# Claude Opus 4.8Medium

> Source: Benchize (https://benchize.com) — https://benchize.com/models/claude-opus-4-8-medium. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/claude-opus-4-8-medium.

Anthropic

Canonical URL: https://benchize.com/models/claude-opus-4-8-medium
Last updated: Thu, 22 Oct 2026 06:30:09 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

Anthropic

## Benchmarks

| Benchmark | Score | ± | Rank | Cost | Latency | Source |  |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [DeepSWE](https://benchize.com/benchmarks/deepswe%3Av1.1.md) | 48.67% | Range 46.43–50.91% | 51 / 70 | $3.44 | 880.01s | [deepswe](https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_at_1` \| 0.48672566371681414 \| score_fraction \| scored_rollout_attempts \| Higher is better \| \| `pass_at_4` \| 0.7610619469026548 \| score_fraction \| tasks_with_one_passing_rollout \| Higher is better \| \| `cost_per_attempt` \| 3.4438571028761062 \| USD \| scored_attempt \| Lower is better \| \| `duration` \| 880.0083837986726 \| seconds \| scored_attempt \| Lower is better \| ### Configuration harness mini-swe-agent Reasoning effort medium sourceConfiguration mini_swe_agent_claude_opus_4_8_medium ### Reported statistics Uncertainty Reported interval: 46.43–50.91% interval [0.4643336050994396,0.5091177223341886] intervalMethod 95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R)) runCount 4 sampleSize 452 taskCount 113 ### Source [Original source](https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json) Source deepswe Original model label claude-opus-4-8 Observed 2026-10-22T03:50:05.889Z Evidence SHA-256 `a7c15d66288fd249c020b9931c017b92d1a3b90e480b3ff34974b752bd030019` Source locator `/rows/50` |  |  |  |  |  |  |  |
| [FrontierCode 1.1 extended](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Aextended.md) | 55.37% | — | 63 / 125 | $3.06 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.5537 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.6076 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 3.062 \| USD \| per_rollout \| Lower is better \| ### Configuration harness claude-code Reasoning effort medium sourceVersion v1_1 subset extended ### Reported statistics flaggedRate 0.004 sampleSize 150 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label Claude Opus 4.8 Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/Claude%20Opus%204.8/medium/extended` |  |  |  |  |  |  |  |
| [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 71.67% | — | 53 / 243 | 2.39usd per task | — | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.7167 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 2.3896 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup anthropic-opus-4-8 modelType CoT Reasoning effort medium sourceModelVersion anthropic-opus-4-8-medium thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label Claude Opus 4.8 (Medium) Source version v2 Observed 2026-10-22T05:20:04.306Z Evidence SHA-256 `4351eb696e78113b0459e9bb5f0258318b905efef34f473dcea51ce641b0d94d` Source locator `/evaluations/120` |  |  |  |  |  |  |  |
| [FrontierCode 1 main](https://benchize.com/benchmarks/frontiercode%3Av1%3Amain.md) | 26.89% | — | 9 / 39 | $3.3 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.2689 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.294 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 3.3 \| USD \| per_rollout \| Lower is better \| ### Configuration harness claude-code Reasoning effort medium sourceVersion v1 subset main ### Reported statistics flaggedRate Not reported sampleSize 100 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label Claude Opus 4.8 Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1/data/Claude%20Opus%204.8/medium/main` |  |  |  |  |  |  |  |
| [FrontierCode 1 extended](https://benchize.com/benchmarks/frontiercode%3Av1%3Aextended.md) | 45.49% | — | 9 / 39 | $2.74 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.4549 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.4947 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 2.7449 \| USD \| per_rollout \| Lower is better \| ### Configuration harness claude-code Reasoning effort medium sourceVersion v1 subset extended ### Reported statistics flaggedRate Not reported sampleSize 150 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label Claude Opus 4.8 Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1/data/Claude%20Opus%204.8/medium/extended` |  |  |  |  |  |  |  |
| [AutomationBench](https://benchize.com/benchmarks/zapier%3Aautomationbench.md) | 14% | — | 54 / 113 | $1.44 | — | [zapier](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 14 \| percent \| reported \| Higher is better \| \| `cost` \| 1.44 \| USD \| per_task \| Lower is better \| ### Configuration benchmarkVersion 1.0.6 costFootnote false Fallback policy Not reported Reasoning effort medium Model configuration Claude Opus 4.8 (Medium) thinkingEnabled true ### Reported statistics rank 58 ### Source [Original source](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) Source zapier Original model label Claude Opus 4.8 (Medium) Observed 2026-10-21T16:34:56.783Z Evidence SHA-256 `43978e38f018789fa59c11de5328abe9e5905bfa9a5a4d601fa3aa4d9c153b0d` Source locator `/rows/57` |  |  |  |  |  |  |  |
| [FrontierCode 1.1 main](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Amain.md) | 40.46% | — | 68 / 125 | $3.7 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.4046 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.4493 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 3.7029 \| USD \| per_rollout \| Lower is better \| ### Configuration harness claude-code Reasoning effort medium sourceVersion v1_1 subset main ### Reported statistics flaggedRate 0.005 sampleSize 100 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label Claude Opus 4.8 Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/Claude%20Opus%204.8/medium/main` |  |  |  |  |  |  |  |
| [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 91.5% | — | 61 / 245 | 0.91usd per task | — | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.915 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.9115 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup anthropic-opus-4-8 modelType CoT Reasoning effort medium sourceModelVersion anthropic-opus-4-8-medium thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label Claude Opus 4.8 (Medium) Source version v1 Observed 2026-10-22T05:20:04.066Z Evidence SHA-256 `2bf68d22dafba37047d07ad833ebc0e8199c9aa2f9eeaed50c75c1b704462836` Source locator `/evaluations/118` |  |  |  |  |  |  |  |

---
Cite as: Claude Opus 4.8Medium — Benchize, https://benchize.com/models/claude-opus-4-8-medium (retrieved 2026-10-22)