Claude Fable 5 vs Gemini 4 Carbon
Gemini 4 Carbon leads Claude Fable 5 by 9.5 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5 wins 0 and Gemini 4 Carbon wins 13 of 15 shared benchmarks. Gemini 4 Carbon is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | Claude Fable 5 | Gemini 4 Carbon |
|---|---|---|
| Agentic coding | 74 | 82 |
| Long-horizon autonomy | 69 | 80 |
| Knowledge-work agents | 52 | 63 |
| Computer use | 55 | 68 |
| Security & context learning | 59 | 63 |
Shared benchmarks
| Benchmark | Claude Fable 5 | Gemini 4 Carbon |
|---|---|---|
| APEX-Agentsindex | 63.6% | 84.2% |
| Vending-Bench 2index | $5,680 | $16,484 |
| FrontierSWEindex | 47.0% | 61.2% |
| PostTrainBenchindex | 37.3% | 41.0% |
| ARC-AGI | 98.5% | 98.5% |
| ARC-AGI-2 | 89.2% | 94.2% |
| Chess Puzzles | 47.0% | 78.0% |
| CritPt | 28.6% | 36.0% |
| FrontierMath Tier 4 | 90.2% | 95.1% |
| FrontierMath Tiers 1-3 | 87.0% | 90.5% |
| GPQA Diamond | 93.9% | 96.5% |
| OTIS Mock AIME | 100.0% | 100.0% |
| SciCode | 61.0% | 64.2% |
| SimpleBench | 81.9% | 92.6% |
| SimpleQA Verified | 70.7% | 77.7% |
Specs and price
| Claude Fable 5 | Gemini 4 Carbon | |
|---|---|---|
| Agent Index | 64.1 (#12) | 73.6 (#2) |
| Agent $/M | $4.62 | $0.84 |
| Input / output $/M | $10.00 / $50.00 | $2.00 / $10.00 |
| Context | 1M | 1M |
| Released | Jun 9, 2026 | Nov 10, 2026 |
| Weights | Closed | Closed |
| API hosts | 4 | 5 |
Don’t pick one. Route.
Shogo can run Claude Fable 5 and Gemini 4 Carbon side by side and send each step of an agent to the one that’s cheaper for it.
Try both in Shogo