Claude Fable 5.2 vs Gemini 4 Carbon
Claude Fable 5.2 leads Gemini 4 Carbon by 2.8 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5.2 wins 8 and Gemini 4 Carbon wins 7 of 16 shared benchmarks. Gemini 4 Carbon is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | Claude Fable 5.2 | Gemini 4 Carbon |
|---|---|---|
| Agentic coding | 86 | 82 |
| Long-horizon autonomy | 78 | 80 |
| Knowledge-work agents | 67 | 63 |
| Computer use | 77 | 68 |
| Security & context learning | 65 | 63 |
Shared benchmarks
| Benchmark | Claude Fable 5.2 | Gemini 4 Carbon |
|---|---|---|
| APEX-Agentsindex | 80.1% | 84.2% |
| Vending-Bench 2index | $9,628 | $16,484 |
| FrontierSWEindex | 69.9% | 61.2% |
| CursorBenchindex | 60.0% | 60.4% |
| PostTrainBenchindex | 44.6% | 41.0% |
| ARC-AGI | 98.5% | 98.5% |
| ARC-AGI-2 | 93.8% | 94.2% |
| Chess Puzzles | 79.0% | 78.0% |
| CritPt | 35.7% | 36.0% |
| FrontierMath Tier 4 | 100.0% | 95.1% |
| FrontierMath Tiers 1-3 | 95.1% | 90.5% |
| GPQA Diamond | 96.0% | 96.5% |
| OTIS Mock AIME | 99.7% | 100.0% |
| SciCode | 67.7% | 64.2% |
| SimpleBench | 94.9% | 92.6% |
| SimpleQA Verified | 94.0% | 77.7% |
Specs and price
| Claude Fable 5.2 | Gemini 4 Carbon | |
|---|---|---|
| Agent Index | 76.4 (#1) | 73.6 (#2) |
| Agent $/M | $3.21 | $0.84 |
| Input / output $/M | $8.00 / $40.00 | $2.00 / $10.00 |
| Context | 1M | 1M |
| Released | Nov 9, 2026 | Nov 10, 2026 |
| Weights | Closed | Closed |
| API hosts | 4 | 5 |
Don’t pick one. Route.
Shogo can run Claude Fable 5.2 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