Benchmark Almanac

OmniGameArena

GPT-5.5 0.47 leads since June 2026
Not in model cards

Models play games while response latency advances the game clock.

The June 2026 paper compares models under latency-aware game scoring. The abstract does not state the best score.

Released
June 2026
Kind
Video games
Level
Everyday
Scored
Settled by events
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Actions
Interaction
Agentic
Environment
OmniGameArena
Refresh
Live
Run by
Anyone
Strongest model tested
GPT-5.5 #21 on the capability index
Last model added
April 2026
Scores refreshed
November 20th, 2026
12
Entries on its own leaderboard, 10 models we track

GPT-5.5 leads with 0.47 among models released by April 2026 GPT-5.5 leads with 0.47 among models released by April 2026

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. The site reports each game separately. The headline is the cold-start score on ObstacleRun2D, its first solo game. 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 April 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 GPT-5.5 Cold start 0.47
  2. 2 Claude Opus 4.6 Cold start 0.33
  3. 3 Gemini 3 Flash Cold start 0.28
  4. 4 Claude Opus 4.7 Cold start 0.21
  5. 5 GPT-5.4 Cold start 0.12
  6. 6 Qwen3.5 397B-A17B Cold start 0.11
  7. 7 Kimi K2.5 Cold start 0.11
  8. 8 Gemini 3.1 Pro Cold start 0.10
  9. 9 Qwen3.5-122B-A10B Cold start 0.09
  10. 10 Claude Sonnet 4.6 Cold start 0.07
  11. 11 Open-P2P Cold start 0.06
  12. 12 NitroGen Cold start 0.03

Source: Official OmniGameArena leaderboard

#EntryScoreSettingDateSource
1 GPT-5.5 0.47 Cold start Apr 2026 Official leaderboard
2 Claude Opus 4.6 0.33 Cold start Feb 2026 Official leaderboard
3 Gemini 3 Flash 0.28 Cold start Dec 2025 Official leaderboard
4 Claude Opus 4.7 0.21 Cold start Apr 2026 Official leaderboard
5 GPT-5.4 0.12 Cold start Mar 2026 Official leaderboard
6 Qwen3.5 397B-A17B 0.11 Cold start Feb 2026 Official leaderboard
7 Kimi K2.5 0.11 Cold start Jan 2026 Official leaderboard
8 Gemini 3.1 Pro 0.10 Cold start Feb 2026 Official leaderboard
9 Qwen3.5-122B-A10B 0.09 Cold start Feb 2026 Official leaderboard
10 Claude Sonnet 4.6 0.07 Cold start Feb 2026 Official leaderboard
11 Open-P2P 0.06 Cold start Official leaderboard
12 NitroGen 0.03 Cold start Official leaderboard
#ModelScoreSettingDateSource
1 GPT-5.5 0.47 Cold start Apr 2026 Official leaderboard
2 Claude Opus 4.6 0.33 Cold start Feb 2026 Official leaderboard
3 Gemini 3 Flash 0.28 Cold start Dec 2025 Official leaderboard
4 Claude Opus 4.7 0.21 Cold start Apr 2026 Official leaderboard
5 GPT-5.4 0.12 Cold start Mar 2026 Official leaderboard
6 Qwen3.5 397B-A17B 0.11 Cold start Feb 2026 Official leaderboard
7 Kimi K2.5 0.11 Cold start Jan 2026 Official leaderboard
8 Gemini 3.1 Pro 0.10 Cold start Feb 2026 Official leaderboard
9 Qwen3.5-122B-A10B 0.09 Cold start Feb 2026 Official leaderboard
10 Claude Sonnet 4.6 0.07 Cold start Feb 2026 Official leaderboard

Rankings by part

We read 24 parts from the benchmark’s own leaderboard in 3 groups: solo, coop and pvp. Each ranks models on one part of the test. GPT-5.5 leads 14 of them, and 4 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

ObstacleRun2D

10 models we track have a score here.

  1. 1 GPT-5.5 0.47
  2. 2 Claude Opus 4.6 0.33
  3. 3 Gemini 3 Flash 0.28
  4. 4 Claude Opus 4.7 0.21
  5. 5 GPT-5.4 0.12
  6. 6 Qwen3.5 397B-A17B 0.11
  7. 7 Kimi K2.5 0.11
  8. 8 Gemini 3.1 Pro 0.10
  9. 9 Qwen3.5-122B-A10B 0.09
  10. 10 Claude Sonnet 4.6 0.07

Number one over time

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

OpenAI
Own leaderboard Not tested since Jun 2026
GPT-5.5 0.47

Source: Official OmniGameArena 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
0.00 0.10 0.20 0.30 0.40 0.50 2026 0.00 0.10 0.20 0.30 0.40 0.50 2026

Source: Official OmniGameArena 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 Games and long tasks

All 261 in Games and long tasks
  • ARC-AGI-3 In use Interactive game environments where agents must explore, infer goals and rules, and act efficiently without instructions. GPT-6.2 Astra 100%
  • Orak Fading LLM agents play 12 popular video games across most genres through an MCP interface. Each game scores in-game progress or outcomes, and the board ranks models by their average rank across the games. Gemini 2.5 Pro 3.90
  • MineDojo Fading Agents complete open-ended tasks in Minecraft, such as mining blocks and fighting mobs, from a large simulation suite. Programmatic checks score many tasks. Seed2.0 Pro 49%
  • TextQuests Only in system cards Agents play 25 classic interactive fiction games. The score is harmful actions per 100 steps, where lower is better. The board also reports game progress. Llama 4 Scout 7.00
  • GameWorld Only in system cards Multimodal game agents play 34 browser games across 170 tasks. Outcomes are checked from the game state. GPT-6.1 Terra 76.8%
  • Swarm Bench Only in system cards Models orchestrate agent swarms on complex tasks that benefit from coordinated decomposition and parallel execution. Kimi K3 76.3%

Data audit

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 7 months ago, in April 2026, for GPT-5.5. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (12 entries).
  • Pass Models scored 10 models we track, plus 2 other entries on its leaderboard.
  • Warning Newest score The newest came 7 months ago, in April 2026, for GPT-5.5.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.5 (#21).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on mxlin043.github.io: 10 rows for models we track and 2 other entries 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