Benchmark Almanac

OmniGUI

Gemini 3.1 Pro 65.4% leads since March 2026
Not in model cards

Models use screenshots, sound, and video to predict the next action in 29 phone apps. The grader compares each action with a human demonstration.

XPeng ranks nine models on 708 episodes with 2,572 actions after filtering invalid samples.

Made by
XPeng Motors
Released
March 2026
Kind
Phones
Level
Everyday
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
In and out
Screens, Audio, Video, Text → Actions
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Strongest model tested
Gemini 3.1 Pro #40 on the capability index
Last model added
February 2026
Scores refreshed
November 20th, 2026
9
Entries on its own leaderboard, 8 models we track

Gemini 3.1 Pro leads with 65.4% among models released by February 2026 Gemini 3.1 Pro leads with 65.4% among models released by February 2026

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. 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. This view shows only models we track, each at its best.

The newest model with a score here came out in February 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Gemini 3.1 Pro 65.4%
  2. 2 Gemini 3 Pro 63.7%
  3. 3 Gemini 3 Flash 61.4%
  4. 4 Gemini 2.5 Pro Jun 2025 44.1%
  5. 5 Gemini 2.5 Flash Sep 2025 37.8%
  6. 6 Qwen3-Omni 32.4%
  7. 7 VITA-1.5 12.1%
  8. 8 MiniCPM-o 4.5 4.90%
  9. 9 Baichuan-Omni-1.5 3.30%

Source: Official OmniGUI leaderboard

#EntryScoreSettingDateSource
1 Gemini 3.1 Pro 65.4% Feb 2026 Official leaderboard
2 Gemini 3 Pro 63.7% Nov 2025 Official leaderboard
3 Gemini 3 Flash 61.4% Dec 2025 Official leaderboard
4 Gemini 2.5 Pro Jun 2025 44.1% Jun 2025 Official leaderboard
5 Gemini 2.5 Flash Sep 2025 37.8% Sep 2025 Official leaderboard
6 Qwen3-Omni 32.4% Official leaderboard
7 VITA-1.5 12.1% Dec 2024 Official leaderboard
8 MiniCPM-o 4.5 4.90% Feb 2026 Official leaderboard
9 Baichuan-Omni-1.5 3.30% Jan 2025 Official leaderboard
#ModelScoreSettingDateSource
1 Gemini 3.1 Pro 65.4% Feb 2026 Official leaderboard
2 Gemini 3 Pro 63.7% Nov 2025 Official leaderboard
3 Gemini 3 Flash 61.4% Dec 2025 Official leaderboard
4 Gemini 2.5 Pro Jun 2025 44.1% Jun 2025 Official leaderboard
5 Gemini 2.5 Flash Sep 2025 37.8% Sep 2025 Official leaderboard
6 VITA-1.5 12.1% Dec 2024 Official leaderboard
7 MiniCPM-o 4.5 4.90% Feb 2026 Official leaderboard
8 Baichuan-Omni-1.5 3.30% Jan 2025 Official leaderboard

Rankings by part

We read 24 parts from the benchmark’s own leaderboard in 6 groups: localization, semantic understanding, cross-modal discrimination, temporal reasoning, instant response and overall. Each ranks models on one part of the test. Gemini 3.1 Pro leads 20 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

Type Match

8 models we track have a score here.

  1. 1 Gemini 3.1 Pro 87.9%
  2. 2 Gemini 3 Pro 86.3%
  3. 3 Gemini 2.5 Pro Jun 2025 ↑1 86.1%
  4. 4 Gemini 3 Flash ↓1 85%
  5. 5 Gemini 2.5 Flash Sep 2025 75.1%
  6. 6 VITA-1.5 48.4%
  7. 7 MiniCPM-o 4.5 34.8%
  8. 8 Baichuan-Omni-1.5 19.5%

Number one over time

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

Google DeepMind
Own leaderboard Not tested since Mar 2026

Source: Official OmniGUI 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 2026 Near the ceiling (85%) Gemini 3.1 Pro Gemini 2.5 Pro VITA-1.5 0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Gemini 3.1 Pro Gemini 2.5 Pro

Source: Official OmniGUI 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.

More in Computer and browser use

All 119 in Computer and browser use
  • BrowseComp In use Hard-to-find facts that need persistent web browsing. Short verifiable answers graded for exact correctness. Claude Fable 5 93.3%
  • ScreenSpot-Pro In use GUI grounding on high-resolution professional-software screenshots. The model must locate the target UI element. GPT-6 Astra 92.7%
  • AndroidWorld In use Agents complete 116 tasks across 20 real Android apps in an emulator. Each task checks the device's system state to judge success. GPT-6 Astra 100%
  • OSWorld 2.1 In use Agents complete 108 long-horizon workflows across 31 self-hosted websites and desktop apps, averaging 318 tool calls. Scored by binary completion and checkpoint partial credit. Claude Opus 5 44.3%
  • WebArena-Verified In use Agents complete 812 audited WebArena tasks on self-hosted websites. Deterministic evaluators check the agent's answer and captured network traces. Muse Spark 1.1 69%
  • OSWorld 2.1 (offline subset) In use Agents complete the 82 OSWorld 2.1 tasks on the official offline list, with no internet access. Scored by checkpoint partial credit and strict pass rate. Claude Fable 5.2 89.3%

Data audit

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 9 months ago, in February 2026, for Gemini 3.1 Pro. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (9 entries).
  • Pass Models scored 8 models we track, plus 1 other entry on its leaderboard.
  • Warning Newest score The newest came 9 months ago, in February 2026, for Gemini 3.1 Pro.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 3.1 Pro (#40).
  • Pass Headroom The best is 65.4%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on omni-gui.github.io: 8 rows for models we track and 1 other entry at the last read.
  • Pass Last read November 20th, 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