# Claude 3 Opus > Source: Benchize (https://benchize.com) — https://benchize.com/models/claude-3-opus. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/claude-3-opus. Anthropic Canonical URL: https://benchize.com/models/claude-3-opus Last updated: Wed, 21 Oct 2026 18:52:20 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Anthropic ## Benchmarks | Benchmark | Score | ± | Rank | Source | | | --- | --- | --- | --- | --- | --- | | [Humanity's Last Exam Text Only (Preview)](https://benchize.com/benchmarks/scale%3Ahumanitys_last_exam_text_only_preview.md) | 3.97source score | CI 3.18–4.76 | 8 / 9 | [scale](https://labs.scale.com/leaderboard/humanitys_last_exam_text_only_preview) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 3.97 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude 3 Opus sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 3.18–4.76 contaminationWarning Not reported rank 23 reportedConfidenceHalfWidth 0.79 ### Source [Original source](https://labs.scale.com/leaderboard/humanitys_last_exam_text_only_preview) Source scale Original model label Claude 3 Opus Observed 2026-10-21T16:35:41.566Z Evidence SHA-256 `4d23bf746c160370d6a729032cb829dd9d2b40f12bad31ca5723d121464988b7` Source locator `/rows/22` | | | | | | | [Humanity's Last Exam (Preview)](https://benchize.com/benchmarks/scale%3Ahumanitys_last_exam_preview.md) | 4.19source score | CI 3.43–4.95 | 5 / 6 | [scale](https://labs.scale.com/leaderboard/humanitys_last_exam_preview) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 4.19 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude 3 Opus sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 3.43–4.95 contaminationWarning Not reported rank 18 reportedConfidenceHalfWidth 0.76 ### Source [Original source](https://labs.scale.com/leaderboard/humanitys_last_exam_preview) Source scale Original model label Claude 3 Opus Observed 2026-10-21T16:35:41.114Z Evidence SHA-256 `cc993dfe2ce4fc1640be10f28c7c8ab5c1db9071f780ac20ed11dd4f026105a5` Source locator `/rows/17` | | | | | | | [Korean](https://benchize.com/benchmarks/scale%3Akorean.md) | 52.78source score | CI 47.01–58.55 | 4 / 8 | [scale](https://labs.scale.com/leaderboard/korean) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 52.78 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude 3 Opus sourceModelVersion claude-3-opus-20240229 thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 47.01–58.55 contaminationWarning Not reported rank 11 reportedConfidenceHalfWidth 5.77 ### Source [Original source](https://labs.scale.com/leaderboard/korean) Source scale Original model label Claude 3 Opus Observed 2026-10-21T16:35:44.172Z Evidence SHA-256 `e1846e496288a3d1d0a49f645276e266d451f5bb5704de0e8e1a771e011f803b` Source locator `/rows/10` | | | | | | | [SimpleBench](https://benchize.com/benchmarks/simplebench%3Aavg-at-5.md) | 23.5% | — | 54 / 62 | [simplebench](https://simple-bench.com/static/js/leaderboard-data.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 23.5 \| percent \| average_at_5 \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude 3 Opus thinkingEnabled Not reported ### Reported statistics rank 92nd ### Source [Original source](https://simple-bench.com/static/js/leaderboard-data.js) Source simplebench Original model label Claude 3 Opus Observed 2026-10-21T16:32:13.183Z Evidence SHA-256 `b2d0285ad3e4e15750ed20d39897e7558d1c05e8962e90c861b06f93c8019dc9` Source locator `/rows/93` | | | | | | | [SWE-bench Lite](https://benchize.com/benchmarks/swe-bench%3Alite.md) | 11.67% | — | 21 / 22 | [SWE-bench](https://www.swebench.com/) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `resolved` \| 11.67 \| percent \| lite \| Higher is better \| ### Configuration agent SWE-agent agentOrganization SWE-agent models Not reported Reasoning effort Not reported sourceSubmission 20240402_sweagent_claude3opus subset Lite system Not reported ### Source [Original source](https://www.swebench.com/) Source SWE-bench Original model label Claude 3 Opus Observed 2026-10-21T14:54:06.913Z Evidence SHA-256 `c862011a4ee1d1a7199fad6ca0905fa5c64f58216f7217ac1eddf37f28788433` Source locator `/leaderboard-data/3/results/77` | | | | | | | [Coding](https://benchize.com/benchmarks/scale%3Acoding.md) | 959source score | CI 933–985 | 5 / 8 | [scale](https://labs.scale.com/leaderboard/coding) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 959 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude 3 Opus sourceModelVersion claude-3-opus-20240229 thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 933–985 contaminationWarning Not reported rank 21 reportedConfidenceHalfWidth 26 ### Source [Original source](https://labs.scale.com/leaderboard/coding) Source scale Original model label Claude 3 Opus Observed 2026-10-21T16:35:43.120Z Evidence SHA-256 `0c9ec6a10c453ad3d004b54cea41d9957b4739308340858336bbff82141ff309` Source locator `/rows/20` | | | | | | | [Adversarial Robustness](https://benchize.com/benchmarks/scale%3Aadversarial_robustness.md) | 13source score | CI 4–22 | 4 / 4 | [scale](https://labs.scale.com/leaderboard/adversarial_robustness) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 13 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude 3 Opus sourceModelVersion claude-3-opus-20240229 thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 4–22 contaminationWarning Not reported rank 3 reportedConfidenceHalfWidth 9 ### Source [Original source](https://labs.scale.com/leaderboard/adversarial_robustness) Source scale Original model label Claude 3 Opus Observed 2026-10-21T16:35:39.820Z Evidence SHA-256 `9ad617f4026dbd8729d7a28d03eca7818e4f0f6e7e03675760b4a0d2f1ab8f47` Source locator `/rows/2` | | | | | | | [Math](https://benchize.com/benchmarks/scale%3Amath.md) | 95.19source score | CI 93.98–96.4 | 1 / 5 | [scale](https://labs.scale.com/leaderboard/math) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 95.19 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude 3 Opus sourceModelVersion claude-3-opus-20240229 thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 93.98–96.4 contaminationWarning Not reported rank 4 reportedConfidenceHalfWidth 1.21 ### Source [Original source](https://labs.scale.com/leaderboard/math) Source scale Original model label Claude 3 Opus Observed 2026-10-21T16:35:44.522Z Evidence SHA-256 `9733a9f093382f55ad8f743d72cbdefe7c68699b651a4c4344e87489642a779d` Source locator `/rows/3` | | | | | | | [SWE-bench Lite](https://benchize.com/benchmarks/swe-bench%3Alite.md) | 4.33% | — | 22 / 22 | [SWE-bench](https://www.swebench.com/) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `resolved` \| 4.33 \| percent \| lite \| Higher is better \| ### Configuration agent RAG baseline agentOrganization Not reported models ["claude-3-opus-20240229"] Reasoning effort Not reported sourceSubmission 20240402_rag_claude3opus subset Lite system Not reported ### Source [Original source](https://www.swebench.com/) Source SWE-bench Original model label Claude 3 Opus Observed 2026-10-21T14:54:06.913Z Evidence SHA-256 `c862011a4ee1d1a7199fad6ca0905fa5c64f58216f7217ac1eddf37f28788433` Source locator `/leaderboard-data/3/results/78` | | | | | | | [SWE-bench Verified](https://benchize.com/benchmarks/swe-bench%3Averified.md) | 15.8% | — | 60 / 63 | [SWE-bench](https://www.swebench.com/) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `resolved` \| 15.8 \| percent \| verified \| Higher is better \| ### Configuration agent SWE-agent agentOrganization SWE-agent models ["claude-3-opus-20240229"] Reasoning effort Not reported sourceSubmission 20240402_sweagent_claude3opus subset Verified system ["System: Attempts - 1"] ### Source [Original source](https://www.swebench.com/) Source SWE-bench Original model label Claude 3 Opus Observed 2026-10-21T14:54:06.913Z Evidence SHA-256 `c862011a4ee1d1a7199fad6ca0905fa5c64f58216f7217ac1eddf37f28788433` Source locator `/leaderboard-data/2/results/169` | | | | | | | [Spanish](https://benchize.com/benchmarks/scale%3Aspanish.md) | 919source score | CI 897–941 | 5 / 5 | [scale](https://labs.scale.com/leaderboard/spanish) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 919 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude 3 Opus sourceModelVersion claude-3-opus-20240229 thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 897–941 contaminationWarning Not reported rank 21 reportedConfidenceHalfWidth 22 ### Source [Original source](https://labs.scale.com/leaderboard/spanish) Source scale Original model label Claude 3 Opus Observed 2026-10-21T16:35:44.884Z Evidence SHA-256 `20dbd29f5dee622033d82f3adac6f1fd3067ca0737ea686c945855c6ce1c38ac` Source locator `/rows/20` | | | | | | | [VISTA](https://benchize.com/benchmarks/scale%3Avisual_language_understanding.md) | 27.82source score | CI 27.27–28.37 | 14 / 16 | [scale](https://labs.scale.com/leaderboard/visual_language_understanding) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 27.82 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude 3 Opus sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 27.27–28.37 contaminationWarning Not reported rank 56 reportedConfidenceHalfWidth 0.55 ### Source [Original source](https://labs.scale.com/leaderboard/visual_language_understanding) Source scale Original model label Claude 3 Opus Observed 2026-10-21T16:35:38.974Z Evidence SHA-256 `469e2d64808796dc35f1a8b8b0abe7daefeb7c5ee06fa9b6ba8b34c42d4b19b5` Source locator `/rows/55` | | | | | | | [MASK](https://benchize.com/benchmarks/scale%3Amask.md) | 79source score | CI 77.69–80.31 | 8 / 25 | [scale](https://labs.scale.com/leaderboard/mask) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 79 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude 3 Opus sourceModelVersion claude-3-opus-20240229 thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 77.69–80.31 contaminationWarning Not reported rank 26 reportedConfidenceHalfWidth 1.31 ### Source [Original source](https://labs.scale.com/leaderboard/mask) Source scale Original model label Claude 3 Opus Observed 2026-10-21T16:35:38.046Z Evidence SHA-256 `506198f10b9789b267cc2a11dcdfedc27067703da430d78b374b2c5dffb8ec7d` Source locator `/rows/25` | | | | | | | [SWE-bench Test](https://benchize.com/benchmarks/swe-bench%3Atest.md) | 3.79% | — | 4 / 4 | [SWE-bench](https://www.swebench.com/) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `resolved` \| 3.79 \| percent \| test \| Higher is better \| ### Configuration agent RAG baseline agentOrganization Not reported models ["claude-3-opus-20240229"] Reasoning effort Not reported sourceSubmission 20240402_rag_claude3opus subset Test system ["System: Attempts - 1"] ### Source [Original source](https://www.swebench.com/) Source SWE-bench Original model label Claude 3 Opus Observed 2026-10-21T14:54:06.913Z Evidence SHA-256 `c862011a4ee1d1a7199fad6ca0905fa5c64f58216f7217ac1eddf37f28788433` Source locator `/leaderboard-data/1/results/18` | | | | | | | [SWE-bench Test](https://benchize.com/benchmarks/swe-bench%3Atest.md) | 10.51% | — | 3 / 4 | [SWE-bench](https://www.swebench.com/) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `resolved` \| 10.51 \| percent \| test \| Higher is better \| ### Configuration agent SWE-agent agentOrganization SWE-agent models ["claude-3-opus-20240229"] Reasoning effort Not reported sourceSubmission 20240402_sweagent_claude3opus subset Test system ["System: Attempts - 1"] ### Source [Original source](https://www.swebench.com/) Source SWE-bench Original model label Claude 3 Opus Observed 2026-10-21T14:54:06.913Z Evidence SHA-256 `c862011a4ee1d1a7199fad6ca0905fa5c64f58216f7217ac1eddf37f28788433` Source locator `/leaderboard-data/1/results/17` | | | | | | | [Agentic Tool Use (Chat)](https://benchize.com/benchmarks/scale%3Atool_use_chat.md) | 48.49source score | CI 41.53–55.45 | 5 / 11 | [scale](https://labs.scale.com/leaderboard/tool_use_chat) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 48.49 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude 3 Opus sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 41.53–55.45 contaminationWarning Not reported rank 23 reportedConfidenceHalfWidth 6.96 ### Source [Original source](https://labs.scale.com/leaderboard/tool_use_chat) Source scale Original model label Claude 3 Opus Observed 2026-10-21T16:35:40.196Z Evidence SHA-256 `53ee3ef4e3efd7d807b9d93d3755560597812d218b9beb4b3ca98b8752d70590` Source locator `/rows/22` | | | | | | | [Instruction Following](https://benchize.com/benchmarks/scale%3Ainstruction_following.md) | 80.12source score | CI 78.58–81.66 | 3 / 4 | [scale](https://labs.scale.com/leaderboard/instruction_following) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 80.12 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude 3 Opus sourceModelVersion claude-3-opus-20240229 thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 78.58–81.66 contaminationWarning Not reported rank 16 reportedConfidenceHalfWidth 1.54 ### Source [Original source](https://labs.scale.com/leaderboard/instruction_following) Source scale Original model label Claude 3 Opus Observed 2026-10-21T16:35:41.991Z Evidence SHA-256 `2c7dbe83fd053bd9116743dda0283e16adc2d63e4ae4b62d23fc991f6772ff2f` Source locator `/rows/15` | | | | | | | [Agentic Tool Use (Enterprise)](https://benchize.com/benchmarks/scale%3Atool_use_enterprise.md) | 52.78source score | CI 47.01–58.55 | 7 / 11 | [scale](https://labs.scale.com/leaderboard/tool_use_enterprise) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 52.78 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude 3 Opus sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 47.01–58.55 contaminationWarning Not reported rank 24 reportedConfidenceHalfWidth 5.77 ### Source [Original source](https://labs.scale.com/leaderboard/tool_use_enterprise) Source scale Original model label Claude 3 Opus Observed 2026-10-21T16:35:40.753Z Evidence SHA-256 `fbc7110acd9299aeb97bd56cddab6949bfbd09b2f3e01ee6edfa7f7df8cee3a8` Source locator `/rows/23` | | | | | | | [SWE-bench Verified](https://benchize.com/benchmarks/swe-bench%3Averified.md) | 7% | — | 63 / 63 | [SWE-bench](https://www.swebench.com/) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `resolved` \| 7 \| percent \| verified \| Higher is better \| ### Configuration agent RAG baseline agentOrganization Not reported models ["claude-3-opus-20240229"] Reasoning effort Not reported sourceSubmission 20240402_rag_claude3opus subset Verified system ["System: Attempts - 2+"] ### Source [Original source](https://www.swebench.com/) Source SWE-bench Original model label Claude 3 Opus Observed 2026-10-21T14:54:06.913Z Evidence SHA-256 `c862011a4ee1d1a7199fad6ca0905fa5c64f58216f7217ac1eddf37f28788433` Source locator `/leaderboard-data/2/results/174` | | | | | | --- Cite as: Claude 3 Opus — Benchize, https://benchize.com/models/claude-3-opus (retrieved 2026-10-21)