Opus 4.5 (Thinking, 64K): benchmark scores, price and ranking
Opus 4.5 (Thinking, 64K) ranks #247 of 743 LLMs on the LLMs Tiger aggregate benchmark score (49.6), based on 1 benchmark results captured up to 2026-10-13.
- Type
- Frontier model
- Open weights
- No
- Aggregate rank
- #247 of 743 (score 49.6)
Across the 1 benchmark where at least ten models are scored, Opus 4.5 (Thinking, 64K) is in the top 10% on 0 and in the top half on 1.
Opus 4.5 (Thinking, 64K) benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| ARC-AGI-2 | 37.6% | #41 of 87 | ARC Prize official leaderboard | 2026-10-13 |
About Opus 4.5 (Thinking, 64K)
Opus 4.5 (Thinking, 64K) is a frontier model. No API price is listed for it yet. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.
Where Opus 4.5 (Thinking, 64K) stands
On our aggregate score, Opus 4.5 (Thinking, 64K) is #247 of 743 ranked models, around the middle of the table. Its score is 49.6; the scale is centred on 50, so it sits 0.4 points below the typical model. That beats 67% of the ranked field.
Opus 4.5 (Thinking, 64K), benchmark by benchmark
ARC-AGI-2 puts Opus 4.5 (Thinking, 64K) at 37.6%, #41 of 87. That beats 53% of the models tested, but 57.4 points short of GPT-6 Astra (max) (95.0%). The results either side are Inkling Small (xhigh) (40.1%) and Gemini 3 Flash Preview (High) (33.6%). It covers abstract reasoning, ARC Prize public eval set. The board median is 22.8%, so Opus 4.5 (Thinking, 64K) is 14.9 points above it. Source: ARC Prize official leaderboard, captured 2026-10-13.
Reading these numbers
The 1 score on this page comes from 1 source: ARC Prize official leaderboard (1). 1 of them come from an official leaderboard and 0 from datasets or third-party runs. With 1 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #244 Inkling Small (xhigh) (49.7)
- #245 GLM-4.5-FP8 (49.6)
- #246 GLM-5.1 (49.6)
- #248 GLM-5.3-Flash (max) (49.6)
- #249 grok-4.20-0309-reasoning (49.6)
- #250 Grok-2 (49.6)
Compare it on the live leaderboard → · How the aggregate score works