claude-sonnet-4-20250514_32K: benchmark scores, price and ranking

claude-sonnet-4-20250514_32K from Anthropic ranks #225 of 743 LLMs on the LLMs Tiger aggregate benchmark score (49.9), based on 3 benchmark results captured up to 2026-10-13.

Organisation: Anthropic
Type: Frontier model
Open weights: No
Released: 2025-05-22 (source: curated)
Aggregate rank: #225 of 743 (score 49.9)

Relative to other models, claude-sonnet-4-20250514_32K is strongest on OTIS Mock AIME (#76 of 189) and weakest on ALE-Bench (#48 of 79).

Across the 3 benchmarks where at least ten models are scored, claude-sonnet-4-20250514_32K is in the top 10% on 0 and in the top half on 2.

claude-sonnet-4-20250514_32K benchmark results

claude-sonnet-4-20250514_32K benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
OTIS Mock AIME	71.1%	#76 of 189	Epoch AI Benchmarking Hub	2026-10-13
GPQA Diamond	78.3%	#114 of 275	Epoch AI Benchmarking Hub	2026-10-13
ALE-Bench	655	#48 of 79	Epoch AI Benchmarking Hub	2026-10-13

About claude-sonnet-4-20250514_32K

claude-sonnet-4-20250514_32K is a frontier model from Anthropic. It was released on 2025-05-22, according to the developer's announcement. No API price is listed for it yet. We hold 3 benchmark results for it across 2 areas, and none is in the top tenth of its board.

Where claude-sonnet-4-20250514_32K stands

On our aggregate score, claude-sonnet-4-20250514_32K is #225 of 743 ranked models, around the middle of the table. Its score is 49.9; the scale is centred on 50, so it sits 0.1 points below the typical model. That beats 70% of the ranked field. Among the 70 ranked Anthropic models it is #38. The next one up is claude-sonnet-4-20250514_2K at 50.0. The next one down is claude-sonnet-4-20250514_12K at 49.9.

claude-sonnet-4-20250514_32K, benchmark by benchmark

OTIS Mock AIME puts claude-sonnet-4-20250514_32K at 71.1%, #76 of 189. That beats 60% of the models tested, but 28.9 points short of Claude Fable 5.1 (max) (100.0%). The results either side are Claude Sonnet 4.6 (max) (71.1%) and MiniMax-M3 (71.1%). It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so claude-sonnet-4-20250514_32K is 13.3 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

On GPQA Diamond, claude-sonnet-4-20250514_32K reaches 78.3%. It ranks #114 of 275, ahead of 59% of the field, and 17.5 points behind GPT-6 Astra (max) at 95.8%. The results either side are DeepSeek R1 (0528) (78.8%) and claude-opus-4-1-20250805_16K (77.3%). It covers expert-level science questions. The board median is 71.7%, so claude-sonnet-4-20250514_32K is 6.6 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

claude-sonnet-4-20250514_32K lands below the middle on ALE-Bench: 655, #48 of 79, with 59% of the field scoring higher. GPT-6 Astra (max) leads at 2,951; the closest result above is gemini-2.5-flash at 662. It covers AtCoder heuristic-optimisation contests (performance rating). The board median is 764, so claude-sonnet-4-20250514_32K is 109 points below 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 OTIS Mock AIME (#76 of 189) and its weakest is GPQA Diamond (#114 of 275).

Release history

The Anthropic model released before it was claude-sonnet-4-20250514 on 2025-05-22, which scores 48.9. The next one was Claude Sonnet 4 (unknown thinking) on 2025-05-22, at 46.1.

Reading these numbers

The 3 scores on this page come from 1 source: Epoch AI Benchmarking Hub (3). No official leaderboard supplied any of them, so treat them as third-party measurements. With 3 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

#222 gemini-2.5-flash-preview-09-2025 (50.0)
#223 DeepSeek v4 (unknown) (50.0)
#224 Devstral Small (2512) (49.9)
#226 Mistral-Small-4-119B-2603 (49.9)
#227 DeepSeek Coder V2 0724 (49.9)
#228 MiniMax-M2.1 (49.9)