# Claude Opus 5Medium

> Source: Benchize (https://benchize.com) — https://benchize.com/models/claude-opus-5-medium. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/claude-opus-5-medium.

Anthropic

Canonical URL: https://benchize.com/models/claude-opus-5-medium
Last updated: Thu, 22 Oct 2026 05:30:58 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 |  |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [FrontierCode 1.1 extended](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Aextended.md) | 63.63% | — | 7 / 125 | $3.51 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.6363 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.6963 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 3.511 \| 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 5 Observed 2026-10-21T16:31:00.878Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/Claude%20Opus%205/medium/extended` |  |  |  |  |  |  |  |
| [AutomationBench](https://benchize.com/benchmarks/zapier%3Aautomationbench.md) | 23.9% | — | 30 / 113 | $0.89 | — | [zapier](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 23.9 \| percent \| reported \| Higher is better \| \| `cost` \| 0.89 \| USD \| per_task \| Lower is better \| ### Configuration benchmarkVersion 1.0.6 costFootnote false Fallback policy Not reported Reasoning effort medium Model configuration Claude Opus 5 (Medium) thinkingEnabled true ### Reported statistics rank 30 ### Source [Original source](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) Source zapier Original model label Claude Opus 5 (Medium) Observed 2026-10-21T16:34:56.783Z Evidence SHA-256 `43978e38f018789fa59c11de5328abe9e5905bfa9a5a4d601fa3aa4d9c153b0d` Source locator `/rows/29` |  |  |  |  |  |  |  |
| [FrontierCode 1.1 main](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Amain.md) | 53.38% | — | 5 / 125 | $4.31 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.5338 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.5885 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 4.3127 \| USD \| per_rollout \| Lower is better \| ### Configuration harness claude-code Reasoning effort medium sourceVersion v1_1 subset main ### Reported statistics flaggedRate 0.006 sampleSize 100 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label Claude Opus 5 Observed 2026-10-21T16:31:00.878Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/Claude%20Opus%205/medium/main` |  |  |  |  |  |  |  |
| [DeepSWE](https://benchize.com/benchmarks/deepswe%3Av1.1.md) | 68.9% | Range 67.73–70.08% | 17 / 70 | $3.29 | 759.23s | [deepswe](https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_at_1` \| 0.6890380313199105 \| score_fraction \| scored_rollout_attempts \| Higher is better \| \| `pass_at_4` \| 0.8938053097345132 \| score_fraction \| tasks_with_one_passing_rollout \| Higher is better \| \| `cost_per_attempt` \| 3.28978764541387 \| USD \| scored_attempt \| Lower is better \| \| `duration` \| 759.2254874630873 \| seconds \| scored_attempt \| Lower is better \| ### Configuration harness mini-swe-agent Reasoning effort medium sourceConfiguration mini_swe_agent_claude_opus_5_medium ### Reported statistics Uncertainty Reported interval: 67.73–70.08% interval [0.6773124446609795,0.7007636179788415] intervalMethod 95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R)) runCount 4 sampleSize 447 taskCount 113 ### Source [Original source](https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json) Source deepswe Original model label claude-opus-5 Observed 2026-10-22T03:50:05.889Z Evidence SHA-256 `a7c15d66288fd249c020b9931c017b92d1a3b90e480b3ff34974b752bd030019` Source locator `/rows/16` |  |  |  |  |  |  |  |

---
Cite as: Claude Opus 5Medium — Benchize, https://benchize.com/models/claude-opus-5-medium (retrieved 2026-10-22)