Benchmark Almanac

LLM Game Benchmark

Claude 3.5 Sonnet 185.0 leads since June 2024
Not in model cards

Models compete in tic-tac-toe, Connect Four, Gomoku, and other grid games through a shared interface.

The public leaderboard compares Claude, Gemini, GPT, and Llama models. The checked page reports game outcomes but no single best aggregate score.

Released
January 2024
Kind
Puzzles and chess
Level
Everyday
Scored
Settled by events
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Actions
Interaction
Multi-agent
Items from
Live play or votes
Refresh
Live
Run by
Anyone
In views
Games, Agents, Kept fresh
Strongest model tested
Claude 3.5 Sonnet #158 on the capability index
Last model added
June 2024
Scores refreshed
November 20th, 2026
7
Entries on its own leaderboard, 3 models we track

Claude 3.5 Sonnet leads with 185.0 among models released by June 2024 Claude 3.5 Sonnet leads with 185.0 among models released by June 2024

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 June 2024, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Claude 3.5 Sonnet First player, all prompts and opponents 185.0
  2. 2 gpt-4o (snapshot unspecified) First player, all prompts and opponents 160.0
  3. 3 gemini-1.5-pro (snapshot unspecified) First player, all prompts and opponents 138.0
  4. 4 gpt-4-turbo (snapshot unspecified) First player, all prompts and opponents 137.0
  5. 5 gemini-1.5-flash (snapshot unspecified) First player, all prompts and opponents 129.0
  6. 6 Claude 3 Sonnet First player, all prompts and opponents 126.0
  7. 7 Llama 3-70B First player, all prompts and opponents 116.0

Source: Official LLM Game Benchmark leaderboard

#EntryScoreSettingDateSource
1 Claude 3.5 Sonnet 185.0 First player, all prompts and opponents Jun 2024 Official leaderboard
2 gpt-4o (snapshot unspecified) 160.0 First player, all prompts and opponents Official leaderboard
3 gemini-1.5-pro (snapshot unspecified) 138.0 First player, all prompts and opponents Official leaderboard
4 gpt-4-turbo (snapshot unspecified) 137.0 First player, all prompts and opponents Official leaderboard
5 gemini-1.5-flash (snapshot unspecified) 129.0 First player, all prompts and opponents Official leaderboard
6 Claude 3 Sonnet 126.0 First player, all prompts and opponents Feb 2024 Official leaderboard
7 Llama 3-70B 116.0 First player, all prompts and opponents Apr 2024 Official leaderboard
#ModelScoreSettingDateSource
1 Claude 3.5 Sonnet 185.0 First player, all prompts and opponents Jun 2024 Official leaderboard
2 Claude 3 Sonnet 126.0 First player, all prompts and opponents Feb 2024 Official leaderboard
3 Llama 3-70B 116.0 First player, all prompts and opponents Apr 2024 Official leaderboard

Rankings by part

We read 3 parts from the benchmark’s own leaderboard: Tic-tac-toe, Gomoku and Connect Four. Each ranks models on one part of the test. Claude 3.5 Sonnet leads 2 of them, and Claude 3 Sonnet leads the other one. Arrows show how far a model moved from its overall rank among the models we track.

Tic-tac-toe

3 models we track have a score here.

  1. 1 Claude 3.5 Sonnet 74.0
  2. 2 Llama 3-70B ↑1 41.0
  3. 3 Claude 3 Sonnet ↓1 36.0

2 models have held number one on the official leaderboard since its release in January 2024

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

Anthropic
Own leaderboard Not tested since Jun 2024

Source: Official LLM Game Benchmark 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
100.0 120.0 140.0 160.0 180.0 200.0 2024 100.0 120.0 140.0 160.0 180.0 200.0 2024

Source: Official LLM Game Benchmark 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 2 years ago, in June 2024, for Claude 3.5 Sonnet. 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 (7 entries).
  • Pass Models scored 3 models we track, plus 4 other entries on its leaderboard.
  • Warning Newest score The newest came 2 years ago, in June 2024, for Claude 3.5 Sonnet.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Claude 3.5 Sonnet (#158).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on research-outcome.github.io: 3 rows for models we track and 4 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