| 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.
| View this score in rankings |
|---|
| Accuracy86.8%Reported 86.8% · Unit % Published Unconfirmed | BrowseComp · token-budget sweep, unreleased effort- Settings
- 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.
| |
|---|
| Accuracy89.8%Reported 89.8% · Unit % Published Unconfirmed | BrowseComp · token-budget sweep, unreleased effort- Settings
- 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.
| |
|---|
| Accuracy90.2%Reported 90.2% · Unit % Published Unconfirmed | BrowseComp · token-budget sweep, unreleased effort- Settings
- 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.
| |
|---|
| Accuracy84.4%Reported 84.4% · Unit % Published Unconfirmed | BrowseComp · 10M-token budget · Low effort- Settings
- 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.
- Tools
- Tools allowed
- Reasoning budget
- low
- Framework
- not recorded
- Protocol
- BrowseComp single-agent; 10M-token task budget; effort scaling.
- Conditions
- Explicit effort labels from Figure 8.10.2.B; web tools and 200K-triggered context compaction described in §8.10.2.
| View this score in rankings |
|---|
| Accuracy88.9%Reported 88.9% · Unit % Published Unconfirmed | BrowseComp · 10M-token budget · Medium effort- Settings
- 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.
- Tools
- Tools allowed
- Reasoning budget
- medium
- Framework
- not recorded
- Protocol
- BrowseComp single-agent; 10M-token task budget; effort scaling.
- Conditions
- Explicit effort labels from Figure 8.10.2.B; web tools and 200K-triggered context compaction described in §8.10.2.
| View this score in rankings |
|---|
| Accuracy90.2%Reported 90.2% · Unit % Published Unconfirmed | BrowseComp · 10M-token budget · High effort- Settings
- 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.
- Tools
- Tools allowed
- Reasoning budget
- high
- Framework
- not recorded
- Protocol
- BrowseComp single-agent; 10M-token task budget; effort scaling.
- Conditions
- Explicit effort labels from Figure 8.10.2.B; web tools and 200K-triggered context compaction described in §8.10.2.
| View this score in rankings |
|---|
| Accuracy90.7%Reported 90.7% · Unit % Published Unconfirmed | BrowseComp · 10M-token budget · Xhigh effort- Settings
- 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.
- Tools
- Tools allowed
- Reasoning budget
- xhigh
- Framework
- not recorded
- Protocol
- BrowseComp single-agent; 10M-token task budget; effort scaling.
- Conditions
- Explicit effort labels from Figure 8.10.2.B; web tools and 200K-triggered context compaction described in §8.10.2.
| View this score in rankings |
|---|
| Accuracy90.8%Reported 90.8% · Unit % Published Unconfirmed | BrowseComp · 10M-token budget · Max effort- Settings
- 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.
- Tools
- Tools allowed
- Reasoning budget
- max
- Framework
- not recorded
- Protocol
- BrowseComp single-agent; 10M-token task budget; effort scaling.
- Conditions
- Explicit effort labels from Figure 8.10.2.B; web tools and 200K-triggered context compaction described in §8.10.2.
| View this score in rankings |
|---|