elo) | 1,492 | Not checked yet |
| LMArena web development rating (Elo) | 1,625 | Not checked yet |
| LMArena vision rating (Elo) | 1,326 | Not checked yet |
| Design Arena rating (Elo) | 1,329 | Not checked yet |
| Gpqa diamond | 85.9% (for 9 June 2026) | Not checked yet |
| Frontiermath tiers 1 3 v2 private | 87% (for 9 June 2026) | Not checked yet |
| Simpleqa verified | 70.7% (for 9 June 2026) | Not checked yet |
| Arc agi 2 | 89.2% (for 9 June 2026) | Not checked yet |
| Apex agents | 63.6% (for 9 June 2026) | Not checked yet |
| Arc agi | 98.5% (for 9 June 2026) | Not checked yet |
| Chess puzzles | 47% (for 9 June 2026) | Not checked yet |
| Dtbench | 98.4% (for 9 June 2026) | Not checked yet |
| Ebr bench | 39.5% (for 9 June 2026) | Not checked yet |
| Frontiercode | 53.5% (for 9 June 2026) | Not checked yet |
| Frontiermath tier 4 v2 private | 90.2% (for 9 June 2026) | Not checked yet |
| Frontierswe | 47% (for 9 June 2026) | Not checked yet |
| Furniture assembly | 35.8% (for 9 June 2026) | Not checked yet |
| Gso bench | 78.4% (for 9 June 2026) | Not checked yet |
| Lmca | 61.2% (for 9 June 2026) | Not checked yet |
| Mirrorcode | 63.9% (for 9 June 2026) | Not checked yet |
| Mystery game puzzles | 52% (for 9 June 2026) | Not checked yet |
| Posttrainbench | 41.8% (for 9 June 2026) | Not checked yet |
| Proofbench | 95% (for 9 June 2026) | Not checked yet |
| Remote labor index | 16.1% (for 9 June 2026) | Not checked yet |
| Simplebench | 81.9% (for 9 June 2026) | Not checked yet |
| Surface evolver bench | 95% (for 9 June 2026) | Not checked yet |
| Weirdml | 91.9% (for 9 June 2026) | Not checked yet |
| Weirdml v3 | 27.9% (for 9 June 2026) | Not checked yet |
| Otis mock aime 2024 2025 | 100% (saturated benchmark: the top models all score near the ceiling) (for 9 June 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.