Claude 4.5 Opus: benchmark scores, price and ranking

Claude 4.5 Opus from Anthropic ranks #21 of 743 LLMs on the LLMs Tiger aggregate benchmark score (54.5), based on 3 benchmark results captured up to 2026-10-13.

Organisation: Anthropic
Type: Frontier model
Open weights: No
Released: 2025-11-24 (source: curated)
Aggregate rank: #21 of 743 (score 54.5)

Relative to other models, Claude 4.5 Opus is strongest on SWE-bench Test (#1 of 11) and weakest on SWE-bench Multilingual (#3 of 11).

Across the 3 benchmarks where at least ten models are scored, Claude 4.5 Opus is in the top 10% on 1 and in the top half on 3.

Claude 4.5 Opus benchmark results

Claude 4.5 Opus benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
SWE-bench Test	52.6%	#1 of 11	SWE-bench Test leaderboard	2026-10-13
SWE-bench Verified	74.4%	#9 of 73	SWE-bench Verified leaderboard	2026-10-13
SWE-bench Multilingual	70.7%	#3 of 11	SWE-bench Multilingual leaderboard	2026-10-13

About Claude 4.5 Opus

Claude 4.5 Opus is a frontier model from Anthropic. It was released on 2025-11-24, 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 1 is in the top tenth of its board.

Where Claude 4.5 Opus stands

On our aggregate score, Claude 4.5 Opus is #21 of 743 ranked models, in the top fifty. Its score is 54.5; the scale is centred on 50, so it sits 4.5 points above the typical model. That beats 97% of the ranked field. Among the 70 ranked Anthropic models it is #8. The next one up is Claude 4 Sonnet at 54.5. The next one down is Claude 3.5-Sonnet-20241022 at 54.4.

Claude 4.5 Opus, benchmark by benchmark

SWE-bench Test is where Claude 4.5 Opus does best: 52.6%, first of 11. The next result is CodeAct v2.1 (claude-3-5-sonnet-20241022) at 29.4%, 23.2 points behind. It covers real GitHub issues resolved. The board median is 12.5%, so Claude 4.5 Opus is 40.1 points above it. Source: SWE-bench Test leaderboard, captured 2026-10-13.

On SWE-bench Verified, Claude 4.5 Opus reaches 74.4%. It ranks #9 of 73, ahead of 88% of the field, and 9.1 points behind Claude Opus 4.7 (max) at 83.5%. The results either side are Claude 4.6 Opus (75.6%) and Gemini 3 Pro Preview (74.2%). It covers real GitHub issues resolved. The board median is 56.4%, so Claude 4.5 Opus is 18.0 points above it. Source: SWE-bench Verified leaderboard, captured 2026-10-13.

Claude 4.5 Opus manages 70.7% on SWE-bench Multilingual, good for #3 of 11. Gemini 3 Flash leads at 72.7%, 2.0 points further up, and 73% of models sit below. The results either side are Claude 4.6 Opus (72.0%) and GLM-5 (69.7%). It covers real GitHub issues resolved. The board median is 68.3%, so Claude 4.5 Opus is 2.4 points above it. Source: SWE-bench Multilingual leaderboard, captured 2026-10-13.

Strengths and weaknesses

General knowledge and chat: strong, ahead of 82% of the field on average across 2 benchmarks. Its best board here is SWE-bench Test (#1 of 11) and its weakest is SWE-bench Multilingual (#3 of 11).

Release history

The Anthropic model released before it was Claude Haiku 4.5 (Thinking 32K) on 2025-10-15, which scores 47.7. The next one was Claude Opus 4.5 (128k thinking) on 2025-11-24, at 49.9.

Reading these numbers

The 3 scores on this page come from 3 sources: SWE-bench Multilingual leaderboard (1), SWE-bench Test leaderboard (1), SWE-bench Verified leaderboard (1). 2 of them come from an official leaderboard and 1 from datasets or third-party runs. With 3 results the aggregate rank can move a lot when one new score arrives.