Anthropic·released 2026-09-281 source
Claude Sonnet 5.5 benchmark scores: 14 benchmarks tracked, leading 2. 0% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 2 of 14 benchmarks·best result 100 on OTIS Mock AIME 2024-2025 (unverified)·0 of 14 independently reproduced
Head-to-headClaude Sonnet 5.5 vs GPT-5.5Leads on: OTIS Mock AIME 2024-2025, ProofBench
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 100accuracy (%) | unverifiedT2 | 2026-09-28 |
| ProofBench | 100accuracy (%) | unverifiedT1 | 2026-09-28https://www.vals.ai/benchmarks/proof_bench |
| GPQA diamond | 94.11accuracy (%) | unverifiedT2 | 2026-09-28 |
| FrontierMath-Tiers-1-3-v2-Private | 88.77accuracy (%) | unverifiedT2 | 2026-09-28 |
| FrontierMath-Tier-4-v2-Private | 80.49accuracy (%) | unverifiedT2 | 2026-09-28 |
| APEX-Agents | 75.5accuracy (%) | unverifiedT2 | 2026-09-28 |
| Furniture Assembly | 64.29accuracy (%) | unverifiedT2 | 2026-09-28 |
| FrontierSWE | 61.89accuracy (%) | unverifiedT1 | 2026-09-28https://www.frontierswe.com/ |
| Mystery Game Puzzles | 61.45accuracy (%) | unverifiedT2 | 2026-09-28 |
| Chess Puzzles | 56.86accuracy (%) | unverifiedT2 | 2026-09-28 |
| FrontierCode | 52.09accuracy (%) | unverifiedT1 | 2026-09-28https://cognition.com/frontiercode |
| SimpleQA Verified | 46.5accuracy (%) | unverifiedT2 | 2026-09-28 |
| HLE | 43.4accuracy (%) | unverifiedT2 | 2026-09-28 |
| SpireClimb | 1.33accuracy (%) | unverifiedT2 | 2026-09-28 |
Claims drawn from cited facts, not live model generation.
This model was developed by Anthropic and released in 2026.
2 cited facts
This model has scores on 14 tracked benchmarks and currently leads 2 of them. The record’s evidence status is unverified.
3 cited facts
Its mean gap to the best recorded score across its tracked benchmarks is 10.72 points.
1 cited fact
1 facts cross-checked across data sources: 1 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks
Claude Sonnet 5.5 is an AI model developed by Anthropic, released 2026-09-28. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Claude Sonnet 5.5 has recorded scores on 14 benchmarks, each shown with its evidence status.
Claude Sonnet 5.5 has recorded scores on 14 benchmarks — GPQA diamond, OTIS Mock AIME 2024-2025, SimpleQA Verified, Chess Puzzles, HLE, FrontierMath-Tiers-1-3-v2-Private, and 8 more. The full table above shows each score with its evidence status.
0 of 14 recorded scores (0%) are independently reproduced rather than self-reported by the lab.
Claude Sonnet 5.5 has 14 tracked claims: 14 unverified.