Claude Sonnet 5.5 (max): benchmark scores, price and ranking
Claude Sonnet 5.5 (max) from Anthropic ranks #4 of 741 LLMs on the LLMs Tiger aggregate benchmark score (60.8), based on 13 benchmark results captured up to 2026-10-05.
- Organisation
- Anthropic
- Type
- Frontier model
- Open weights
- No
- Released
- 2026-09-28 (source: curated)
- Cheapest API price
- $2.00 in / $10.00 out per million tokens (via anthropic, observed 2026-10-05T21:47Z)
- Aggregate rank
- #4 of 741 (score 60.8)
Relative to other models, Claude Sonnet 5.5 (max) is strongest on GPQA Diamond (#2 of 274) and weakest on SimpleQA Verified (#26 of 66).
Claude Sonnet 5.5 (max) benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| GPQA Diamond | 95.6% | #2 of 274 | Epoch AI Benchmarking Hub | 2026-10-05 |
| OTIS Mock AIME | 100.0% | #3 of 188 | Epoch AI Benchmarking Hub | 2026-10-05 |
| SciCode | 61.0% | #4 of 100 | Epoch AI Benchmarking Hub | 2026-10-05 |
| CritPt | 31.4% | #5 of 111 | Epoch AI Benchmarking Hub | 2026-10-05 |
| ProofBench | 100.0% | #3 of 43 | Epoch AI Benchmarking Hub | 2026-10-05 |
| Mystery Games | 65.0% | #4 of 57 | Epoch AI Benchmarking Hub | 2026-10-05 |
| APEX-Agents | 75.5% | #1 of 14 | Epoch AI Benchmarking Hub | 2026-10-05 |
| FrontierMath T1-3 | 88.8% | #7 of 69 | Epoch AI Benchmarking Hub | 2026-10-05 |
| FrontierMath T4 | 80.5% | #8 of 52 | Epoch AI Benchmarking Hub | 2026-10-05 |
| CursorBench | 55.5% | #2 of 13 | Epoch AI Benchmarking Hub | 2026-10-05 |
| Furniture Assembly | 75.0% | #4 of 25 | Epoch AI Benchmarking Hub | 2026-10-05 |
| FrontierSWE | 61.9% | #3 of 16 | Epoch AI Benchmarking Hub | 2026-10-05 |
| SimpleQA Verified | 46.5% | #26 of 66 | Epoch AI Benchmarking Hub | 2026-10-05 |
Claude Sonnet 5.5 (max) is also listed at 5 other reasoning-effort settings; this page shows the highest-effort row, which is the one the leaderboard keeps by default.
Models ranked nearby
- #1 Claude Opus 5.5 (max) (64.2)
- #2 GPT-6 Astra (max) (63.8)
- #3 Claude Fable 5.1 (max) (61.9)
- #5 GPT-6.1 Sol (max) (60.6)
- #6 Claude Opus 5 (max) (60.1)
- #7 GPT-5.6 Sol (max) (60.1)
Compare it on the live leaderboard → · How the aggregate score works