claude-opus-4-8-xhigh-effort: benchmark scores, price and ranking
claude-opus-4-8-xhigh-effort from Anthropic ranks #14 of 743 LLMs on the LLMs Tiger aggregate benchmark score (56.6), based on 7 benchmark results captured up to 2026-10-13.
- Organisation
- Anthropic
- Type
- Frontier model
- Open weights
- No
- Released
- 2026-05-28 (source: curated)
- Cheapest API price
- $5.00 in / $25.00 out per million tokens (via anthropic, observed 2026-10-13T20:47Z)
- Aggregate rank
- #14 of 743 (score 56.6)
Relative to other models, claude-opus-4-8-xhigh-effort is strongest on LiveBench Agentic Coding (#1 of 17) and weakest on LiveBench Language (#5 of 17).
Across the 7 benchmarks where at least ten models are scored, claude-opus-4-8-xhigh-effort is in the top 10% on 2 and in the top half on 7.
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-4-8-xhigh-effort benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| LiveBench Agentic Coding | 56.1% | #1 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-13 |
| LiveBench Reasoning | 89.7% | #1 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-13 |
| LiveBench Mathematics | 95.3% | #2 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-13 |
| LiveBench Coding | 79.3% | #4 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-13 |
| LiveBench Data Analysis | 78.3% | #4 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-13 |
| LiveBench IF | 72.4% | #4 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-13 |
| LiveBench Language | 81.4% | #5 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-13 |
About claude-opus-4-8-xhigh-effort
claude-opus-4-8-xhigh-effort is a frontier model from Anthropic. It was released on 2026-05-28, 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 7 benchmark results for it across 3 areas, and 2 are in the top tenth of their boards.
Where claude-opus-4-8-xhigh-effort stands
On our aggregate score, claude-opus-4-8-xhigh-effort is #14 of 743 ranked models, in the top fifty. Its score is 56.6; the scale is centred on 50, so it sits 6.6 points above the typical model. That beats 98% of the ranked field. Among the 70 ranked Anthropic models it is #6. The next one up is Claude Fable 5 (max) at 59.9. The next one down is Claude 4 Sonnet at 54.5.
claude-opus-4-8-xhigh-effort, benchmark by benchmark
LiveBench Agentic Coding is where claude-opus-4-8-xhigh-effort does best: 56.1%, first of 17. The next result is GPT-5.4 (xhigh) at 53.8%, 2.2 points behind. It covers LiveBench release 2026_06_25. The board median is 45.8%, so claude-opus-4-8-xhigh-effort is 10.3 points above it. Source: LiveBench 2026_06_25 official CSV, captured 2026-10-13.
LiveBench Reasoning is where claude-opus-4-8-xhigh-effort does best: 89.7%, first of 17. The next result is GPT-5.5 (xhigh) at 89.7%, 0.1 points behind. It covers LiveBench release 2026_06_25. The board median is 81.1%, so claude-opus-4-8-xhigh-effort is 8.6 points above it. Source: LiveBench 2026_06_25 official CSV, captured 2026-10-13.
claude-opus-4-8-xhigh-effort manages 95.3% on LiveBench Mathematics, good for #2 of 17. GPT-5.5 (xhigh) leads at 95.9%, 0.5 points further up, and 88% of models sit below. The results either side are GPT-5.5 (xhigh) (95.9%) and GPT-5.4 (xhigh) (94.1%). It covers LiveBench release 2026_06_25. The board median is 88.2%, so claude-opus-4-8-xhigh-effort is 7.1 points above it. Source: LiveBench 2026_06_25 official CSV, captured 2026-10-13.
LiveBench Coding puts claude-opus-4-8-xhigh-effort at 79.3%, #4 of 17. That beats 76% of the models tested, but 4.3 points short of GPT-5.2 Codex (83.6%). The results either side are claude-opus-4-5-20251101-thinking-64k-high-effort (79.7%) and kimi-k2.6-thinking (78.6%). It covers LiveBench release 2026_06_25. The board median is 76.5%, so claude-opus-4-8-xhigh-effort is 2.8 points above it. Source: LiveBench 2026_06_25 official CSV, captured 2026-10-13.
On LiveBench Data Analysis, claude-opus-4-8-xhigh-effort reaches 78.3%. It ranks #4 of 17, ahead of 76% of the field, and 3.2 points behind GPT-5.5 (xhigh) at 81.6%. The results either side are gemini-3.1-pro-preview-high (78.5%) and GPT-5.2 Codex (78.2%). It covers LiveBench release 2026_06_25. The board median is 71.8%, so claude-opus-4-8-xhigh-effort is 6.6 points above it. Source: LiveBench 2026_06_25 official CSV, captured 2026-10-13.
claude-opus-4-8-xhigh-effort manages 72.4% on LiveBench IF, good for #4 of 17. gemini-3.1-pro-preview-high leads at 79.1%, 6.7 points further up, and 76% of models sit below. The results either side are Qwen3.7 Max (74.0%) and GPT-5.5 (xhigh) (70.7%). It covers LiveBench release 2026_06_25. The board median is 65.2%, so claude-opus-4-8-xhigh-effort is 7.2 points above it. Source: LiveBench 2026_06_25 official CSV, captured 2026-10-13.
LiveBench Language puts claude-opus-4-8-xhigh-effort at 81.4%, #5 of 17. That beats 71% of the models tested, but 5.9 points short of GPT-5.5 (xhigh) (87.4%). The results either side are GPT-5.4 (xhigh) (82.6%) and claude-opus-4-5-20251101-thinking-64k-high-effort (81.3%). It covers LiveBench release 2026_06_25. The board median is 77.9%, so claude-opus-4-8-xhigh-effort is 3.5 points above it. Source: LiveBench 2026_06_25 official CSV, captured 2026-10-13.
Strengths and weaknesses
Software engineering: strong, ahead of 85% of the field on average across 2 benchmarks. Its best board here is LiveBench Agentic Coding (#1 of 17) and its weakest is LiveBench Coding (#4 of 17). Reasoning, maths and science: strong, ahead of 91% of the field on average across 2 benchmarks. Its best board here is LiveBench Reasoning (#1 of 17) and its weakest is LiveBench Mathematics (#2 of 17). General knowledge and chat: solid, ahead of 75% of the field on average across 3 benchmarks. Its best board here is LiveBench Data Analysis (#4 of 17) and its weakest is LiveBench Language (#5 of 17).
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so claude-opus-4-8-xhigh-effort costs more than the typical listing. Models that score within 1.5 points or better and cost less: GPT-5.6 Luna (max) ($0.200, 55.1), Kimi K3 (max) ($0.730, 55.7), Muse Spark 1.3 (max) ($1.25, 55.1).
Release history
The Anthropic model released before it was Claude Opus 4.7 (max) on 2026-04-16, which scores 53.7. The next one was Claude Fable 5 (max) on 2026-06-09, at 59.9.
Reading these numbers
The 7 scores on this page come from 1 source: LiveBench 2026_06_25 official CSV (7). 7 of them come from an official leaderboard and 0 from datasets or third-party runs. The leaderboard also lists 4 other reasoning-effort settings of this model, which redirect here. This page shows the highest. With 7 results the aggregate rank can move a lot when one new score arrives.
claude-opus-4-8-xhigh-effort is also listed at 4 other reasoning-effort settings; this page shows the highest-effort row, which is the one the leaderboard keeps by default.
Models ranked nearby
- #11 GPT-5.5 (xhigh) (58.0)
- #12 GPT-5.6 Terra (max) (57.8)
- #13 GPT-5.4 (xhigh) (56.9)
- #15 Kimi K3 (max) (55.7)
- #16 gemini-3.1-pro-preview-high (55.3)
- #17 GPT-5.6 Luna (max) (55.1)
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 4 Sonnet (#20, 54.5)
Compare it on the live leaderboard → · How the aggregate score works