Benchmark Almanac

WISER-Search

o4 mini / Prll Search MCP 82.1% tops its leaderboard
Not in model cards
Version search

Web research agents answer fresh and business questions that require current sources, multi-hop search, and evidence synthesis.

The composite contains 76 WISER-Fresh questions and 120 WISER-Atomic questions. Parallel reports twelve model and search combinations from four language models, with accuracy from 56.12% to 82.14%.

Released
July 2025
Kind
Deep research
Level
Expert
Scored
Graded by a model
Answers
Agent task
Tasks
Public, plus a private test set
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Agentic
Environment
Browser, APIs and tools
Items from
Real work and use
Refresh
One fixed set
Run by
A host
12
Entries on its own leaderboard, 0 models we track

o4 mini / Prll Search MCP tops the leaderboard with 82.1%

Best score per entry from the benchmark's own leaderboard, read on November 21st, 2026. Answer accuracy on the blended WISER-Fresh and WISER-Atomic test set Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

  1. 1 o4 mini / Prll Search MCP 82.1%
  2. 2 o3 / Prll Search MCP 80.6%
  3. 3 o3 w/ Native Search 79.1%
  4. 4 sonnet 4 / Prll Search MCP 78.6%
  5. 5 o4 mini w/ Native Search 77.5%
  6. 6 GPT 4.1 w/ Prll Search MCP 74.9%
  7. 7 GPT 4.1 w/ Native Search 68.9%
  8. 8 sonnet 4 w/ Native Search 68.8%
  9. 9 sonnet 4 w/ Exa Search MCP 67.1%
  10. 10 o4 mini w/ Exa Search MCP 61.7%
  11. 11 GPT 4.1 w/ Exa Search MCP 58.7%
  12. 12 o3 w/ Exa Search MCP 56.1%

Source: Official WISER-Search leaderboard

#EntryScoreSettingDateSource
1 o4 mini / Prll Search MCP 82.1% Official leaderboard
2 o3 / Prll Search MCP 80.6% Official leaderboard
3 o3 w/ Native Search 79.1% Official leaderboard
4 sonnet 4 / Prll Search MCP 78.6% Official leaderboard
5 o4 mini w/ Native Search 77.5% Official leaderboard
6 GPT 4.1 w/ Prll Search MCP 74.9% Official leaderboard
7 GPT 4.1 w/ Native Search 68.9% Official leaderboard
8 sonnet 4 w/ Native Search 68.8% Official leaderboard
9 sonnet 4 w/ Exa Search MCP 67.1% Official leaderboard
10 o4 mini w/ Exa Search MCP 61.7% Official leaderboard
11 GPT 4.1 w/ Exa Search MCP 58.7% Official leaderboard
12 o3 w/ Exa Search MCP 56.1% Official leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

Versions

More in Tool use

All 265 in Tool use
  • AutomationBench In use Agent completes end-to-end business workflows inside a simulated company exposing dozens of REST APIs. Graded on resulting state. Gemini 4 Neon 56.3%
  • MCP Atlas In use Multi-step workflows over real MCP servers. Scores tool-use competency on realistic tasks. Gemini 4 Argon 90.7%
  • BFCL V4 In use Models call functions and tools, including multi-turn agentic tasks with web search and memory. Checked against expected calls and outcomes. Qwen3.7-Max 75%
  • τ³-bench Banking In use Agents act as banking customer-service reps over many turns with a simulated user, following policy. Pass^1 on the final database state. Qwen 3.8 Max 55.1%
  • Toolathlon-Verified In use 108 long-horizon tasks across 32 apps through about 600 MCP tools. Execution-based checkers inspect final environment state. GLM-5.3-Flash 78.4%
  • DeepSearchQA In use Questions that need multi-step search and synthesis. Final answers graded against references. Kimi K3 95%

Data audit

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access Public tasks, plus a private test set.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (12 entries).
  • Pass Models scored 12 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom No scores yet.
Leaderboard import 3 pass
  • Pass Importer We read the board on parallel.ai: 12 entries at the last read, none a model we track.
  • Pass Last read November 21st, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check