Anthropic·released 2026-10-071 source
Claude Haiku 5.5 benchmark scores: 14 benchmarks tracked. 0% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 14 benchmarks·best result 98.89 on OTIS Mock AIME 2024-2025 (unverified)·0 of 14 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.89accuracy (%) | unverifiedT2 | 2026-10-07 |
| ProofBench | 89accuracy (%) | unverifiedT1 | 2026-10-07https://www.vals.ai/benchmarks/proof_bench |
| GPQA diamond | 86.2accuracy (%) | unverifiedT2 | 2026-10-07 |
| FrontierMath-Tiers-1-3-v2-Private | 75.09accuracy (%) | unverifiedT2 | 2026-10-07 |
| APEX-Agents | 56.1accuracy (%) | unverifiedT2 | 2026-10-07 |
| Chess Puzzles | 52.65accuracy (%) | unverifiedT2 | 2026-10-07 |
| FrontierCode | 46.36accuracy (%) | unverifiedT1 | 2026-10-07https://cognition.com/frontiercode |
| FrontierMath-Tier-4-v2-Private | 46.34accuracy (%) | unverifiedT2 | 2026-10-07 |
| EBR-bench | 43.81accuracy (%) | unverifiedT2 | 2026-10-07 |
| FrontierSWE | 43.77accuracy (%) | unverifiedT1 | 2026-10-07https://www.frontierswe.com/ |
| HLE | 26.6accuracy (%) | unverifiedT2 | 2026-10-07 |
| Furniture Assembly | 25accuracy (%) | unverifiedT2 | 2026-10-07 |
| SimpleQA Verified | 23.8accuracy (%) | unverifiedT2 | 2026-10-07 |
| Mystery Game Puzzles | 22.89accuracy (%) | unverifiedT2 | 2026-10-07 |
Claims drawn from cited facts, not live model generation.
This model was developed by Anthropic and released in 2026.
2 cited facts
It is scored on 14 tracked benchmarks but holds no current top score. Its record is unverified, meaning outside evaluation has neither confirmed nor disputed the reported results.
3 cited facts
On average it trails the benchmark leader by 27.92 points under the disclosed harness, a wide gap that reads as well behind the leaders rather than at the frontier. It holds the top score on 0 benchmarks, meaning there is no category leadership yet.
2 cited facts
1 facts cross-checked across data sources: 1 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks
Claude Haiku 5.5 is an AI model developed by Anthropic, released 2026-10-07. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Claude Haiku 5.5 has recorded scores on 14 benchmarks, each shown with its evidence status.
Claude Haiku 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 Haiku 5.5 has 14 tracked claims: 14 unverified.