# Claude Fable 5 vs Gemini 3.6 Flash

> Claude Fable 5 is the stronger model overall, scoring 66.3 to 54.1 on the Noometry Index. Gemini 3.6 Flash costs 13× 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-3-6-flash
- Last updated: 2026-10-10
- Shared benchmarks: 45

## Summary

- They share 45 benchmarks with published results for both. Claude Fable 5 scores higher in 9 categories and Gemini 3.6 Flash in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Fable 5 leads 88.4 to 57.0.
- The biggest single-benchmark swing is FrontierMath Tier 4: 90.2% for Claude Fable 5 and 22% for Gemini 3.6 Flash.
- Gemini 3.6 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $10 / $50 for Claude Fable 5.
- Gemini 3.6 Flash accepts more context: 1.05M tokens versus 1M.

## Snapshot

| | Claude Fable 5 | Gemini 3.6 Flash |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 66.3 | 54.1 |
| Rank | 5 | 30 |
| Context | 1M | 1.05M |
| Input $/M | $10 | $0.75 |
| Output $/M | $50 | $3.75 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Fable 5: 67.0 (#4)
- Gemini 3.6 Flash: 49.6 (#45)

| Benchmark | Claude Fable 5 | Gemini 3.6 Flash |
|---|---|---|
| DeepSWE | 69.9% | 46.7% |
| FrontierCode | 53.5% | 34.4% |
| LMArena WebDev | 1626 | 1536 |
| SciCode | 61% | 52.7% |
| WeirdML | 91.9% | 56.1% |
| LMArena Coding | 1519 | 1492 |
| ALE-Bench | 2,041 | 715.52 |
| FrontierSWE | 47% | — |
| MirrorCode | 63.9% | — |

## Agentic & Tool Use

- Claude Fable 5: 54.1 (#2)
- Gemini 3.6 Flash: 32.4 (#56)

| Benchmark | Claude Fable 5 | Gemini 3.6 Flash |
|---|---|---|
| APEX-Agents | 63.6% | 46.9% |
| GDP.pdf | 30% | 14% |
| Remote Labor Index | 16.1% | — |
| τ²-bench Banking | 39.7% | — |
| PostTrainBench | 41.8% | — |
| GBAEval | 74.5% | — |
| LMArena Search | 1230 | — |
| Vending-Bench 2 | 5,680 | — |

## Reasoning

- Claude Fable 5: 76.8 (#4)
- Gemini 3.6 Flash: 58.9 (#20)

| Benchmark | Claude Fable 5 | Gemini 3.6 Flash |
|---|---|---|
| ARC-AGI-2 | 89.2% | 60.4% |
| NYT Connections (extended) | 92.7% | 89% |
| ARC-AGI-1 | 98.5% | 91.2% |
| CritPt | 28.6% | 10.6% |
| Chess Puzzles | 41% | 43% |
| LMArena Hard Prompts | 1508 | 1486 |
| Mystery Game Puzzles | 52% | 30% |
| DTBench | 98.4% | 95.5% |
| LMCA | 61.1% | 44.9% |
| Epoch Capabilities Index | 163.6 | 154.36 |
| SimpleBench | 81.9% | — |
| Kagi LLM Benchmark | 91.4% | — |
| EnigmaEval | 39.3% | — |
| EBR-Bench | 39.5% | — |
| Surface Evolver Bench | 95% | — |
| Bench to the Future 3 | 0.13 | — |

## Math

- Claude Fable 5: 88.4 (#5)
- Gemini 3.6 Flash: 57.0 (#33)

| Benchmark | Claude Fable 5 | Gemini 3.6 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 87% | 58.9% |
| FrontierMath Tier 4 | 90.2% | 22% |
| OTIS Mock AIME 2024-2025 | 100% | 94.2% |
| ProofBench | 95% | 36% |
| LMArena Math | 1519 | 1504 |
| MathArena Final-Answer Competitions | — | 70.8% |
| FrontierMath Erdős | 0% | — |

## Knowledge

- Claude Fable 5: 62.3 (#22)
- Gemini 3.6 Flash: 67.8 (#7)

| Benchmark | Claude Fable 5 | Gemini 3.6 Flash |
|---|---|---|
| GPQA Diamond | 85.9% | 94.1% |
| SimpleQA Verified | 70.7% | 66.2% |
| LMArena Expert | 1534 | 1489 |

## Multimodal

- Claude Fable 5: 45.6 (#14)
- Gemini 3.6 Flash: 38.7 (#55)

| Benchmark | Claude Fable 5 | Gemini 3.6 Flash |
|---|---|---|
| LMArena Vision | 1326 | 1297 |
| Blueprint-Bench 2 | 38.6% | 31.2% |
| Furniture Assembly | 35.8% | 23.3% |
| LMArena Document | 1496 | 1456 |

## Multilingual

- Claude Fable 5: 57.6 (#8)
- Gemini 3.6 Flash: 56.8 (#17)

| Benchmark | Claude Fable 5 | Gemini 3.6 Flash |
|---|---|---|
| LMArena Non-English | 1483 | 1470 |
| LMArena Chinese | 1546 | 1530 |
| LMArena French | 1509 | 1501 |
| LMArena German | 1486 | 1478 |
| LMArena Japanese | 1507 | 1477 |
| LMArena Korean | 1493 | 1435 |
| LMArena Russian | 1507 | 1490 |
| LMArena Spanish | 1503 | 1477 |

## Instruction Following

- Claude Fable 5: 78.8 (#7)
- Gemini 3.6 Flash: 77.2 (#27)

| Benchmark | Claude Fable 5 | Gemini 3.6 Flash |
|---|---|---|
| LMArena Instruction Following | 1503 | 1467 |

## Long Context

- Claude Fable 5: 46.3 (#22)
- Gemini 3.6 Flash: 45.1 (#47)

| Benchmark | Claude Fable 5 | Gemini 3.6 Flash |
|---|---|---|
| LMArena Longer Query | 1510 | 1475 |

## Writing & Preference

- Claude Fable 5: 76.1 (#5)
- Gemini 3.6 Flash: 68.3 (#26)

| Benchmark | Claude Fable 5 | Gemini 3.6 Flash |
|---|---|---|
| LMArena Text | 1491 | 1478 |
| LMArena Creative Writing | 1494 | 1464 |
| EQ-Bench Creative Writing | 1943 | 1604 |
| LMArena Multi-Turn | 1505 | 1481 |
| EQ-Bench 4 | 1340 | — |

## FAQ

### Is Claude Fable 5 better than Gemini 3.6 Flash?

Claude Fable 5 is the stronger model overall, scoring 66.3 to 54.1 on the Noometry Index. Gemini 3.6 Flash costs 13× 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 3.6 Flash?

Gemini 3.6 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Claude Fable 5 lists at $10 and $50.

### Is Claude Fable 5 or Gemini 3.6 Flash better for coding?

Claude Fable 5 scores higher on coding benchmarks: 67.0 versus 49.6 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.6 Flash does, with 1.05M tokens against 1M.

### How many benchmarks do Claude Fable 5 and Gemini 3.6 Flash share?

45 benchmarks have published results for both models. Claude Fable 5 has 61 scored results on Noometry and Gemini 3.6 Flash has 46.