Atlas

Benchmarks

Prophet Arena Arena Score (Fixed Context)

Prophet Arena (UChicago SIGMA Lab with Kalshi, arXiv 2510.17638) has models forecast open Kalshi prediction-market events and scores them once the events resolve; in the Fixed Context track each model makes one call on a centrally curated research context, with no web search or tools. The Arena score is each forecaster's skill from an item-response fit over every resolved event and forecaster, anchored so the market's own prices sit at zero skill, translated to predicted 1 - Brier on one shared reference set and shown x100. The fit is joint across the cohort and refit as events resolve, so every value moves with the cohort and the score is diagnostic.

Models
20
Top score
85.5
Leader
Claude Opus 5.5
Updated
Nov 14, 2026
Resolution
—
Saturation
—

No signal or difficulty estimate. Held out of the fit by design.

Organizations
20 dated models · 6 frontier modelsClosed weightsOpen weights
Data: Prophet Arenaatlas.village.dev

Prophet Arena Arena Score (Fixed Context) leaderboard

#ModelSettingScoreSource
1Claude Opus 5.5not reported
85.5
2Kimi K3.1 Pronot reported
85.4
3Claude Haiku 5.5not reported
85.4
4Gemini 4 Argonnot reported
85.3
5Claude Sonnet 5.5not reported
85.3
6Gemini 3.8 Flashnot reported
85.3
7GPT-6.1 Terranot reported
85.2
8Muse Wondernot reported
85.2
9Claude Fable 5.1not reported
85.0
10Grok 4.6not reported
85.0
11Claude Fable 5not reported
84.9
12Gemini 3.1 Pro Previewnot reported
84.9
13GPT-5.6 Solnot reported
84.8
14GPT-6.1 Solnot reported
84.8
15GPT-6 Lunanot reported
84.8
16GPT-6 Astranot reported
84.7
17DeepSeek V4 Pro 0813not reported
84.6
18GLM-5.3not reported
84.6
19Kimi K3not reported
84.6
20Hy3not reported
84.6

Related benchmarks

Loading Atlas data…