Benchmark Almanac

Economics Arena for Large Language Models

Claude 2 0.95 leads since January 2024
Not in model cards

Models choose numbers in beauty contests and place sealed bids in auctions. Researchers compare payoffs and measure how strategies change when players see previous rounds.

In January 2024, GPT-3.5 led the five-model senior group after 100 sessions, averaging 0.410 in beauty contests and 1.206 in auctions.

Made by
Shangmin Guo and colleagues
Released
January 2024
Kind
Multi-agent games
Level
University
Scored
Ranked by matches
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Actions
Interaction
Multi-agent
Environment
A simulator
Items from
Live play or votes
Refresh
Live
Run by
Anyone
Strongest model tested
Claude 2 #192 on the capability index
Last model added
July 2023
Scores refreshed
November 20th, 2026
5
Entries in its paper, 1 model we track

Claude 2 leads with 0.95 Claude 2 leads with 0.95

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports no overall score, so this is the plain mean of its six game and session payoffs. 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.

  1. 1 Claude 2 Senior environment, 20 sessions 0.95
  2. 2 GPT3.5 (snapshot unspecified) Senior environment, 100 sessions 0.81
  3. 3 GPT4 (snapshot unspecified) Senior environment, 100 sessions 0.63
  4. 4 Claude-I Senior environment, 60 sessions 0.59
  5. 5 Baichuan2 Senior environment, 20 sessions 0.46

Source: The Economics Arena for Large Language Models paper

Source: The Economics Arena for Large Language Models paper

#EntryScoreSettingDateSource
1 Claude 2 0.95 Senior environment, 20 sessions Jul 2023 Official leaderboard
2 GPT3.5 (snapshot unspecified) 0.81 Senior environment, 100 sessions Official leaderboard
3 GPT4 (snapshot unspecified) 0.63 Senior environment, 100 sessions Official leaderboard
4 Claude-I 0.59 Senior environment, 60 sessions Official leaderboard
5 Baichuan2 0.46 Senior environment, 20 sessions Official leaderboard
#ModelScoreSettingDateSource
1 Claude 2 0.95 Senior environment, 20 sessions Jul 2023 Official leaderboard

Number one over time

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

Anthropic
Benchmark paper Not tested since Jan 2024
Claude 2 0.95

Source: The Economics Arena for Large Language Models paper

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
In the benchmark’s paper
0.60 0.70 0.80 0.90 1.00 0.60 0.70 0.80 0.90 1.00

Source: Official Economics Arena for Large Language Models 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 3 years ago, in July 2023, for Claude 2. 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 benchmark’s paper (5 entries).
  • Pass Models scored 1 model we track, plus 4 other entries on its leaderboard.
  • Warning Newest score The newest came 3 years ago, in July 2023, for Claude 2.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Claude 2 (#192).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 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