# Will Grok be the first to hit 1550 on Text Arena

> Liquidity-weighted aggregate at 15% across 4 contracts — refreshed just now.

URL: https://simplefunctions.dev/odds/modelhigh
Updated: 2026-05-09T07:20:23.246Z
Category: general
Status: active
Closes: 2027-01-01

## Headline

- Probability: 15% (liquidity-weighted across 4 contracts)
- Venue: Kalshi (4 contracts)
- 24h volume: $237

## Bound contracts (4)

| Outcome | Price | 24h | Volume | Venue | Slug |
|---|---|---|---|---|---|
| ChatGPT | 7¢ | +2pp | $117 | kalshi | /markets/will-chatgpt-be-the-first-to-hit-1550-on-text-aren-kalshi-kxmodelhigh-27-1550-chat |
| Claude | 35¢ | ±0 | $115 | kalshi | /markets/will-claude-be-the-first-to-hit-1550-on-text-arena-kalshi-kxmodelhigh-27-1550-clau |
| Gemini | 12¢ | ±0 | $5 | kalshi | /markets/will-gemini-be-the-first-to-hit-1550-on-text-arena-kalshi-kxmodelhigh-27-1550-gemi |
| Grok | 7¢ | ±0 | $0 | kalshi | /markets/will-grok-be-the-first-to-hit-1550-on-text-arena-g-kalshi-kxmodelhigh-27-1550-grok |

## 30-day trajectory

| Day | Aggregate |
|---|---|
| 2026-04-09 | 24 |
| 2026-04-25 | 29 |
| 2026-05-02 | 20 |
| 2026-05-09 | 23 |

_29 days of price history captured. Each row is the daily mean of intraday 5-min captures._

## What moved the line

- 2026-05-02 · Claude +8pp 28→36¢ · kalshi
- 2026-05-07 · Claude +5pp 34→39¢ · kalshi
- 2026-05-08 · Claude −5pp 39→34¢ · kalshi
- 2026-05-07 · Gemini −4pp 15→11¢ · kalshi

## Analysis

This 17% probability reflects market expectations that Grok will be the first AI system to achieve a 1550 score on Text Arena in 2026. The low odds suggest skepticism about Grok's near-term performance relative to competitors like Claude and Google's AI models. Market participants appear to weight Claude's current capabilities more heavily, as evidenced by its 36% probability on a similar Kalshi contract. The outcome depends primarily on the relative speed at which each AI company improves their models and achieves benchmark scores this year. Resolution will occur when any AI system first reaches the 1550 threshold on Text Arena, which will likely happen gradually as models are updated and new versions released throughout 2026. The timing of major model releases and benchmark updates from Anthropic, Google, and OpenAI will be critical determinants.

### Key factors

- Grok's recent benchmark performance relative to Claude, Google Gemini, and OpenAI's latest models on similar evaluation metrics
- The frequency and magnitude of model updates from xAI versus competitor releases planned for 2026
- Current market participants are pricing Claude as 2.1x more likely to hit 1550 first, suggesting confidence in Anthropic's development trajectory
- The Text Arena benchmark's difficulty rating and whether intermediate scores suggest any model is approaching the 1550 threshold
- Trading volume and contract spreads suggest moderate uncertainty, with 51¢ on "None in 2026" indicating meaningful probability that no system reaches 1550 this year

## Methodology

Probability is **liquidity-weighted** across all bound Kalshi/Polymarket contracts: Σ(price × volume) ÷ Σ(volume). 30-day trajectory uses the daily mean of intraday 5-min captures. 24h delta = today's mean − yesterday's mean. Movement events are ≥3pp daily moves in the last 7 days.

## How to use this data

- HTML: https://simplefunctions.dev/odds/modelhigh
- JSON: https://simplefunctions.dev/api/public/odds?slug=modelhigh

## License

CC-BY-4.0. Attribute "SimpleFunctions" with a link to https://simplefunctions.dev. See https://simplefunctions.dev/legal for terms.