# Claude Fable 5.1 vs Gemma 3 4B

> Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 28.1 on the Noometry Index. Gemma 3 4B costs 400× 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-gemma-3-4b
- Last updated: 2026-10-12
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Claude Fable 5.1 scores higher in 9 categories and Gemma 3 4B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Fable 5.1 leads 89.6 to 16.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 100% for Claude Fable 5.1 and 7.5% for Gemma 3 4B.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
- Claude Fable 5.1 accepts more context: 1M tokens versus 131K.
- Gemma 3 4B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Fable 5.1 | Gemma 3 4B |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 69.0 | 28.1 |
| Rank | 2 | 326 |
| Context | 1M | 131K |
| Input $/M | $10 | $0.04 |
| Output $/M | $50 | $0.08 |
| Weights | Proprietary | Open |

## Coding

- Claude Fable 5.1: 74.7 (#1)
- Gemma 3 4B: 35.9 (#215)

| Benchmark | Claude Fable 5.1 | Gemma 3 4B |
|---|---|---|
| LMArena Coding | 1528 | 1230 |
| FrontierCode | 50.9% | — |
| CursorBench | 51.8% | — |
| LMArena WebDev | 1744 | — |
| FrontierSWE | 56.3% | — |
| SciCode | 63.1% | — |
| GSO | 88.2% | — |
| WeirdML | 92.9% | — |
| MirrorCode | 73.3% | — |
| ALE-Bench | 2,143 | — |

## Agentic & Tool Use

- Claude Fable 5.1: 50.7 (#5)
- Gemma 3 4B: 20.9 (#142)

| Benchmark | Claude Fable 5.1 | Gemma 3 4B |
|---|---|---|
| APEX-Agents | 68.6% | — |
| Berkeley Function Calling Leaderboard | — | 19.6% |
| Remote Labor Index | 17.9% | — |
| GDP.pdf | 29.6% | — |
| Vending-Bench 2 | 5,422 | — |

## Reasoning

- Claude Fable 5.1: 76.7 (#7)
- Gemma 3 4B: 13.2 (#335)

| Benchmark | Claude Fable 5.1 | Gemma 3 4B |
|---|---|---|
| Chess Puzzles | 47% | 0% |
| LMArena Hard Prompts | 1526 | 1253 |
| DTBench | 97.6% | 50.9% |
| LMCA | 65.5% | 2.8% |
| Epoch Capabilities Index | 164.7 | 116.02 |
| ARC-AGI-2 | 90% | — |
| Kagi LLM Benchmark | — | 25.2% |
| NYT Connections (extended) | 90% | — |
| ARC-AGI-1 | 97.5% | — |
| CritPt | 31.1% | — |
| EBR-Bench | 57.1% | — |
| Mystery Game Puzzles | 58% | — |

## Math

- Claude Fable 5.1: 89.6 (#4)
- Gemma 3 4B: 16.8 (#292)

| Benchmark | Claude Fable 5.1 | Gemma 3 4B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 7.5% |
| LMArena Math | 1525 | 1239 |
| FrontierMath (Tiers 1-3) | 90.2% | — |
| FrontierMath Tier 4 | 87.8% | — |
| ProofBench | 100% | — |
| FrontierMath Erdős | 0% | — |

## Knowledge

- Claude Fable 5.1: 69.6 (#6)
- Gemma 3 4B: 11.8 (#299)

| Benchmark | Claude Fable 5.1 | Gemma 3 4B |
|---|---|---|
| LMArena Expert | 1535 | 1223 |
| GPQA Diamond | — | 23.2% |
| Humanity's Last Exam | 46.5% | — |
| SimpleQA Verified | 70.8% | — |
| Vectara Hallucination Rate | — | 6.4% |

## Multimodal

- Claude Fable 5.1: 53.9 (#4)
- Gemma 3 4B: —

| Benchmark | Claude Fable 5.1 | Gemma 3 4B |
|---|---|---|
| LMArena Vision | 1318 | — |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
| LMArena Document | 1513 | — |

## Multilingual

- Claude Fable 5.1: 59.1 (#3)
- Gemma 3 4B: 42.5 (#194)

| Benchmark | Claude Fable 5.1 | Gemma 3 4B |
|---|---|---|
| LMArena Non-English | 1507 | 1273 |
| LMArena German | 1500 | 1281 |
| LMArena Russian | 1521 | 1294 |
| LMArena Chinese | 1586 | — |
| LMArena French | 1525 | — |
| LMArena Japanese | 1543 | — |
| LMArena Korean | 1534 | — |
| LMArena Spanish | 1516 | — |

## Instruction Following

- Claude Fable 5.1: 79.2 (#6)
- Gemma 3 4B: 65.2 (#225)

| Benchmark | Claude Fable 5.1 | Gemma 3 4B |
|---|---|---|
| LMArena Instruction Following | 1517 | 1239 |

## Long Context

- Claude Fable 5.1: 46.7 (#20)
- Gemma 3 4B: 38.7 (#194)

| Benchmark | Claude Fable 5.1 | Gemma 3 4B |
|---|---|---|
| LMArena Longer Query | 1522 | 1273 |

## Writing & Preference

- Claude Fable 5.1: 79.2 (#2)
- Gemma 3 4B: 42.0 (#239)

| Benchmark | Claude Fable 5.1 | Gemma 3 4B |
|---|---|---|
| LMArena Text | 1510 | 1291 |
| LMArena Creative Writing | 1507 | 1271 |
| EQ-Bench Creative Writing | 2162 | 1068 |
| LMArena Multi-Turn | 1492 | 1255 |

## FAQ

### Is Claude Fable 5.1 better than Gemma 3 4B?

Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 28.1 on the Noometry Index. Gemma 3 4B costs 400× 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 Gemma 3 4B?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Claude Fable 5.1 lists at $10 and $50.

### Is Claude Fable 5.1 or Gemma 3 4B better for coding?

Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 35.9 in the Noometry coding category.

### Which has the bigger context window?

Claude Fable 5.1 does, with 1M tokens against 131K.

### How many benchmarks do Claude Fable 5.1 and Gemma 3 4B share?

18 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and Gemma 3 4B has 22.