BoardBench 0.2
Version 0.2
Models choose one move in each of 30 board positions across ten games. An engine grades each legal move and assigns zero to illegal moves.
The maker ranks eight models. GPT-6 Astra scored 67.2 out of 100 and Gemini 4 Argon scored 66.3.
- Made by
- BoardBench
- Released
- October 2026
- Kind
- Puzzles and chess
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- New versions replace it
- Run by
- Anyone
- Based on
- BoardBench 0.1
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- October 2026
- Scores refreshed
- November 20th, 2026
GPT-6 Astra leads with 67.2
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart.
- 1 GPT-6 Astra high 67.2
- 2
Gemini 4 Argon high 66.3
- 3 GPT-6.1 Sol high 56.4
- 4 GLM-5.3-Flash high 43.9
- 5 GPT-6 Luna high 42.5
- 6
DeepSeek V4.1 Flash high 39.9
- 7 Claude Haiku 5.5 high 39.0
- 8 Claude Opus 5.5 high 37.6
Source: Official BoardBench 0.2 leaderboard
| # | Model | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | GPT-6 Astra | 67.2 | high | Sep 2026 | boardbench.dev | Official leaderboard |
| 2 | | 66.3 | high | Sep 2026 | boardbench.dev | Official leaderboard |
| 3 | GPT-6.1 Sol | 56.4 | high | Sep 2026 | boardbench.dev | Official leaderboard |
| 4 | GLM-5.3-Flash | 43.9 | high | Aug 2026 | boardbench.dev | Official leaderboard |
| 5 | GPT-6 Luna | 42.5 | high | Sep 2026 | boardbench.dev | Official leaderboard |
| 6 | | 39.9 | high | Sep 2026 | boardbench.dev | Official leaderboard |
| 7 | Claude Haiku 5.5 | 39.0 | high | Oct 2026 | boardbench.dev | Official leaderboard |
| 8 | Claude Opus 5.5 | 37.6 | high | Sep 2026 | boardbench.dev | Official leaderboard |
Rankings by part
We read 10 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Xiangqi, Chess and Go. GPT-6 Astra leads 5 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.
Xiangqi
8 models we track have a score here.
- 1 GPT-6 Astra 88.3
- 2 GPT-6.1 Sol ↑1 88.3
- 3
Gemini 4 Argon ↓1 55.2
- 4 GLM-5.3-Flash 55.0
- 5 Claude Opus 5.5 ↑3 55.0
- 6
DeepSeek V4.1 Flash 33.3
- 7 GPT-6 Luna ↓2 21.9
- 8 Claude Haiku 5.5 ↓1 0.00
Chess
8 models we track have a score here.
- 1
Gemini 4 Argon ↑1 66.7
- 2 GLM-5.3-Flash ↑2 33.3
- 3 GPT-6 Astra ↓2 33.3
- 4
DeepSeek V4.1 Flash ↑2 33.3
- 5 Claude Opus 5.5 ↑3 33.3
- 6 GPT-6.1 Sol ↓3 33.3
- 7 GPT-6 Luna ↓2 0.00
- 8 Claude Haiku 5.5 ↓1 0.00
Go
8 models we track have a score here.
- 1 Claude Opus 5.5 ↑7 67.8
- 2
Gemini 4 Argon 67.1
- 3 Claude Haiku 5.5 ↑4 66.7
- 4 GPT-6 Luna ↑1 66.7
- 5 GPT-6 Astra ↓4 33.9
- 6 GPT-6.1 Sol ↓3 33.3
- 7 GLM-5.3-Flash ↓3 33.3
- 8
DeepSeek V4.1 Flash ↓2 33.3
Backgammon
8 models we track have a score here.
- 1 Claude Haiku 5.5 ↑6 100.0
- 2 GPT-6 Astra ↓1 88.6
- 3
DeepSeek V4.1 Flash ↑3 88.6
- 4
Gemini 4 Argon ↓2 88.6
- 5 GPT-6 Luna 75.7
- 6 Claude Opus 5.5 ↑2 66.4
- 7 GPT-6.1 Sol ↓4 53.0
- 8 GLM-5.3-Flash ↓4 44.2
Shogi
8 models we track have a score here.
- 1 GPT-6.1 Sol ↑2 100.0
- 2
Gemini 4 Argon 79.4
- 3 GPT-6 Astra ↓2 69.0
- 4 GPT-6 Luna ↑1 55.8
- 5 GLM-5.3-Flash ↓1 45.6
- 6 Claude Opus 5.5 ↑2 45.6
- 7
DeepSeek V4.1 Flash ↓1 40.4
- 8 Claude Haiku 5.5 ↓1 22.4
Scrabble
8 models we track have a score here.
- 1 GPT-6 Astra 91.4
- 2
Gemini 4 Argon 91.4
- 3 GLM-5.3-Flash ↑1 56.0
- 4 GPT-6.1 Sol ↓1 53.9
- 5 GPT-6 Luna 36.1
- 6 Claude Haiku 5.5 ↑1 32.2
- 7
DeepSeek V4.1 Flash ↓1 22.1
- 8 Claude Opus 5.5 14.5
Kalah
8 models we track have a score here.
- 1 GPT-6 Astra 100.0
- 2
DeepSeek V4.1 Flash ↑4 66.7
- 3 GPT-6.1 Sol 66.7
- 4
Gemini 4 Argon ↓2 66.7
- 5 Claude Haiku 5.5 ↑2 66.7
- 6 GLM-5.3-Flash ↓2 33.3
- 7 Claude Opus 5.5 ↑1 33.3
- 8 GPT-6 Luna ↓3 33.3
Gomoku
8 models we track have a score here.
- 1 GPT-6 Astra 45.9
- 2 GLM-5.3-Flash ↑2 34.0
- 3 Claude Haiku 5.5 ↑4 19.1
- 4 GPT-6 Luna ↑1 13.5
- 5
DeepSeek V4.1 Flash ↑1 13.1
- 6 GPT-6.1 Sol ↓3 13.1
- 7 Claude Opus 5.5 ↑1 12.6
- 8
Gemini 4 Argon ↓6 12.6
Othello
8 models we track have a score here.
- 1 GPT-6 Astra 55.1
- 2 GPT-6 Luna ↑3 55.1
- 3 GPT-6.1 Sol 55.1
- 4
Gemini 4 Argon ↓2 55.1
- 5 GLM-5.3-Flash ↓1 37.8
- 6
DeepSeek V4.1 Flash 34.5
- 7 Claude Haiku 5.5 2.67
- 8 Claude Opus 5.5 0.43
Connect Four
8 models we track have a score here.
- 1
Gemini 4 Argon ↑1 80.4
- 2 Claude Haiku 5.5 ↑5 80.4
- 3 GLM-5.3-Flash ↑1 66.7
- 4 GPT-6 Astra ↓3 66.7
- 5 GPT-6 Luna 66.7
- 6 GPT-6.1 Sol ↓3 66.7
- 7 Claude Opus 5.5 ↑1 47.1
- 8
DeepSeek V4.1 Flash ↓2 33.3
The best score, 67.2, costs $0.56 a task
Runs on the cost frontier score higher than any run that's cheaper. Gemini 4 Argon at high comes within 0.9 of the best for $0.28 a task, about half the cost. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official BoardBench 0.2 leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| GPT-6 Astra | high | 67.2 | $0.56 | ||
| high | 66.3 | $0.28 | |||
| GPT-6.1 Sol | high | 56.4 | $0.10 | ||
| GLM-5.3-Flash | high | 43.9 | $0.01 | ||
| GPT-6 Luna | high | 42.5 | $0.004 | ||
| high | 39.9 | $0.03 | |||
| Claude Haiku 5.5 | high | 39.0 | $0.003 | ||
| Claude Opus 5.5 | high | 37.6 | $0.08 |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official BoardBench 0.2 leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official BoardBench 0.2 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 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
All 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (8 entries).
- Pass Models scored 8 models we track.
- Pass Newest score The newest is from October 2026, for Claude Haiku 5.5.
- Pass Frontier models 4 of the top 10 have a score, led by GPT-6 Astra (#4).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on boardbench.dev: 8 rows for models we track 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.