# Claude Fable 5 vs Gemini 2.5 Pro

> Claude Fable 5 is the stronger model overall, scoring 66.3 to 44.9 on the Noometry Index. Gemini 2.5 Pro costs 5.8× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-fable-5-vs-gemini-2-5-pro
- Last updated: 2026-10-10
- Shared benchmarks: 42

## Summary

- They share 42 benchmarks with published results for both. Claude Fable 5 scores higher in 9 categories and Gemini 2.5 Pro in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Fable 5 leads 88.4 to 31.9.
- The biggest single-benchmark swing is FrontierMath Tier 4: 90.2% for Claude Fable 5 and 0% for Gemini 2.5 Pro.
- Gemini 2.5 Pro is cheaper at $1.25 / $10 per million input/output tokens, against $10 / $50 for Claude Fable 5.
- Gemini 2.5 Pro accepts more context: 1.05M tokens versus 1M.

## Snapshot

| | Claude Fable 5 | Gemini 2.5 Pro |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 66.3 | 44.9 |
| Rank | 5 | 67 |
| Context | 1M | 1.05M |
| Input $/M | $10 | $1.25 |
| Output $/M | $50 | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Fable 5: 67.0 (#4)
- Gemini 2.5 Pro: 42.8 (#86)

| Benchmark | Claude Fable 5 | Gemini 2.5 Pro |
|---|---|---|
| LMArena WebDev | 1626 | 1227 |
| SciCode | 61% | 42.8% |
| WeirdML | 91.9% | 54% |
| LMArena Coding | 1519 | 1452 |
| ALE-Bench | 2,041 | 785.52 |
| SWE-bench Verified | — | 57.6% |
| DeepSWE | 69.9% | — |
| FrontierCode | 53.5% | — |
| SWE-bench Verified (bash only) | — | 53.6% |
| Aider Polyglot | — | 83.1% |
| FrontierSWE | 47% | — |
| GSO | — | 3.9% |
| LiveBench Coding | — | 85.9% |
| MirrorCode | 63.9% | — |
| CadEval | — | 64% |
| AlgoTune | — | 1.51 |

## Agentic & Tool Use

- Claude Fable 5: 54.1 (#2)
- Gemini 2.5 Pro: 29.1 (#81)

| Benchmark | Claude Fable 5 | Gemini 2.5 Pro |
|---|---|---|
| Remote Labor Index | 16.1% | 0.8% |
| τ²-bench Banking | 39.7% | 13.7% |
| LMArena Search | 1230 | 1142 |
| Vending-Bench 2 | 5,680 | 573.64 |
| Terminal-Bench | — | 32.6% |
| APEX-Agents | 63.6% | — |
| GDPval | — | 23.3% |
| TheAgentCompany | — | 30.3% |
| DeepResearch Bench | — | 42.8% |
| PostTrainBench | 41.8% | — |
| BALROG | — | 43.3% |
| GBAEval | 74.5% | — |
| GDP.pdf | 30% | — |
| METR Time Horizons | — | 55.4% |

## Reasoning

- Claude Fable 5: 76.8 (#4)
- Gemini 2.5 Pro: 28.8 (#85)

| Benchmark | Claude Fable 5 | Gemini 2.5 Pro |
|---|---|---|
| ARC-AGI-2 | 89.2% | 4.9% |
| SimpleBench | 81.9% | 62.4% |
| Kagi LLM Benchmark | 91.4% | 70.3% |
| ARC-AGI-1 | 98.5% | 41% |
| CritPt | 28.6% | 2% |
| Chess Puzzles | 41% | 20% |
| EnigmaEval | 39.3% | 5.6% |
| LMArena Hard Prompts | 1508 | 1455 |
| DTBench | 98.4% | 82.4% |
| LMCA | 61.1% | 34.8% |
| Epoch Capabilities Index | 163.6 | 145.32 |
| NYT Connections (extended) | 92.7% | — |
| EBR-Bench | 39.5% | — |
| LiveBench Reasoning | — | 89.8% |
| Mystery Game Puzzles | 52% | — |
| LiveBench Data Analysis | — | 79.9% |
| Surface Evolver Bench | 95% | — |
| Bench to the Future 3 | 0.13 | — |
| ForecastBench | — | 61.3 |
| LiveBench | — | 82.3% |

## Math

- Claude Fable 5: 88.4 (#5)
- Gemini 2.5 Pro: 31.9 (#191)

| Benchmark | Claude Fable 5 | Gemini 2.5 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 87% | 24.6% |
| FrontierMath Tier 4 | 90.2% | 0% |
| OTIS Mock AIME 2024-2025 | 100% | 84.7% |
| LMArena Math | 1519 | 1450 |
| ProofBench | 95% | — |
| Omni-MATH | — | 41.6% |
| LiveBench Math | — | 90.2% |
| MATH Level 5 | — | 95.9% |
| FrontierMath (Feb 2025 set) | — | 14.1% |
| FrontierMath Erdős | 0% | — |
| FrontierMath Tier 4 (v1) | — | 4.2% |

## Knowledge

- Claude Fable 5: 62.3 (#22)
- Gemini 2.5 Pro: 55.8 (#41)

| Benchmark | Claude Fable 5 | Gemini 2.5 Pro |
|---|---|---|
| GPQA Diamond | 85.9% | 85.3% |
| LMArena Expert | 1534 | 1452 |
| Humanity's Last Exam | — | 21.6% |
| SimpleQA Verified | 70.7% | — |
| MMLU-Pro | — | 86.3% |
| Confabulations | — | 10.6% |
| Vectara Hallucination Rate | — | 7% |
| GPQA (HELM) | — | 74.9% |

## Multimodal

- Claude Fable 5: 45.6 (#14)
- Gemini 2.5 Pro: 44.5 (#16)

| Benchmark | Claude Fable 5 | Gemini 2.5 Pro |
|---|---|---|
| LMArena Vision | 1326 | 1263 |
| LMArena Document | 1496 | 1421 |
| GeoBench | — | 86% |
| VPCT | — | 48% |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 35.8% | — |
| SpatialViz-Bench | — | 44.7% |

## Multilingual

- Claude Fable 5: 57.6 (#8)
- Gemini 2.5 Pro: 55.5 (#30)

| Benchmark | Claude Fable 5 | Gemini 2.5 Pro |
|---|---|---|
| LMArena Non-English | 1483 | 1452 |
| LMArena Chinese | 1546 | 1507 |
| LMArena French | 1509 | 1473 |
| LMArena German | 1486 | 1487 |
| LMArena Japanese | 1507 | 1462 |
| LMArena Korean | 1493 | 1435 |
| LMArena Russian | 1507 | 1460 |
| LMArena Spanish | 1503 | 1473 |

## Instruction Following

- Claude Fable 5: 78.8 (#7)
- Gemini 2.5 Pro: 75.2 (#71)

| Benchmark | Claude Fable 5 | Gemini 2.5 Pro |
|---|---|---|
| LMArena Instruction Following | 1503 | 1436 |
| LiveBench Instruction Following | — | 80.6% |
| IFEval | — | 84% |

## Long Context

- Claude Fable 5: 46.3 (#22)
- Gemini 2.5 Pro: 59.7 (#5)

| Benchmark | Claude Fable 5 | Gemini 2.5 Pro |
|---|---|---|
| LMArena Longer Query | 1510 | 1449 |
| Fiction.LiveBench | — | 91.7% |

## Writing & Preference

- Claude Fable 5: 76.1 (#5)
- Gemini 2.5 Pro: 63.9 (#60)

| Benchmark | Claude Fable 5 | Gemini 2.5 Pro |
|---|---|---|
| LMArena Text | 1491 | 1458 |
| LMArena Creative Writing | 1494 | 1453 |
| EQ-Bench Creative Writing | 1943 | 1421 |
| LMArena Multi-Turn | 1505 | 1453 |
| Short-Story Creative Writing | — | 83.8% |
| WildBench | — | 85.7% |
| EQ-Bench 4 | 1340 | — |
| LiveBench Language | — | 67.8% |

## FAQ

### Is Claude Fable 5 better than Gemini 2.5 Pro?

Claude Fable 5 is the stronger model overall, scoring 66.3 to 44.9 on the Noometry Index. Gemini 2.5 Pro costs 5.8× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

### Which is cheaper, Claude Fable 5 or Gemini 2.5 Pro?

Gemini 2.5 Pro is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; Claude Fable 5 lists at $10 and $50.

### Is Claude Fable 5 or Gemini 2.5 Pro better for coding?

Claude Fable 5 scores higher on coding benchmarks: 67.0 versus 42.8 in the Noometry coding category.

### Which has the bigger context window?

Gemini 2.5 Pro does, with 1.05M tokens against 1M.

### How many benchmarks do Claude Fable 5 and Gemini 2.5 Pro share?

42 benchmarks have published results for both models. Claude Fable 5 has 61 scored results on Noometry and Gemini 2.5 Pro has 78.