# Top Math AI this month

> Gemini leads at 93%, runner-up 3% across 3 winner-take-all outcomes — refreshed 4 min ago.

URL: https://simplefunctions.dev/odds/mathai
Updated: 2026-06-29T01:20:51.157Z
Category: technology
Status: active
Closes: 2026-06-30

## Headline

- Leader: Gemini at 93%
- Runner-up: Claude at 3%
- Outcomes: 3 (winner-take-all)
- Venue: Kalshi (3 contracts)
- 24h volume: $678

## Bound contracts (3)

| Outcome | Price | 24h | Volume | Venue | Slug |
|---|---|---|---|---|---|
| Gemini | 93¢ | ±0 | $165 | kalshi | /markets/top-math-ai-this-month-gemini-kalshi-kxmathai-26jun30-gemi |
| Claude | 3¢ | +3pp | $262 | kalshi | /markets/top-math-ai-this-month-claude-kalshi-kxmathai-26jun30-clau |
| ChatGPT | 3¢ | +14pp | $250 | kalshi | /markets/top-math-ai-this-month-chatgpt-kalshi-kxmathai-26jun30-chat |

## 30-day trajectory

| Day | Gemini | Claude | ChatGPT |
|---|---|---|---|
| 2026-06-10 | 28 | 31 | 6 |
| 2026-06-15 | 61 | 30 | 2 |
| 2026-06-22 | 74 | 18 | 2 |
| 2026-06-27 | 92 | 5 | 16 |

_18 days of price history captured. Each row is the daily mean of intraday 5-min captures._

## What moved the line

- 2026-06-27 · ChatGPT +14pp 2→16¢ · kalshi
- 2026-06-24 · Claude −12pp 16→4¢ · kalshi
- 2026-06-24 · Gemini +9pp 78→87¢ · kalshi
- 2026-06-25 · Gemini +7pp 87→94¢ · kalshi
- 2026-06-23 · Gemini +4pp 74→78¢ · kalshi

## Analysis

This probability reflects market expectations for which AI system will be ranked as the top performer on mathematical reasoning benchmarks during June 2026. Gemini is currently the market leader at 56%, with Claude at 39% and ChatGPT at 4%. The assessment depends primarily on how different AI systems perform on standardized math evaluation frameworks released or updated this month. Key drivers include recent benchmark releases, performance on competitions like the International Mathematical Olympiad or similar assessments, and how different providers measure and publicize their results. Resolution will likely depend on which model demonstrates superior performance on verifiable mathematical problem-solving tasks released by major AI research organizations or independent evaluators during this period.

### Key factors

- Benchmark results released by major organizations (OpenAI, Google DeepMind, Anthropic) during June 2026 on standardized math evaluation sets
- Performance on mathematical olympiad-style problems or other third-party mathematical reasoning competitions active this month
- Publication dates and methodologies of any major peer-reviewed evaluations comparing AI systems on mathematical tasks
- Market participants' weighting of different evaluation sources and their perceived credibility for ranking math capability
- Volume concentration ($478 vs $413 vs $136 24h) suggesting unequal confidence levels across outcomes rather than genuine uncertainty

## Methodology

Headline is the **leader's price**, not an arithmetic mean — averaging disjoint winner-take-all outcomes is meaningless. Per-outcome prices come from the venue's last-traded mid; cross-venue values are simple means across contracts on each venue.

## How to use this data

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

## License

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