Claude Fable 5.2 vs GPT-6 Sol
Claude Fable 5.2 leads GPT-6 Sol by 12.8 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5.2 wins 15 and GPT-6 Sol wins 2 of 17 shared benchmarks. GPT-6 Sol is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | Claude Fable 5.2 | GPT-6 Sol |
|---|---|---|
| Agentic coding | 86 | 72 |
| Long-horizon autonomy | 78 | 76 |
| Knowledge-work agents | 67 | 48 |
| Computer use | 77 | 54 |
| Security & context learning | 65 | 59 |
Shared benchmarks
| Benchmark | Claude Fable 5.2 | GPT-6 Sol |
|---|---|---|
| APEX-Agentsindex | 80.1% | 54.3% |
| Vending-Bench 2index | $9,628 | $14,428 |
| ARC-AGI | 98.5% | 95.5% |
| ARC-AGI-2 | 93.8% | 89.6% |
| Chess Puzzles | 79.0% | 56.0% |
| CritPt | 35.7% | 30.9% |
| DTBench | 99.2% | 97.3% |
| FrontierMath Tier 4 | 100.0% | 90.0% |
| FrontierMath Tiers 1-3 | 95.1% | 89.8% |
| GPQA Diamond | 96.0% | 94.3% |
| LMCA | 70.6% | 59.1% |
| OTIS Mock AIME | 99.7% | 100.0% |
| ProofBench | 100.0% | 83.0% |
| SciCode | 67.7% | 57.6% |
| SimpleBench | 94.9% | 73.1% |
| SimpleQA Verified | 94.0% | 60.7% |
| WeirdML v3 | 43.1% | 19.7% |
Specs and price
| Claude Fable 5.2 | GPT-6 Sol | |
|---|---|---|
| Agent Index | 76.4 (#1) | 63.6 (#13) |
| Agent $/M | $3.21 | $0.92 |
| Input / output $/M | $8.00 / $40.00 | $2.00 / $10.00 |
| Context | 1M | 1.1M |
| Released | Nov 9, 2026 | Sep 22, 2026 |
| Weights | Closed | Closed |
| API hosts | 4 | 5 |
Don’t pick one. Route.
Shogo can run Claude Fable 5.2 and GPT-6 Sol side by side and send each step of an agent to the one that’s cheaper for it.
Try both in Shogo