# Claude Fable 5.1 vs Mercury 2.5

> Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 33.5 on the Noometry Index. Mercury 2.5 costs 296× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-fable-5-1-vs-mercury-2-5
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Claude Fable 5.1 scores higher in 3 categories and Mercury 2.5 in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Fable 5.1 leads 89.6 to 23.3.
- The biggest single-benchmark swing is ProofBench: 100% for Claude Fable 5.1 and 3% for Mercury 2.5.
- Mercury 2.5 is cheaper at $0.04 / $0.15 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
- Claude Fable 5.1 accepts more context: 1M tokens versus 260K.

## Snapshot

| | Claude Fable 5.1 | Mercury 2.5 |
|---|---|---|
| Provider | Anthropic | Inception |
| Noometry Index | 69.0 | 33.5 |
| Rank | 2 | 242 |
| Context | 1M | 260K |
| Input $/M | $10 | $0.04 |
| Output $/M | $50 | $0.15 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Fable 5.1: 74.7 (#1)
- Mercury 2.5: 39.5 (#156)

| Benchmark | Claude Fable 5.1 | Mercury 2.5 |
|---|---|---|
| SciCode | 63.1% | 38.5% |
| ALE-Bench | 2,143 | 301.65 |
| FrontierCode | 50.9% | — |
| CursorBench | 51.8% | — |
| LMArena WebDev | 1744 | — |
| FrontierSWE | 56.3% | — |
| GSO | 88.2% | — |
| WeirdML | 92.9% | — |
| LMArena Coding | 1528 | — |
| MirrorCode | 73.3% | — |

## Agentic & Tool Use

- Claude Fable 5.1: 50.7 (#5)
- Mercury 2.5: —

| Benchmark | Claude Fable 5.1 | Mercury 2.5 |
|---|---|---|
| APEX-Agents | 68.6% | — |
| Remote Labor Index | 17.9% | — |
| GDP.pdf | 29.6% | — |
| Vending-Bench 2 | 5,422 | — |

## Reasoning

- Claude Fable 5.1: 76.7 (#7)
- Mercury 2.5: 22.4 (#193)

| Benchmark | Claude Fable 5.1 | Mercury 2.5 |
|---|---|---|
| CritPt | 31.1% | 0% |
| ARC-AGI-2 | 90% | — |
| NYT Connections (extended) | 90% | — |
| ARC-AGI-1 | 97.5% | — |
| Chess Puzzles | 47% | — |
| EBR-Bench | 57.1% | — |
| LMArena Hard Prompts | 1526 | — |
| Mystery Game Puzzles | 58% | — |
| DTBench | 97.6% | — |
| LMCA | 65.5% | — |
| Epoch Capabilities Index | 164.7 | — |

## Math

- Claude Fable 5.1: 89.6 (#4)
- Mercury 2.5: 23.3 (#272)

| Benchmark | Claude Fable 5.1 | Mercury 2.5 |
|---|---|---|
| ProofBench | 100% | 3% |
| FrontierMath (Tiers 1-3) | 90.2% | — |
| FrontierMath Tier 4 | 87.8% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| LMArena Math | 1525 | — |
| FrontierMath Erdős | 0% | — |

## Knowledge

- Claude Fable 5.1: 69.6 (#6)
- Mercury 2.5: —

| Benchmark | Claude Fable 5.1 | Mercury 2.5 |
|---|---|---|
| Humanity's Last Exam | 46.5% | — |
| SimpleQA Verified | 70.8% | — |
| LMArena Expert | 1535 | — |

## Multimodal

- Claude Fable 5.1: 53.9 (#4)
- Mercury 2.5: —

| Benchmark | Claude Fable 5.1 | Mercury 2.5 |
|---|---|---|
| LMArena Vision | 1318 | — |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
| LMArena Document | 1513 | — |

## Multilingual

- Claude Fable 5.1: 59.1 (#3)
- Mercury 2.5: —

| Benchmark | Claude Fable 5.1 | Mercury 2.5 |
|---|---|---|
| LMArena Non-English | 1507 | — |
| LMArena Chinese | 1586 | — |
| LMArena French | 1525 | — |
| LMArena German | 1500 | — |
| LMArena Japanese | 1543 | — |
| LMArena Korean | 1534 | — |
| LMArena Russian | 1521 | — |
| LMArena Spanish | 1516 | — |

## Instruction Following

- Claude Fable 5.1: 79.2 (#6)
- Mercury 2.5: —

| Benchmark | Claude Fable 5.1 | Mercury 2.5 |
|---|---|---|
| LMArena Instruction Following | 1517 | — |

## Long Context

- Claude Fable 5.1: 46.7 (#20)
- Mercury 2.5: —

| Benchmark | Claude Fable 5.1 | Mercury 2.5 |
|---|---|---|
| LMArena Longer Query | 1522 | — |

## Writing & Preference

- Claude Fable 5.1: 79.2 (#2)
- Mercury 2.5: —

| Benchmark | Claude Fable 5.1 | Mercury 2.5 |
|---|---|---|
| LMArena Text | 1510 | — |
| LMArena Creative Writing | 1507 | — |
| EQ-Bench Creative Writing | 2162 | — |
| LMArena Multi-Turn | 1492 | — |

## FAQ

### Is Claude Fable 5.1 better than Mercury 2.5?

Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 33.5 on the Noometry Index. Mercury 2.5 costs 296× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.

### Which is cheaper, Claude Fable 5.1 or Mercury 2.5?

Mercury 2.5 is cheaper. It lists at $0.04 per million input tokens and $0.15 per million output tokens; Claude Fable 5.1 lists at $10 and $50.

### Is Claude Fable 5.1 or Mercury 2.5 better for coding?

Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 39.5 in the Noometry coding category.

### Which has the bigger context window?

Claude Fable 5.1 does, with 1M tokens against 260K.

### How many benchmarks do Claude Fable 5.1 and Mercury 2.5 share?

4 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and Mercury 2.5 has 4.