claude-3-7-sonnet-20250219: benchmark scores, price and ranking
claude-3-7-sonnet-20250219 from Anthropic ranks #375 of 743 LLMs on the LLMs Tiger aggregate benchmark score (48.2), based on 12 benchmark results captured up to 2026-10-13.
- Organisation
- Anthropic
- Type
- Frontier model
- Open weights
- No
- Released
- 2025-02-24 (source: curated)
- Aggregate rank
- #375 of 743 (score 48.2)
Relative to other models, claude-3-7-sonnet-20250219 is strongest on Aider Polyglot (#8 of 49) and weakest on GSO-Bench (#14 of 19).
Across the 11 benchmarks where at least ten models are scored, claude-3-7-sonnet-20250219 is in the top 10% on 0 and in the top half on 6.
claude-3-7-sonnet-20250219 benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| Aider Polyglot | 64.9% | #8 of 49 | Aider polyglot leaderboard | 2026-10-13 |
| TheAgentCompany | 30.9% | #3 of 13 | Epoch AI Benchmarking Hub | 2026-10-13 |
| METR time horizon | 60 min | #11 of 31 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Cybench | 20.0% | #7 of 16 | Epoch AI Benchmarking Hub | 2026-10-13 |
| SWE-bench Verified | 61.0% | #32 of 73 | Epoch AI Benchmarking Hub | 2026-10-13 |
| SimpleBench | 44.9% | #29 of 61 | Epoch AI Benchmarking Hub | 2026-10-13 |
| GPQA Diamond | 66.0% | #153 of 275 | Epoch AI Benchmarking Hub | 2026-10-13 |
| EnigmaEval | 2.3% | #14 of 24 | Epoch AI Benchmarking Hub | 2026-10-13 |
| OSWorld | 35.8% | #3 of 5 | Epoch AI Benchmarking Hub | 2026-10-13 |
| OTIS Mock AIME | 21.9% | #128 of 189 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Fiction.liveBench | 50.0% | #33 of 47 | Epoch AI Benchmarking Hub | 2026-10-13 |
| GSO-Bench | 3.8% | #14 of 19 | Epoch AI Benchmarking Hub | 2026-10-13 |
About claude-3-7-sonnet-20250219
claude-3-7-sonnet-20250219 is a frontier model from Anthropic. It was released on 2025-02-24, according to the developer's announcement. No API price is listed for it yet. We hold 12 benchmark results for it across 4 areas, and none is in the top tenth of its board.
Where claude-3-7-sonnet-20250219 stands
On our aggregate score, claude-3-7-sonnet-20250219 is #375 of 743 ranked models, around the middle of the table. Its score is 48.2; the scale is centred on 50, so it sits 1.8 points below the typical model. That beats 50% of the ranked field. Among the 70 ranked Anthropic models it is #52. The next one up is Claude 3.5 Haiku at 48.5. The next one down is Claude Haiku 4.5 (Thinking 32K) at 47.7.
claude-3-7-sonnet-20250219, benchmark by benchmark
Aider Polyglot puts claude-3-7-sonnet-20250219 at 64.9%, #8 of 49. That beats 84% of the models tested, but 18.2 points short of gemini-2.5-pro-preview-06-05 (83.1%). The results either side are DeepSeek R1 (0528) (71.4%) and DeepSeek R1 + claude-3-5-sonnet-20241022 (64.0%). It covers edits across 6 languages (225 exercises). The board median is 44.9%, so claude-3-7-sonnet-20250219 is 20.0 points above it. Source: Aider polyglot leaderboard, captured 2026-10-13.
On TheAgentCompany, claude-3-7-sonnet-20250219 reaches 30.9%. It ranks #3 of 13, ahead of 77% of the field, and 10.2 points behind gemini-2.5-flash-preview-09-2025 at 41.1%. The results either side are claude-sonnet-4-20250514 (33.1%) and Gemini 2.5 Pro Preview (Jun 2025) (30.3%). It covers work tasks in a simulated software company. The board median is 8.6%, so claude-3-7-sonnet-20250219 is 22.3 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
claude-3-7-sonnet-20250219 manages 60 min on METR time horizon, good for #11 of 31. Claude Mythos Preview (Early) leads at 1,045 min, 984 minutes further up, and 65% of models sit below. The results either side are claude-sonnet-4-20250514_16K (75 min) and Kimi K2 Thinking (54 min). It covers length of task (minutes) done at 50% success. The board median is 23 min, so claude-3-7-sonnet-20250219 is 37 minutes above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Cybench puts claude-3-7-sonnet-20250219 at 20.0%, #7 of 16. That beats 56% of the models tested, but 23.0 points short of grok-4-0709 (43.0%). The results either side are grok-4-fast (30.0%) and Claude 3.5 Sonnet (Jun 2024) (17.5%). It covers cybersecurity capture-the-flag tasks. The board median is 17.5%, so claude-3-7-sonnet-20250219 is 2.5 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
On SWE-bench Verified, claude-3-7-sonnet-20250219 reaches 61.0%. It ranks #32 of 73, ahead of 56% of the field, and 22.5 points behind Claude Opus 4.7 (max) at 83.5%. The results either side are MiniMax-M2 (61.0%) and Qwen3-Coder-30B-A3B-Instruct (60.4%). It covers real GitHub issues resolved. The board median is 56.4%, so claude-3-7-sonnet-20250219 is 4.6 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
claude-3-7-sonnet-20250219 manages 44.9% on SimpleBench, good for #29 of 61. Claude Fable 5 (max) leads at 81.9%, 37.0 points further up, and 52% of models sit below. The results either side are claude-sonnet-4-20250514_12K (45.5%) and o1-preview (41.7%). It covers trick questions that test common sense. The board median is 41.4%, so claude-3-7-sonnet-20250219 is 3.5 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
claude-3-7-sonnet-20250219 lands below the middle on EnigmaEval: 2.3%, #14 of 24, with 54% of the field scoring higher. Gemini 3 Pro Preview leads at 18.2%; the closest result above is gemini-2.5-flash-preview-05-20 at 2.7%. It covers multi-step puzzle hunts. The board median is 2.9%, so claude-3-7-sonnet-20250219 is 0.7 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
claude-3-7-sonnet-20250219 lands below the middle on OTIS Mock AIME: 21.9%, #128 of 189, with 67% of the field scoring higher. Claude Fable 5.1 (max) leads at 100.0%; the closest result above is gemma-3-27b-it at 22.5%. It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so claude-3-7-sonnet-20250219 is 35.8 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
claude-3-7-sonnet-20250219 lands below the middle on Fiction.liveBench: 50.0%, #33 of 47, with 68% of the field scoring higher. grok-4-0709 leads at 94.4%; the closest result above is Gemini 2.0 Flash Thinking Exp at 52.8%. It covers long-context story comprehension (16k). The board median is 61.1%, so claude-3-7-sonnet-20250219 is 11.1 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
claude-3-7-sonnet-20250219 lands below the middle on GSO-Bench: 3.8%, #14 of 19, with 68% of the field scoring higher. GPT-5.5 (xhigh) leads at 40.2%; the closest result above is Gemini 2.5 Pro Preview (Jun 2025) at 3.9%. It covers software performance optimisation. The board median is 4.9%, so claude-3-7-sonnet-20250219 is 1.1 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
The full table above also lists the other 2 results, including boards with fewer than ten models, where a rank says little.
Strengths and weaknesses
Software engineering: solid, ahead of 55% of the field on average across 3 benchmarks. Its best board here is Aider Polyglot (#8 of 49) and its weakest is GSO-Bench (#14 of 19). Reasoning, maths and science: uneven, ahead of 43% of the field on average across 4 benchmarks. Its best board here is SimpleBench (#29 of 61) and its weakest is OTIS Mock AIME (#128 of 189). General knowledge and chat: solid, ahead of 50% of the field on average across 3 benchmarks. Its best board here is METR time horizon (#11 of 31) and its weakest is Fiction.liveBench (#33 of 47).
Release history
The Anthropic model released before it was Claude 3.5 Sonnet (Oct 2024) on 2024-10-22, which scores 45.4. The next one was Claude 3.7 Sonnet (64k thinking) on 2025-02-24, at 50.4.
Reading these numbers
The 12 scores on this page come from 2 sources: Epoch AI Benchmarking Hub (11), Aider polyglot leaderboard (1). 1 of them come from an official leaderboard and 11 from datasets or third-party runs.
Models ranked nearby
- #372 qwen3.5-35b-a3b (48.2)
- #373 DeepSeek-R1 (May 2025) (48.2)
- #374 Qwen2.5 (7B + 72B) (48.2)
- #376 qwen2:72b-instruct-q8_0 (48.2)
- #377 Qwen3-Max-Instruct (48.2)
- #378 internlm3-8b-instruct (48.2)
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