# Game Arena

> Kaggle Game Arena fits one Bradley-Terry rating to results across strategic games. Matches played and games covered accompany the rating; it is not a percentage or a chess Elo rating.

Canonical page: https://benchlm.ai/benchmarks/game-arena

- Category: [Reasoning](/reasoning)
- Last updated: October 19, 2026

Evaluation results published by [Kaggle](https://www.kaggle.com/benchmarks/kaggle/game-arena). undefined

Kaggle labels this benchmark Apache 2.0. We retain aggregate measurements with attribution and source links. That declaration does not establish rights to third-party documents, videos, or other underlying task material; no task contents are included. [Original article terms](https://www.apache.org/licenses/LICENSE-2.0).

Game Arena fits a pooled Bradley-Terry model to win, loss, and draw outcomes across its games. Each game receives equal total weight, and only the core variant counts when a game has several formats. The published Score is a relative rating, with matches played and games covered retained for each model.

The rating depends on this opponent pool and game mix. It is neither a percentage nor a chess Elo rating, and a model with fewer covered games has a different evidence base. Published interval widths remain in the source measurements without an inferred confidence level.

The complete official download includes models hidden by the source page's default filters. Source names and task versions stay separate from canonical model profiles; these results do not enter overall or category rankings.

These are published source configurations. Compare the task version and disclosed settings before treating a score difference as a model difference.

- [Official Kaggle leaderboard](https://www.kaggle.com/benchmarks/kaggle/game-arena)
- [Official leaderboard JSON](https://www.kaggle.com/api/v1/benchmarks/kaggle/game-arena/leaderboard)
- [Evaluation method](https://www.kaggle.com/game-arena-faq)
- [Benchmark-page Apache 2.0 declaration](https://www.apache.org/licenses/LICENSE-2.0)

## About Game Arena

- Year: 2025
- Tasks: Strategic games; per-model coverage retained
- Format: Pooled pairwise game outcomes
- Paper: [Game Arena methodology](https://www.kaggle.com/game-arena-faq)

Game Arena fits a pooled Bradley-Terry model to win, loss, and draw outcomes across its games. Each game receives equal total weight, and only the core variant counts when a game has several formats. The published Score is a relative rating, with matches played and games covered retained for each model. The rating depends on this opponent pool and game mix. It is neither a percentage nor a chess Elo rating, and a model with fewer covered games has a different evidence base. Published interval widths remain in the source measurements without an inferred confidence level. The complete official download includes models hidden by the source page's default filters. Source names and task versions stay separate from canonical model profiles; these results do not enter overall or category rankings.

Game Arena is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (39 source rows)

| Rank | Model | Configuration | Creator | Score |
|------|-------|---------------|---------|-------|
| 1 | [Gemini 4 Argon](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 535 |
| 2 | [GPT-6 Astra](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 491 |
| 3 | [Claude Opus 5](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 436 |
| 4 | [GPT-6.1 Sol](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 436 |
| 5 | [Gemini 3.8 Flash](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 429 |
| 6 | [Claude Fable 5.1](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 418 |
| 7 | [GPT-5.5](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 407 |
| 8 | [Claude Opus 5.5](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 398 |
| 9 | [Gemini 3.1 Pro Preview](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 381 |
| 10 | [Gemini 3.7 Flash](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 368 |
| 11 | [GPT-5.6 Sol](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 352 |
| 12 | [GPT-5.4](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 352 |
| 13 | [Grok 4.7](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 335 |
| 14 | [GPT-6 Sol](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 331 |
| 15 | [Gemini 3.6 Flash](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 325 |
| 16 | [Claude Sonnet 5.5](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 324 |
| 17 | [Claude Opus 4.8](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 321 |
| 18 | [Gemini 3.5 Flash](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 321 |
| 19 | [Grok 4.6](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 316 |
| 20 | [GPT-5.2](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 283 |
| 21 | [Gemini 3 Flash Preview](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 278 |
| 22 | [o3](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 268 |
| 23 | [Claude Opus 4.6](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 259 |
| 24 | [Grok 4.5](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 258 |
| 25 | [Claude Sonnet 5](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 256 |
| 26 | [Claude Haiku 5.5](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 251 |
| 27 | [Claude Opus 4.7](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 209 |
| 28 | [Claude Sonnet 4.6](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 200 |
| 29 | [GPT-5.6 Terra](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 195 |
| 30 | [Grok 4.20 Reasoning](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 189 |
| 31 | [Grok 4](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 181 |
| 32 | [Claude Sonnet 4.5](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 173 |
| 33 | [GPT-6 Luna](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 169 |
| 34 | [GPT-5.6 Luna](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 164 |
| 35 | [GPT-5 mini](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 154 |
| 36 | [Grok 4.3](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 145 |
| 37 | [GPT-5.4 mini](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 140 |
| 38 | [Grok 4.1 Fast Reasoning](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 135 |
| 39 | [DeepSeek V3.2](https://www.kaggle.com/benchmarks/kaggle/game-arena) | Kaggle benchmark v1; task revision 1; Evaluated 2026-10-19 | — | 0 |

## FAQ

### What does Game Arena measure?

Kaggle Game Arena fits one Bradley-Terry rating to results across strategic games. Matches played and games covered accompany the rating; it is not a percentage or a chess Elo rating.

### Which source row has the highest reported Game Arena value?

Gemini 4 Argon has the highest reported Game Arena value at 535. These are published source configurations. Compare the task version and disclosed settings before treating a score difference as a model difference.

### How many models are evaluated on Game Arena?

The October 19, 2026 contains 39 AI models.

### Does Game Arena affect BenchLM's overall score?

Not directly. Game Arena is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.