Public Artificial Intelligence Benchmark Records Database
BrowseComp
Versions / Variants
| Version or Variant | Reference | Status | Records |
|---|---|---|---|
| Context-folding strategy | browsecomp/context-folding | ACTIVE | 1 |
| Unspecified | browsecomp/default | ACTIVE | 5 |
| Discard-all strategy | browsecomp/discard-all | ACTIVE | 1 |
| Multi-agent | browsecomp/multi-agent | ACTIVE | 1 |
| Single-agent | browsecomp/single-agent | ACTIVE | 1 |
Table may be scrolled horizontally on narrow displays.
| Record No. | Model | Benchmark | Metric | Score | Eval Date | Source | Model ID |
|---|---|---|---|---|---|---|---|
BR-00155-002 |
GPT-5.5 | BrowseComp | Overall | 84.4 | Unknown | Primary source | OPNAI-55 |
BR-002O47-006 |
Claude Opus 4.7 | BrowseComp | Overall | 79.3% | Unknown | Primary source | ANTHR-O47 |
BR-002O48-005 |
Claude Opus 4.8 | BrowseComp Single-agent | Overall | 84.3 | Unknown | Primary source | ANTHR-O48 |
BR-002O48-006 |
Claude Opus 4.8 | BrowseComp Multi-agent | Overall | 88.5 | Unknown | Primary source | ANTHR-O48 |
BR-00331P-015 |
Gemini 3.1 Pro | BrowseComp | Overall | 85.9% | Unknown | Primary source | GOOGL-G31P |
BR-00735-022 |
Qwen3.5-397B-A17B | BrowseComp Context-folding strategy | Overall | 69.0 | Unknown | Primary source | QWEN-35 |
BR-00735-023 |
Qwen3.5-397B-A17B | BrowseComp Discard-all strategy | Overall | 78.6 | Unknown | Primary source | QWEN-35 |
BR-008V4FLASH-018 |
DeepSeek V4-Flash | BrowseComp | Pass@1 | 73.2 | Unknown | Primary source | DPSK-V4FLASH |
BR-008V4PRO-018 |
DeepSeek V4-Pro | BrowseComp | Pass@1 | 83.4 | Unknown | Primary source | DPSK-V4PRO |
Showing records 1–9 of 9
Page 1 of 1