Benchmark Almanac

WISER-Atomic

Core 77% tops its leaderboard o3 69% leads the models we track
Not in model cards
Version atomic

Web research systems answer 121 customer-inspired questions across finance, sales, recruitment, and other domains.

The benchmark has 50% multi-hop questions and 50% single-hop questions. Parallel reports results for eleven model or processor configurations and uses a proprietary evaluator against verified answers.

Released
April 2025
Kind
Deep research
Level
Expert
Scored
Graded by a model
Answers
Agent task
Tasks
Kept private
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
Strongest model tested
o3 #84 on the capability index
Last model added
September 2025
Scores refreshed
November 21st, 2026
10
Entries on its own leaderboard, 6 models we track

Core tops the leaderboard with 77% o3 leads with 69% among models released by September 2025

Best score per entry from the benchmark's own leaderboard, read on November 21st, 2026. Answer accuracy on 121 customer-inspired web-research questions 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. The best model we track is o3, at 69%. This view shows only models we track, each at its best.

The newest model with a score here came out in September 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Core 77%
  2. 2 Base 75%
  3. 3 o3 69%
  4. 4 o4-mini low 68%
  5. 5 Lite 64%
  6. 6 Sonar Pro high 64%
  7. 7 4.1 mini low 63%
  8. 8 Gemini 2.5 Pro Jun 2025 56%
  9. 9 Gemini 2.5 Flash Sep 2025 53%
  10. 10 sonar low 48%

Source: Official WISER-Atomic leaderboard

#EntryScoreSettingDateSource
1 Core 77% Official leaderboard
2 Base 75% Official leaderboard
3 o3 69% Apr 2025 Official leaderboard
4 o4-mini 68% low Apr 2025 Official leaderboard
5 Lite 64% Official leaderboard
6 Sonar Pro 64% high Jan 2025 Official leaderboard
7 4.1 mini low 63% Official leaderboard
8 Gemini 2.5 Pro Jun 2025 56% Jun 2025 Official leaderboard
9 Gemini 2.5 Flash Sep 2025 53% Sep 2025 Official leaderboard
10 sonar 48% low Jan 2025 Official leaderboard
#ModelScoreSettingDateSource
1 o3 69% Apr 2025 Official leaderboard
2 o4-mini 68% low Apr 2025 Official leaderboard
3 Sonar Pro 64% high Jan 2025 Official leaderboard
4 Gemini 2.5 Pro Jun 2025 56% Jun 2025 Official leaderboard
5 Gemini 2.5 Flash Sep 2025 53% Sep 2025 Official leaderboard
6 sonar 48% low Jan 2025 Official leaderboard

2 models have held number one on the official leaderboard since its release in April 2025

Lab claims count from the day the card came out, independent runs from the model’s release.

Perplexity OpenAI
Own leaderboard Replaced by WISER-Search, Sep 2025
o3 69%

Source: Official WISER-Atomic leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) o3 Sonar Pro 0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) o3

Source: Official WISER-Atomic 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 9 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access The tasks are private.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (10 entries).
  • Pass Models scored 6 models we track, plus 4 other entries on its leaderboard.
  • Note Newest score The newest came 14 months ago, in September 2025, for Gemini 2.5 Flash. That’s expected for a test replaced by WISER-Search.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is o3 (#84).
  • Pass Headroom The best is 69%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on parallel.ai: 7 rows for models we track and 4 other entries at the last read.
  • 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