Claude Opus 4.5 (128k thinking): benchmark scores, price and ranking

Claude Opus 4.5 (128k thinking) from Anthropic ranks #230 of 743 LLMs on the LLMs Tiger aggregate benchmark score (49.9), based on 2 benchmark results captured up to 2026-10-13.

Organisation: Anthropic
Type: Frontier model
Open weights: No
Released: 2025-11-24 (source: curated)
Cheapest API price: $5.00 in / $25.00 out per million tokens (via anthropic, observed 2026-10-13T20:47Z)
Aggregate rank: #230 of 743 (score 49.9)

Across the 2 benchmarks where at least ten models are scored, Claude Opus 4.5 (128k thinking) is in the top 10% on 0 and in the top half on 1.

Its cheapest listed input price, $5.00 per million tokens, is lower than that of 7% of the 427 models with a listed price.

Claude Opus 4.5 (128k thinking) benchmark results

Claude Opus 4.5 (128k thinking) benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
Terminal-Bench 2.0	59.1%	#5 of 28	Epoch AI Benchmarking Hub	2026-10-13
EBR-Bench	14.3%	#16 of 21	Epoch AI Benchmarking Hub	2026-10-13

About Claude Opus 4.5 (128k thinking)

Claude Opus 4.5 (128k thinking) is a frontier model from Anthropic. It was released on 2025-11-24, according to the developer's announcement. The cheapest API listing we track charges $5.00 per million input tokens and $25.00 per million output tokens, through anthropic. We hold 2 benchmark results for it across 2 areas, and none is in the top tenth of its board.

Where Claude Opus 4.5 (128k thinking) stands

On our aggregate score, Claude Opus 4.5 (128k thinking) is #230 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 69% of the ranked field. Among the 70 ranked Anthropic models it is #40. The next one up is claude-sonnet-4-20250514_12K at 49.9. The next one down is claude-haiku-4-5-20251001_1K at 49.8.

Claude Opus 4.5 (128k thinking), benchmark by benchmark

Terminal-Bench 2.0 puts Claude Opus 4.5 (128k thinking) at 59.1%, #5 of 28. That beats 82% of the models tested, but 10.3 points short of Gemini 3 Pro Preview (69.4%). The results either side are GPT-5.1-Codex-Max (60.4%) and GPT-5.1 Codex (57.8%). It covers real terminal tasks (agent + model). The board median is 37.3%, so Claude Opus 4.5 (128k thinking) is 21.8 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Claude Opus 4.5 (128k thinking) lands below the middle on EBR-Bench: 14.3%, #16 of 21, with 71% of the field scoring higher. GPT-6 Astra (max) leads at 76.2%; the closest result above is Claude Opus 4.7 (max) at 19.0%. It covers evidence-based reasoning. The board median is 31.4%, so Claude Opus 4.5 (128k thinking) is 17.1 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Strengths and weaknesses

Claude Opus 4.5 (128k thinking) has too few results on boards with ten or more models to say where it is strong or weak. Treat any single score as a data point, not a verdict.

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so Claude Opus 4.5 (128k thinking) 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), DeepSeek V4 Flash 0731 (max) ($0.016, 53.1). Similar scores cost more on gpt-4-1106-preview ($10.00) and gpt-4-0125-preview ($10.00).

Release history

The Anthropic model released before it was Claude 4.5 Opus on 2025-11-24, which scores 54.5. The next one was claude-opus-4-5-20251101-high-32k on 2025-11-24, at 48.9.

Reading these numbers

The 2 scores on this page come from 1 source: Epoch AI Benchmarking Hub (2). No official leaderboard supplied any of them, so treat them as third-party measurements. The leaderboard also lists 9 other reasoning-effort settings of this model, which redirect here. This page shows the highest. With 2 results the aggregate rank can move a lot when one new score arrives.

Claude Opus 4.5 (128k thinking) is also listed at 9 other reasoning-effort settings; this page shows the highest-effort row, which is the one the leaderboard keeps by default.

Models ranked nearby

#227 DeepSeek Coder V2 0724 (49.9)
#228 MiniMax-M2.1 (49.9)
#229 claude-sonnet-4-20250514_12K (49.9)
#231 Mistral Large 2 (2407) (49.9)
#232 gpt-5.6-sol-xhigh (codex-harness) (49.8)
#233 o3 (high) (49.8)