claude-3-opus-20240229: benchmark scores, price and ranking

claude-3-opus-20240229 from Anthropic ranks #687 of 743 LLMs on the LLMs Tiger aggregate benchmark score (43.2), based on 13 benchmark results captured up to 2026-10-13.

Organisation

Anthropic

Type

Frontier model

Open weights

No

Released

2024-03-04 (source: curated)

Cheapest API price

$15.00 in / $75.00 out per million tokens (via vertex_ai, observed 2026-10-13T19:47Z)

Aggregate rank

#687 of 743 (score 43.2)

Relative to other models, claude-3-opus-20240229 is strongest on Aider Code Editing (#18 of 92) and weakest on SimpleQA Verified (#64 of 69).

Across the 13 benchmarks where at least ten models are scored, claude-3-opus-20240229 is in the top 10% on 0 and in the top half on 2.

Its cheapest listed input price, $15.00 per million tokens, is lower than that of 2% of the 427 models with a listed price.

claude-3-opus-20240229 benchmark results

About claude-3-opus-20240229

claude-3-opus-20240229 is a frontier model from Anthropic. It was released on 2024-03-04, according to the developer's announcement. The cheapest API listing we track charges $15.00 per million input tokens and $75.00 per million output tokens, through vertex_ai. We hold 13 benchmark results for it across 4 areas, and none is in the top tenth of its board.

Where claude-3-opus-20240229 stands

On our aggregate score, claude-3-opus-20240229 is #687 of 743 ranked models, in the lower half. Its score is 43.2; the scale is centred on 50, so it sits 6.8 points below the typical model. That beats 8% of the ranked field. Among the 70 ranked Anthropic models it is #65. The next one up is Claude 2 at 43.7. The next one down is claude-2.0 at 42.2.

claude-3-opus-20240229, benchmark by benchmark

Aider Code Editing puts claude-3-opus-20240229 at 68.4%, #18 of 92. That beats 80% of the models tested, but 15.8 points short of Claude 3.5-Sonnet-20241022 (84.2%). The results either side are Qwen2.5-Coder-14B-Instruct (69.2%) and GPT-4 (0613) (67.7%). It covers Aider official benchmark. The board median is 55.6%, so claude-3-opus-20240229 is 12.8 points above it. Source: Aider Aider Code Editing leaderboard, captured 2026-10-13.

On Aider Refactoring, claude-3-opus-20240229 reaches 72.3%. It ranks #3 of 12, ahead of 75% of the field, and 19.8 points behind Claude 3.5-Sonnet-20241022 at 92.1%. The results either side are o1-preview (75.3%) and claude-3.5-sonnet-20240620 (64.0%). It covers Aider official benchmark. The board median is 50.0%, so claude-3-opus-20240229 is 22.3 points above it. Source: Aider Aider Refactoring leaderboard, captured 2026-10-13.

claude-3-opus-20240229 lands below the middle on Chess Puzzles: 5.0%, #78 of 122, with 63% of the field scoring higher. GPT-6 Astra (max) leads at 72.0%; the closest result above is o3-mini-2025-01-31 (low) at 6.0%. It covers chess tactics puzzles. The board median is 12.5%, so claude-3-opus-20240229 is 7.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

claude-3-opus-20240229 lands below the middle on DTBench: 61.6%, #95 of 146, with 64% of the field scoring higher. Claude Opus 5.5 (max) leads at 98.9%; the closest result above is Llama 4 Maverick at 61.9%. It covers dynamic tool-use benchmark. The board median is 68.8%, so claude-3-opus-20240229 is 7.2 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

claude-3-opus-20240229 lands below the middle on Cybench: 10.0%, #11 of 16, with 62% of the field scoring higher. grok-4-0709 leads at 43.0%; the closest result above is GPT-4o (Nov 2024) at 12.5%. It covers cybersecurity capture-the-flag tasks. The board median is 17.5%, so claude-3-opus-20240229 is 7.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

claude-3-opus-20240229 lands below the middle on GPQA Diamond: 47.2%, #201 of 275, with 73% of the field scoring higher. GPT-6 Astra (max) leads at 95.8%; the closest result above is mistral-small-3-2501 at 47.3%. It covers expert-level science questions. The board median is 71.7%, so claude-3-opus-20240229 is 24.6 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

SimpleBench is a weak spot. claude-3-opus-20240229 scores 23.5%, #51 of 61, behind 82% of the models measured. The leader, Claude Fable 5 (max), reaches 81.9%. It covers trick questions that test common sense. The board median is 41.4%, so claude-3-opus-20240229 is 17.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

METR time horizon is a weak spot. claude-3-opus-20240229 scores 4 min, #27 of 31, behind 84% of the models measured. The leader, Claude Mythos Preview (Early), reaches 1,045 min. It covers length of task (minutes) done at 50% success. The board median is 23 min, so claude-3-opus-20240229 is 19 minutes below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

WeirdML is a weak spot. claude-3-opus-20240229 scores 19.2%, #95 of 109, behind 86% of the models measured. The leader, GPT-6 Astra (max), reaches 93.3%. It covers unusual machine-learning tasks. The board median is 41.2%, so claude-3-opus-20240229 is 22.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

SimpleQA Verified is a weak spot. claude-3-opus-20240229 scores 12.6%, #64 of 69, behind 91% of the models measured. The leader, gemini-4-argon-high, reaches 76.0%. It covers short factual questions. The board median is 41.0%, so claude-3-opus-20240229 is 28.4 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

The full table above also lists the other 3 results, including boards with fewer than ten models, where a rank says little.

Strengths and weaknesses

Reasoning, maths and science: weak, ahead of 20% of the field on average across 4 benchmarks. Its best board here is GPQA Diamond (#201 of 275) and its weakest is SimpleBench (#51 of 61). General knowledge and chat: weak, ahead of 29% of the field on average across 7 benchmarks. Its best board here is Aider Refactoring (#3 of 12) and its weakest is SimpleQA Verified (#64 of 69).

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so claude-3-opus-20240229 costs more than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), Qwen2.5-Coder-3B-Instruct ($0.010, 46.5). Similar scores cost more on GPT-4 (Mar 2023) ($30.00).

Release history

The Anthropic model released before it was Claude 3 Opus on 2024-03-04, which scores 45.7. The next one was claude-3-sonnet-20240229 on 2024-03-04, at 41.9.

Reading these numbers

The 13 scores on this page come from 3 sources: Epoch AI Benchmarking Hub (11), Aider Aider Code Editing leaderboard (1), Aider Aider Refactoring leaderboard (1). 2 of them come from an official leaderboard and 11 from datasets or third-party runs.

Models ranked nearby

• #684 Trinity Large Thinking (43.2)
• #685 granite-4.0-micro (43.2)
• #686 SWE-Llama 13B (43.2)
• #688 granite-3.1-3b-a800m-base (43.1)
• #689 GPT-4.1 mini (43.0)
• #690 GPT-3.5 (43.0)

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