# Claude Fable 5.1 vs Gemini 3 Pro

> Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 54.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-fable-5-1-vs-gemini-3-pro
- Last updated: 2026-10-10
- Shared benchmarks: 33

## Summary

- They share 33 benchmarks with published results for both. Claude Fable 5.1 scores higher in 9 categories and Gemini 3 Pro in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Fable 5.1 leads 89.5 to 48.8.
- The biggest single-benchmark swing is ProofBench: 100% for Claude Fable 5.1 and 20% for Gemini 3 Pro.

## Snapshot

| | Claude Fable 5.1 | Gemini 3 Pro |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 68.5 | 54.7 |
| Rank | 2 | 23 |
| Context | 1M | — |
| Input $/M | $10 | — |
| Output $/M | $50 | — |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Fable 5.1: 70.5 (#2)
- Gemini 3 Pro: 52.1 (#33)

| Benchmark | Claude Fable 5.1 | Gemini 3 Pro |
|---|---|---|
| LMArena WebDev | 1753 | 1439 |
| WeirdML | 92.9% | 69.9% |
| LMArena Coding | 1523 | 1482 |
| ALE-Bench | 2,143 | 1,177 |
| SWE-bench Verified | — | 72.9% |
| FrontierCode | 50.9% | — |
| SWE-bench Verified (bash only) | — | 74.2% |
| CursorBench | 51.8% | — |
| SWE-bench Multilingual | — | 68.7% |
| FrontierSWE | 56.3% | — |
| SciCode | 63.1% | — |
| GSO | — | 18.6% |
| MirrorCode | 73.3% | — |
| AlgoTune | — | 1.83 |

## Agentic & Tool Use

- Claude Fable 5.1: 50.8 (#5)
- Gemini 3 Pro: 40.5 (#21)

| Benchmark | Claude Fable 5.1 | Gemini 3 Pro |
|---|---|---|
| Remote Labor Index | 17.9% | 1.3% |
| Vending-Bench 2 | 5,422 | 5,478 |
| Terminal-Bench | — | 69.4% |
| APEX-Agents | 68.6% | — |
| Berkeley Function Calling Leaderboard | — | 72.5% |
| GDPval | — | 40.3% |
| τ²-bench Airline | — | 80.5% |
| τ²-bench Banking | — | 18% |
| τ²-bench Retail | — | 75.9% |
| τ²-bench Telecom | — | 91% |
| DeepResearch Bench | — | 46.3% |
| BALROG | — | 58.1% |
| GDP.pdf | 29.6% | — |
| LMArena Search | — | 1207 |
| METR Time Horizons | — | 71% |

## Reasoning

- Claude Fable 5.1: 76.7 (#5)
- Gemini 3 Pro: 52.5 (#28)

| Benchmark | Claude Fable 5.1 | Gemini 3 Pro |
|---|---|---|
| ARC-AGI-2 | 90% | 31.1% |
| NYT Connections (extended) | 90% | 94.4% |
| ARC-AGI-1 | 97.5% | 75% |
| CritPt | 31.1% | 6.9% |
| Chess Puzzles | 47% | 31% |
| LMArena Hard Prompts | 1526 | 1481 |
| Epoch Capabilities Index | 165 | 152.96 |
| SimpleBench | — | 76.4% |
| Kagi LLM Benchmark | — | 80.1% |
| EnigmaEval | — | 18.2% |
| EBR-Bench | 57.1% | — |
| Mystery Game Puzzles | 58% | — |
| DTBench | 97.6% | — |
| LMCA | 65.5% | — |
| ForecastBench | — | 61.2 |

## Math

- Claude Fable 5.1: 89.5 (#3)
- Gemini 3 Pro: 48.8 (#50)

| Benchmark | Claude Fable 5.1 | Gemini 3 Pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 91.4% |
| ProofBench | 100% | 20% |
| LMArena Math | 1519 | 1475 |
| FrontierMath (Tiers 1-3) | 90.2% | — |
| FrontierMath Tier 4 | 87.8% | — |
| MathArena Final-Answer Competitions | — | 67% |
| Omni-MATH | — | 55.5% |
| FrontierMath (Feb 2025 set) | — | 37.6% |
| FrontierMath Erdős | 0% | — |
| FrontierMath Tier 4 (v1) | — | 18.8% |

## Knowledge

- Claude Fable 5.1: 69.3 (#5)
- Gemini 3 Pro: 64.3 (#15)

| Benchmark | Claude Fable 5.1 | Gemini 3 Pro |
|---|---|---|
| Humanity's Last Exam | 46.5% | 37.5% |
| LMArena Expert | 1528 | 1475 |
| GPQA Diamond | — | 92.6% |
| SimpleQA Verified | 70.8% | — |
| MMLU-Pro | — | 90.3% |
| Vectara Hallucination Rate | — | 13.6% |
| GPQA (HELM) | — | 80.3% |

## Multimodal

- Claude Fable 5.1: 54.1 (#4)
- Gemini 3 Pro: 56.9 (#1)

| Benchmark | Claude Fable 5.1 | Gemini 3 Pro |
|---|---|---|
| LMArena Vision | 1319 | 1305 |
| LMArena Document | 1513 | 1434 |
| GeoBench | — | 84% |
| VPCT | — | 91% |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |

## Multilingual

- Claude Fable 5.1: 59.5 (#2)
- Gemini 3 Pro: 57.1 (#14)

| Benchmark | Claude Fable 5.1 | Gemini 3 Pro |
|---|---|---|
| LMArena Non-English | 1509 | 1474 |
| LMArena Chinese | 1589 | 1522 |
| LMArena French | 1532 | 1492 |
| LMArena German | 1495 | 1517 |
| LMArena Japanese | 1565 | 1513 |
| LMArena Russian | 1525 | 1493 |
| LMArena Spanish | 1503 | 1468 |
| LMArena Korean | — | 1449 |

## Instruction Following

- Claude Fable 5.1: 79.3 (#6)
- Gemini 3 Pro: 76.4 (#42)

| Benchmark | Claude Fable 5.1 | Gemini 3 Pro |
|---|---|---|
| LMArena Instruction Following | 1515 | 1458 |
| IFEval | — | 87.7% |

## Long Context

- Claude Fable 5.1: 46.8 (#19)
- Gemini 3 Pro: 44.0 (#75)

| Benchmark | Claude Fable 5.1 | Gemini 3 Pro |
|---|---|---|
| LMArena Longer Query | 1524 | 1472 |
| CL-bench | — | 15.8% |

## Writing & Preference

- Claude Fable 5.1: 79.3 (#1)
- Gemini 3 Pro: 66.6 (#34)

| Benchmark | Claude Fable 5.1 | Gemini 3 Pro |
|---|---|---|
| LMArena Text | 1511 | 1479 |
| LMArena Creative Writing | 1507 | 1482 |
| EQ-Bench Creative Writing | 2162 | 1525 |
| LMArena Multi-Turn | 1492 | 1484 |
| WildBench | — | 85.9% |

## FAQ

### Is Claude Fable 5.1 better than Gemini 3 Pro?

Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 54.7 on the Noometry Index.

### Is Claude Fable 5.1 or Gemini 3 Pro better for coding?

Claude Fable 5.1 scores higher on coding benchmarks: 70.5 versus 52.1 in the Noometry coding category.

### How many benchmarks do Claude Fable 5.1 and Gemini 3 Pro share?

33 benchmarks have published results for both models. Claude Fable 5.1 has 50 scored results on Noometry and Gemini 3 Pro has 67.