Claude Fable 5 vs Gemini 3.8 Flash
Claude Fable 5 leads Gemini 3.8 Flash by 7.9 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5 wins 17 and Gemini 3.8 Flash wins 5 of 24 shared benchmarks. Gemini 3.8 Flash is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | Claude Fable 5 | Gemini 3.8 Flash |
|---|---|---|
| Agentic coding | 74 | 63 |
| Long-horizon autonomy | 69 | 64 |
| Knowledge-work agents | 52 | 47 |
| Computer use | 55 | 44 |
| Security & context learning | 59 | 53 |
Shared benchmarks
| Benchmark | Claude Fable 5 | Gemini 3.8 Flash |
|---|---|---|
| APEX-Agentsindex | 63.6% | 64.3% |
| DeepSWEindex | 69.9% | 73.8% |
| Vending-Bench 2index | $5,680 | $5,094 |
| FrontierSWEindex | 47.0% | 19.6% |
| Remote Labor Indexindex | 16.1% | 5.8% |
| ARC-AGI | 98.5% | 98.5% |
| ARC-AGI-2 | 89.2% | 89.2% |
| Chess Puzzles | 47.0% | 58.0% |
| CritPt | 28.6% | 18.3% |
| DTBench | 98.4% | 95.7% |
| FrontierCode | 53.5% | 41.2% |
| FrontierMath Tier 4 | 90.2% | 22.0% |
| FrontierMath Tiers 1-3 | 87.0% | 68.4% |
| GeoBench | 89.0% | 86.0% |
| GPQA Diamond | 93.9% | 95.4% |
| LMCA | 61.2% | 52.9% |
| MirrorCode | 70.0% | 38.9% |
| OTIS Mock AIME | 100.0% | 98.9% |
| ProofBench | 95.0% | 48.0% |
| SciCode | 61.0% | 56.6% |
| SimpleBench | 81.9% | 82.4% |
| SimpleQA Verified | 70.7% | 69.7% |
| WebDev Arena | 1628 | 1568 |
| WeirdML v3 | 15.6% | 7.4% |
Specs and price
| Claude Fable 5 | Gemini 3.8 Flash | |
|---|---|---|
| Agent Index | 64.1 (#12) | 56.2 (#21) |
| Agent $/M | $4.62 | $0.35 |
| Input / output $/M | $10.00 / $50.00 | $0.75 / $3.75 |
| Context | 1M | 1M |
| Released | Jun 9, 2026 | Sep 2, 2026 |
| Weights | Closed | Closed |
| API hosts | 4 | 6 |
Don’t pick one. Route.
Shogo can run Claude Fable 5 and Gemini 3.8 Flash side by side and send each step of an agent to the one that’s cheaper for it.
Try both in Shogo