claude-sonnet-4-20250514_59K: benchmark scores, price and ranking
claude-sonnet-4-20250514_59K from Anthropic ranks #155 of 743 LLMs on the LLMs Tiger aggregate benchmark score (50.9), based on 2 benchmark results captured up to 2026-10-13.
- Organisation
- Anthropic
- Type
- Frontier model
- Open weights
- No
- Released
- 2025-05-14 (source: name)
- Aggregate rank
- #155 of 743 (score 50.9)
Across the 2 benchmarks where at least ten models are scored, claude-sonnet-4-20250514_59K is in the top 10% on 0 and in the top half on 2.
claude-sonnet-4-20250514_59K benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| GPQA Diamond | 79.2% | #109 of 275 | Epoch AI Benchmarking Hub | 2026-10-13 |
| OTIS Mock AIME | 68.9% | #81 of 189 | Epoch AI Benchmarking Hub | 2026-10-13 |
About claude-sonnet-4-20250514_59K
claude-sonnet-4-20250514_59K is a frontier model from Anthropic. It was released on 2025-05-14, according to the model's own name. No API price is listed for it yet. We hold 2 benchmark results for it across 1 area, and none is in the top tenth of its board.
Where claude-sonnet-4-20250514_59K stands
On our aggregate score, claude-sonnet-4-20250514_59K is #155 of 743 ranked models, in the top quarter. Its score is 50.9; the scale is centred on 50, so it sits 0.9 points above the typical model. That beats 79% of the ranked field. Among the 70 ranked Anthropic models it is #26. The next one up is Claude 4 Opus at 51.0. The next one down is claude-3-5-haiku-20241022 at 50.8.
claude-sonnet-4-20250514_59K, benchmark by benchmark
GPQA Diamond puts claude-sonnet-4-20250514_59K at 79.2%, #109 of 275. That beats 60% of the models tested, but 16.6 points short of GPT-6 Astra (max) (95.8%). The results either side are NVIDIA-Nemotron-3-Super-120B-A12B-BF16 (79.2%) and K-EXAONE-236B-A23B (79.1%). It covers expert-level science questions. The board median is 71.7%, so claude-sonnet-4-20250514_59K is 7.5 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
On OTIS Mock AIME, claude-sonnet-4-20250514_59K reaches 68.9%. It ranks #81 of 189, ahead of 57% of the field, and 31.1 points behind Claude Fable 5.1 (max) at 100.0%. The results either side are claude-opus-4-1-20250805_27K (68.9%) and GPT-5.5 Instant (68.1%). It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so claude-sonnet-4-20250514_59K is 11.1 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Strengths and weaknesses
Reasoning, maths and science: solid, ahead of 59% of the field on average across 2 benchmarks. Its best board here is GPQA Diamond (#109 of 275) and its weakest is OTIS Mock AIME (#81 of 189).
Release history
The Anthropic model released before it was claude-sonnet-4-20250514_2K on 2025-05-14, which scores 50.0. The next one was Claude 4 Opus on 2025-05-22, at 51.0.
Reading these numbers
The 2 scores on this page come from 1 source: Epoch AI Benchmarking Hub (2). No official leaderboard supplied any of them, so treat them as third-party measurements. With 2 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #152 GLM-4.6-FP8 (51.0)
- #153 Claude 4 Opus (51.0)
- #154 Gemini 2.5 Pro Preview (Mar 2025) (50.9)
- #156 Dracarys2-72B-Instruct (50.9)
- #157 gemini-1.5-pro-exp-0827 (50.9)
- #158 GPT-5.6 Luna 2026-07-30 (Max) (50.9)
More from Anthropic
- Claude Opus 5.5 (max) (#1, 64.3)
- Claude Fable 5.1 (max) (#3, 61.9)
- Claude Sonnet 5.5 (max) (#4, 60.8)
- Claude Opus 5 (max) (#8, 60.0)
- Claude Fable 5 (max) (#9, 59.9)
- claude-opus-4-8-xhigh-effort (#14, 56.6)
Compare it on the live leaderboard → · How the aggregate score works