Single agent; web search/fetch; programmatic tool calling; context compaction at 50K; 10M total-token limit; max reasoning effort; thinking disabled.
未知项
Trial count and exact sampling settings for the Opus 4.5 row are not stated.
工具
允许工具
推理预算
max
框架
未记录
协议
BrowseComp; single-agent; web search/fetch and programmatic tool calling.
条件
50K context compaction; 10M total-token limit; max reasoning effort with thinking disabled. Kept distinct from the custom BrowseComp-Plus evaluation. 来源主文最初发布日期为2026-02-05,但当前HTML修改于2026-10-14;没有与此数值匹配的首发图像历史字节,因此精确首次公布日未知。
March 6 card correction; highest single-agent config, no thinking, max reasoning effort, compaction every 50K, 10M total-token cap. Main release table’s 84.0% is the rounded value; do not merge the separately evaluated 86.57% multi-agent result.
Orchestrator delegates to subagents; each subagent has 200K context; web search/fetch and programmatic tool calling; orchestrator compaction at 50K up to 1M total tokens; Max effort; thinking disabled。
未知项
与单代理基线不同,不作普通 effort 映射。
工具
允许工具
推理预算
max
框架
未记录
协议
BrowseComp;multi-agent;orchestrator/subagents。
条件
March 6 correction; 200K subagent context; web search/fetch, PTC; max effort, no thinking; 86.57 is not combined with single-agent results.。
System Card §8.1 standard configuration: adaptive thinking at max effort; default temperature/top_p; averaged over 5 trials. Context sizes are evaluation-dependent and do not exceed 1M tokens; retain all section-specific exceptions on their results.
未知项
Per-benchmark tools, context/token cap, resolution, trial count, harness and other exceptions are recorded on each result when stated.
工具
允许工具
推理预算
max
框架
未记录
协议
BrowseComp; web search, web fetch, programmatic tool calling and code execution.
条件
Thinking disabled; max effort; 10M total-token limit; context compaction triggered at 200K.
Single-agent BrowseComp with web search, web fetch, programmatic tool calling, and code execution; context compaction triggered at 200K; Opus 4.7 grader; card-wide default max effort.
未知项
未另记
工具
允许工具
推理预算
max
框架
未记录
协议
BrowseComp single-agent with web search, web fetch, programmatic tool calling, and code execution.
条件
90.8%; context compaction triggered at 200K tokens; Opus 4.7 grader; keep separate from the unreleased-effort budget sweep and the 10M fixed-budget effort sweep. Table 8.1.A additionally states default sampling settings, five trials, and evaluation-dependent context windows not exceeding 1M tokens; it does not state this row's per-task token budget.
Single-agent BrowseComp with web search, web fetch, programmatic tool calling, and code execution; context compaction triggered at 200K; per-task token budgets are recorded in each result protocol; the figure explicitly says the effort configuration was unreleased.
未知项
The effort level is not disclosed and is not inferred from token budget.
工具
允许工具
推理预算
未记录
框架
未记录
协议
BrowseComp single-agent; 1M-token task budget.
条件
The figure states Opus 5 used an unreleased effort configuration; no effort level is inferred from the budget.
Single-agent BrowseComp with web search, web fetch, programmatic tool calling, and code execution; context compaction triggered at 200K; per-task token budgets are recorded in each result protocol; the figure explicitly says the effort configuration was unreleased.
未知项
The effort level is not disclosed and is not inferred from token budget.
工具
允许工具
推理预算
未记录
框架
未记录
协议
BrowseComp single-agent; 3M-token task budget.
条件
The figure states Opus 5 used an unreleased effort configuration; no effort level is inferred from the budget.
Single-agent BrowseComp with web search, web fetch, programmatic tool calling, and code execution; context compaction triggered at 200K; per-task token budgets are recorded in each result protocol; the figure explicitly says the effort configuration was unreleased.
未知项
The effort level is not disclosed and is not inferred from token budget.
工具
允许工具
推理预算
未记录
框架
未记录
协议
BrowseComp single-agent; 10M-token task budget.
条件
The figure states Opus 5 used an unreleased effort configuration; no effort level is inferred from the budget.
Single-agent BrowseComp with web search, web fetch, programmatic tool calling, and code execution; context compaction triggered at 200K; fixed 10M-token budget; figure-labeled effort; billed API costs. Explicit adaptive-thinking effort: low.
未知项
The card does not state any additional sampling parameters beyond the cited evaluation description.
Single-agent BrowseComp with web search, web fetch, programmatic tool calling, and code execution; context compaction triggered at 200K; fixed 10M-token budget; figure-labeled effort; billed API costs. Explicit adaptive-thinking effort: medium.
未知项
The card does not state any additional sampling parameters beyond the cited evaluation description.
Single-agent BrowseComp with web search, web fetch, programmatic tool calling, and code execution; context compaction triggered at 200K; fixed 10M-token budget; figure-labeled effort; billed API costs. Explicit adaptive-thinking effort: high.
未知项
The card does not state any additional sampling parameters beyond the cited evaluation description.
Single-agent BrowseComp with web search, web fetch, programmatic tool calling, and code execution; context compaction triggered at 200K; fixed 10M-token budget; figure-labeled effort; billed API costs. Explicit adaptive-thinking effort: xhigh.
未知项
The card does not state any additional sampling parameters beyond the cited evaluation description.
Single-agent BrowseComp with web search, web fetch, programmatic tool calling, and code execution; context compaction triggered at 200K; fixed 10M-token budget; figure-labeled effort; billed API costs. Explicit adaptive-thinking effort: max.
未知项
The card does not state any additional sampling parameters beyond the cited evaluation description.
Differences are calculated only for unique, active, exact values between direct predecessors when the unit, metric, and explicitly recorded configuration and conditions match.
· 1 score record for this release, including 1 exact value (may include historical records)
Claude Opus 4.5 · BrowseComp scores and configurations
Metric and score
Configuration and evaluation conditions
Sources
Accuracy67.8%Reported 67.8% · Unit %
Published Unconfirmed
BrowseComp · comparison article · no thinking
Settings
Single agent; web search/fetch; programmatic tool calling; context compaction at 50K; 10M total-token limit; max reasoning effort; thinking disabled.
Unknowns
Trial count and exact sampling settings for the Opus 4.5 row are not stated.
Tools
Tools allowed
Reasoning budget
max
Framework
not recorded
Protocol
BrowseComp; single-agent; web search/fetch and programmatic tool calling.
Conditions
50K context compaction; 10M total-token limit; max reasoning effort with thinking disabled. Kept distinct from the custom BrowseComp-Plus evaluation. 来源主文最初发布日期为2026-02-05,但当前HTML修改于2026-10-14;没有与此数值匹配的首发图像历史字节,因此精确首次公布日未知。
March 6 card correction; highest single-agent config, no thinking, max reasoning effort, compaction every 50K, 10M total-token cap. Main release table’s 84.0% is the rounded value; do not merge the separately evaluated 86.57% multi-agent result.
Orchestrator delegates to subagents; each subagent has 200K context; web search/fetch and programmatic tool calling; orchestrator compaction at 50K up to 1M total tokens; Max effort; thinking disabled。
Unknowns
与单代理基线不同,不作普通 effort 映射。
Tools
Tools allowed
Reasoning budget
max
Framework
not recorded
Protocol
BrowseComp;multi-agent;orchestrator/subagents。
Conditions
March 6 correction; 200K subagent context; web search/fetch, PTC; max effort, no thinking; 86.57 is not combined with single-agent results.。
· 1 score record for this release, including 1 exact value (may include historical records)
Records for the direct predecessor do not provide matching conditions for a valid difference.
Claude Opus 4.7 · BrowseComp scores and configurations
Metric and score
Configuration and evaluation conditions
Sources
Accuracy79.3%Reported 79.3% · Unit %
Published Unconfirmed
发布表报告值
Settings
System Card §8.1 standard configuration: adaptive thinking at max effort; default temperature/top_p; averaged over 5 trials. Context sizes are evaluation-dependent and do not exceed 1M tokens; retain all section-specific exceptions on their results.
Unknowns
Per-benchmark tools, context/token cap, resolution, trial count, harness and other exceptions are recorded on each result when stated.
Tools
Tools allowed
Reasoning budget
max
Framework
not recorded
Protocol
BrowseComp; web search, web fetch, programmatic tool calling and code execution.
Conditions
Thinking disabled; max effort; 10M total-token limit; context compaction triggered at 200K.
· 9 score records for this release, including 9 exact values (may include historical records)
Records for the direct predecessor do not provide matching conditions for a valid difference.
Claude Opus 5 · BrowseComp scores and configurations
Metric and score
Configuration and evaluation conditions
Sources
Accuracy90.8%Reported 90.8% · Unit %
Published Unconfirmed
BrowseComp · max effort
Settings
Single-agent BrowseComp with web search, web fetch, programmatic tool calling, and code execution; context compaction triggered at 200K; Opus 4.7 grader; card-wide default max effort.
Unknowns
none recorded
Tools
Tools allowed
Reasoning budget
max
Framework
not recorded
Protocol
BrowseComp single-agent with web search, web fetch, programmatic tool calling, and code execution.
Conditions
90.8%; context compaction triggered at 200K tokens; Opus 4.7 grader; keep separate from the unreleased-effort budget sweep and the 10M fixed-budget effort sweep. Table 8.1.A additionally states default sampling settings, five trials, and evaluation-dependent context windows not exceeding 1M tokens; it does not state this row's per-task token budget.
Single-agent BrowseComp with web search, web fetch, programmatic tool calling, and code execution; context compaction triggered at 200K; per-task token budgets are recorded in each result protocol; the figure explicitly says the effort configuration was unreleased.
Unknowns
The effort level is not disclosed and is not inferred from token budget.
Tools
Tools allowed
Reasoning budget
not recorded
Framework
not recorded
Protocol
BrowseComp single-agent; 1M-token task budget.
Conditions
The figure states Opus 5 used an unreleased effort configuration; no effort level is inferred from the budget.
Single-agent BrowseComp with web search, web fetch, programmatic tool calling, and code execution; context compaction triggered at 200K; per-task token budgets are recorded in each result protocol; the figure explicitly says the effort configuration was unreleased.
Unknowns
The effort level is not disclosed and is not inferred from token budget.
Tools
Tools allowed
Reasoning budget
not recorded
Framework
not recorded
Protocol
BrowseComp single-agent; 3M-token task budget.
Conditions
The figure states Opus 5 used an unreleased effort configuration; no effort level is inferred from the budget.
Single-agent BrowseComp with web search, web fetch, programmatic tool calling, and code execution; context compaction triggered at 200K; per-task token budgets are recorded in each result protocol; the figure explicitly says the effort configuration was unreleased.
Unknowns
The effort level is not disclosed and is not inferred from token budget.
Tools
Tools allowed
Reasoning budget
not recorded
Framework
not recorded
Protocol
BrowseComp single-agent; 10M-token task budget.
Conditions
The figure states Opus 5 used an unreleased effort configuration; no effort level is inferred from the budget.
Single-agent BrowseComp with web search, web fetch, programmatic tool calling, and code execution; context compaction triggered at 200K; fixed 10M-token budget; figure-labeled effort; billed API costs. Explicit adaptive-thinking effort: low.
Unknowns
The card does not state any additional sampling parameters beyond the cited evaluation description.
Single-agent BrowseComp with web search, web fetch, programmatic tool calling, and code execution; context compaction triggered at 200K; fixed 10M-token budget; figure-labeled effort; billed API costs. Explicit adaptive-thinking effort: medium.
Unknowns
The card does not state any additional sampling parameters beyond the cited evaluation description.
Single-agent BrowseComp with web search, web fetch, programmatic tool calling, and code execution; context compaction triggered at 200K; fixed 10M-token budget; figure-labeled effort; billed API costs. Explicit adaptive-thinking effort: high.
Unknowns
The card does not state any additional sampling parameters beyond the cited evaluation description.
Single-agent BrowseComp with web search, web fetch, programmatic tool calling, and code execution; context compaction triggered at 200K; fixed 10M-token budget; figure-labeled effort; billed API costs. Explicit adaptive-thinking effort: xhigh.
Unknowns
The card does not state any additional sampling parameters beyond the cited evaluation description.
Single-agent BrowseComp with web search, web fetch, programmatic tool calling, and code execution; context compaction triggered at 200K; fixed 10M-token budget; figure-labeled effort; billed API costs. Explicit adaptive-thinking effort: max.
Unknowns
The card does not state any additional sampling parameters beyond the cited evaluation description.