Model comparison
Claude Fable 5.1 vs Gemini 3.8 Flash
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 61.8 on the Noometry Index. Gemini 3.8 Flash costs 13× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.
Last verified . 47 shared benchmarks.
GoogleSummary
- They share 47 benchmarks with published results for both. Claude Fable 5.1 scores higher in 8 categories and Gemini 3.8 Flash in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Fable 5.1 leads 89.6 to 65.3.
- The biggest single-benchmark swing is FrontierMath Tier 4: 87.8% for Claude Fable 5.1 and 22% for Gemini 3.8 Flash.
- Gemini 3.8 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
- Gemini 3.8 Flash accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Fable 5.1 | Gemini 3.8 Flash | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 69.0 | 61.8 |
| Released | 2026-09-01 | 2026-09-02 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 66K |
| Input $ / M tokens | $10 | $0.75 |
| Output $ / M tokens | $50 | $3.75 |
| Results tracked | 52 | 50 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Fable 5.1 leads
Claude Fable 5.1: 74.7 (#1), Gemini 3.8 Flash: 59.2 (#15)
| Benchmark | Claude Fable 5.1 | Gemini 3.8 Flash |
|---|---|---|
| FrontierCode | 50.9% | 41.2% |
| CursorBench | 51.8% | 39.6% |
| LMArena WebDev | 1744 | 1584 |
| FrontierSWE | 56.3% | 19.6% |
| SciCode | 63.1% | 56.6% |
| WeirdML | 92.9% | 84.8% |
| LMArena Coding | 1528 | 1510 |
| ALE-Bench | 2,143 | 1,270 |
| DeepSWE | — | 73.8% |
| GSO | 88.2% | — |
| MirrorCode | 73.3% | — |
Agentic & Tool Use Claude Fable 5.1 leads
Claude Fable 5.1: 50.7 (#5), Gemini 3.8 Flash: 41.8 (#21)
| Benchmark | Claude Fable 5.1 | Gemini 3.8 Flash |
|---|---|---|
| APEX-Agents | 68.6% | 64.3% |
| Remote Labor Index | 17.9% | 5.8% |
| GDP.pdf | 29.6% | 23.4% |
| Vending-Bench 2 | 5,422 | 5,094 |
Reasoning Too close to call
Claude Fable 5.1: 76.7 (#7), Gemini 3.8 Flash: 76.9 (#5)
| Benchmark | Claude Fable 5.1 | Gemini 3.8 Flash |
|---|---|---|
| ARC-AGI-2 | 90% | 89.2% |
| NYT Connections (extended) | 90% | 97.4% |
| ARC-AGI-1 | 97.5% | 98.5% |
| CritPt | 31.1% | 18.3% |
| Chess Puzzles | 47% | 61% |
| LMArena Hard Prompts | 1526 | 1508 |
| Mystery Game Puzzles | 58% | 47% |
| DTBench | 97.6% | 95.7% |
| LMCA | 65.5% | 52.9% |
| Epoch Capabilities Index | 164.7 | 156.71 |
| EBR-Bench | 57.1% | — |
| Surface Evolver Bench | — | 76.9% |
Math Claude Fable 5.1 leads
Claude Fable 5.1: 89.6 (#4), Gemini 3.8 Flash: 65.3 (#28)
| Benchmark | Claude Fable 5.1 | Gemini 3.8 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 90.2% | 68.4% |
| FrontierMath Tier 4 | 87.8% | 22% |
| OTIS Mock AIME 2024-2025 | 100% | 98.9% |
| ProofBench | 100% | 48% |
| LMArena Math | 1525 | 1528 |
| FrontierMath Erdős | 0% | — |
Knowledge Gemini 3.8 Flash leads
Claude Fable 5.1: 69.6 (#6), Gemini 3.8 Flash: 74.8 (#2)
| Benchmark | Claude Fable 5.1 | Gemini 3.8 Flash |
|---|---|---|
| Humanity's Last Exam | 46.5% | 44.5% |
| SimpleQA Verified | 70.8% | 69.7% |
| LMArena Expert | 1535 | 1524 |
| GPQA Diamond | — | 95.4% |
Multimodal Claude Fable 5.1 leads
Claude Fable 5.1: 53.9 (#4), Gemini 3.8 Flash: 40.7 (#45)
| Benchmark | Claude Fable 5.1 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Vision | 1318 | 1314 |
| Blueprint-Bench 2 | 41.9% | 38.6% |
| Furniture Assembly | 70% | 31.7% |
| LMArena Document | 1513 | — |
Multilingual Claude Fable 5.1 leads
Claude Fable 5.1: 59.1 (#3), Gemini 3.8 Flash: 58.0 (#5)
| Benchmark | Claude Fable 5.1 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Non-English | 1507 | 1491 |
| LMArena Chinese | 1586 | 1554 |
| LMArena French | 1525 | 1498 |
| LMArena German | 1500 | 1493 |
| LMArena Japanese | 1543 | 1502 |
| LMArena Korean | 1534 | 1459 |
| LMArena Russian | 1521 | 1515 |
| LMArena Spanish | 1516 | 1485 |
Instruction Following Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#6), Gemini 3.8 Flash: 78.0 (#13)
| Benchmark | Claude Fable 5.1 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Instruction Following | 1517 | 1490 |
Long Context Too close to call
Claude Fable 5.1: 46.7 (#20), Gemini 3.8 Flash: 46.3 (#24)
| Benchmark | Claude Fable 5.1 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Longer Query | 1522 | 1508 |
Writing & Preference Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#2), Gemini 3.8 Flash: 72.2 (#15)
| Benchmark | Claude Fable 5.1 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Text | 1510 | 1499 |
| LMArena Creative Writing | 1507 | 1492 |
| EQ-Bench Creative Writing | 2162 | 1748 |
| LMArena Multi-Turn | 1492 | 1501 |
Frequently asked questions
Is Claude Fable 5.1 better than Gemini 3.8 Flash?
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 61.8 on the Noometry Index. Gemini 3.8 Flash costs 13× 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 Gemini 3.8 Flash?
Gemini 3.8 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Claude Fable 5.1 lists at $10 and $50.
Is Claude Fable 5.1 or Gemini 3.8 Flash better for coding?
Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 59.2 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.8 Flash does, with 1.05M tokens against 1M.
How many benchmarks do Claude Fable 5.1 and Gemini 3.8 Flash share?
47 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and Gemini 3.8 Flash has 50.