Skip to main content

Vals Agent Poker Bench (Agent Poker Bench)

Which model can make the most money playing poker?

Data verified

How BenchLM shows Agent Poker Bench

BenchLM mirrors the public Vals AI Agent Poker Bench leaderboard captured from https://www.vals.ai/benchmarks/poker_agent and updated by Vals on December 23, 2025. The snapshot preserves overall scores, uncertainty, latency, cost-per-test metadata, and task-level scores where Vals publishes them.

Agent Poker Bench is display only on BenchLM. Vals proprietary or Vals-hosted aggregate views are useful context, but BenchLM does not use them as weighted ranking inputs or as a replacement for benchmark-native source records.

17 Vals rows1 task viewsprivate datasetTasks: OverallDisplay only

Agent Poker Bench score on Agent Poker Bench — December 23, 2025

BenchLM mirrors the published agent poker bench score view for Agent Poker Bench. GPT-5.2 leads the public snapshot at 1131.83% , followed by GPT-5 (1103.18%) and Gemini 3 Flash Preview (1100.21%). BenchLM does not use these results to rank models overall.

17 modelsExternal benchmark mirrorsCurrentDisplay onlyUpdated December 23, 2025

The published Agent Poker Bench snapshot is tightly clustered at the top: GPT-5.2 sits at 1131.83%, while the third row is only 31.62 points behind. The broader top-10 spread is 97.53 points, so the benchmark still separates strong models even when the leaders cluster.

17 models have been evaluated on Agent Poker Bench. The benchmark falls in the External benchmark mirrors category. BenchLM tracks this category separately from its weighted global scoring system, so these results are best compared on the dedicated Korean benchmark views. Agent Poker Bench is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About Agent Poker Bench

Year

2026

Tasks

Poker-playing agent trials

Format

Accuracy score

Difficulty

Strategic game-agent decision making

BenchLM mirrors the public Vals AI Agent Poker Bench leaderboard as display-only external evidence. The captured snapshot preserves overall scores, task-level scores where Vals publishes them, uncertainty, latency, and cost-per-test metadata. It is excluded from BenchLM weighted rankings.

BenchLM freshness & provenance

Version

Agent Poker Bench 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Agent Poker Bench score table (17 models)

1
GPT-5.2openai/gpt-5.2-2025-12-11
1131.83%
2
GPT-5openai/gpt-5-2025-08-07
1103.18%
3
Gemini 3 Flash Previewgoogle/gemini-3-flash-preview
1100.21%
4
DeepSeek V3p2 Thinkingfireworks/deepseek-v3p2-thinking
1090.30%
5
Grok 4.1 Fast Reasoninggrok/grok-4-1-fast-reasoning
1079.22%
6
Gemini 3 Pro Previewgoogle/gemini-3-pro-preview
1078.90%
7
DeepSeek V3p1fireworks/deepseek-v3p1
1058.23%
8
Claude Sonnet 4.5anthropic/claude-sonnet-4-5-20250929
1055.50%
9
GPT-5.1openai/gpt-5.1-2025-11-13
1038.59%
10
Grok 4 Fast Reasoninggrok/grok-4-fast-reasoning
1034.30%
11
Claude Opus 4.5anthropic/claude-opus-4-5-20251101
1033.38%
12
Gemini 2.5 Progoogle/gemini-2.5-pro
1032.60%
13
GPT Oss 120bfireworks/gpt-oss-120b
1015.33%
14
Kimi K2 Thinkingkimi/kimi-k2-thinking
1011.63%
15
Qwen3 Max Previewalibaba/qwen3-max-preview
994.51%
16
GLM 4.6zai/glm-4.6
945.76%
17
Llama4 Maverick Instruct Basicfireworks/llama4-maverick-instruct-basic
890.50%

FAQ

What does Agent Poker Bench measure?

Which model can make the most money playing poker?

Which model leads the published Agent Poker Bench snapshot?

GPT-5.2 currently leads the published Agent Poker Bench snapshot with 1131.83% agent poker bench score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on Agent Poker Bench?

17 AI models are included in BenchLM's mirrored Agent Poker Bench snapshot, based on the public leaderboard captured on December 23, 2025.

Last updated: December 23, 2025 · mirrored from the public benchmark leaderboard

The AI models change fast. We track them for you.

For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.