Benchmark Almanac

MKA

Gemini 4 Neon 56.5% leads since November 2026
In use

Agents complete professional tasks whose work is visual, 200 tasks across 10 fields and 83 occupations, each about three to eight hours of expert work. An agentic grader checks each deliverable against an expert rubric of about 70 yes or no checks, weighted 75% on factual accuracy and 25% on visual design.

Artificial Analysis runs the 200-task set and keeps it private. Ten sample tasks are public on Hugging Face. Every model runs in the same agent harness, Stirrup. The grader is built on a model from outside Google, and experts agreed with it 96% of the time. Labs report Climb WSR, the weighted share of the harder rubric checks a model meets. We don't import Artificial Analysis's leaderboard, so scores here come from lab posts.

Released
November 2026
Kind
Tasks from real jobs
Level
Expert
Scored
Graded by a model
Answers
Open-ended
Tasks
Public, plus a private test set
Measures
Capability
Language
English
Interaction
Agentic
Environment
APIs and tools
Refresh
One fixed set
Run by
A host
Last in a launch post
November 2026
Last model added
November 2026
2
Models scored in lab cards
2
Launch posts list it, from 1 lab
1
System card reports it, from 1 lab

Gemini 4 Neon leads with 56.5%

Best score per model as labs report them in their own cards, drawn striped. Labs pick their own settings, so these compare less cleanly than independent runs.

  1. 1 Gemini 4 Neon 56.5%
  2. 2 Gemini 4 Hydrogen 53.4%

Source: Labs’ model cards

#ModelScoreSettingDateSource
1 Gemini 4 Neon 56.5% Nov 2026 Lab model card
2 Gemini 4 Hydrogen 53.4% Nov 2026 Lab model card

2 models have held number one in labs’ own numbers since its release in November 2026

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

Google DeepMind
Lab claims 2 leaders

Source: Labs’ model cards

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
Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2027 Near the ceiling (85%) Gemini 4 Neon 0% 20% 40% 60% 80% 100% 2027 Near the ceiling (85%) Gemini 4 Neon

Source: Labs’ model cards

One lab put it in a launch post in the last six months

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

Google DeepMind
DateLaunch postScoreAs the post writes it
Nov 18, 2026 Gemini 4 Neon 56.5 MKA (Climb WSR)
Nov 12, 2026 Gemini 4 Hydrogen 53.4 MKA (Climb WSR accuracy)

One system card reports it

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

DateDocumentScoreAs the document writes itSection
Nov 18, 2026 Gemini 4 Neon model card 56.5 MKA (Climb WSR) (results table, p.4) Capabilities

More in Economic work

All 210 in Economic work
  • JobBench In use 130 tasks from 35 occupations workers most want delegated. Agent works through messy reference files, graded by fact-anchored binary rubrics. GLM-5.3 61.4%
  • GDPval In use Real work tasks from 44 occupations with reference files. Experts blindly compare model deliverables with expert work. Metric is win-or-tie rate. Seed2.1 Pro 87.9%
  • GDPval-AA v2.1 In use Agents with shell and web access complete 220 GDPval gold tasks from 44 occupations. Blind pairwise comparisons give Elo ratings. Claude Opus 5.5 1,846
  • AA-Briefcase v1.1 In use Version 1.1 of Artificial Analysis's multi-hour office work evaluation, with Elo ratings fitted by Crowd-BT. Claude Opus 5.5 1,822
  • Agents' Last Exam v1.1 In use Agents complete 122 public long-horizon professional workflow tasks across 55 sub-industries. Deterministic graders check outcomes against hidden references. GPT-6.2 Astra 47.5%
  • CoWorkBench In use Agent completes long-horizon productivity tasks across computer science, finance, law and medicine. Qwen in-house scoring (method unpublished). Claude Fable 5 75.9%

Data audit

All 5 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
  • Note Independent runs Only labs’ own numbers, so no one else has checked them. Scores from launch posts (2 scores) and system cards (1 score).
  • Note Models scored Only 2 models we track.
  • Pass Newest score The newest is from November 2026, for Gemini 4 Neon.
  • Note Frontier models None of its models are on the capabilities index.
  • Pass Headroom The best is 56.5%, under 85%, so it still separates models.
Leaderboard import 1 note
  • Note Importer Artificial Analysis allows reuse of only its index numbers, so we link to its board instead.
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